Steering

Follow this topic Ask about this topic

Momentum

41 papers in the last four weeks, up 242% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 236

May 13, 2026stat.AP

Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts

The rapid advancement of large language models (LLMs) has made machine-generated text increasingly difficult to distinguish from human-written text. While recent studies explore leveraging internal representations of language models to uncover deeper detection signals, these raw features often exhibit substantial overlap between classes, limiting their discriminative power. To address this challenge, we propose Steer-to-Detect (\texttt{S2D}), a two-stage framework for detecting LLM-generated text. In the first stage, \texttt{S2D} learns a steering vector that is injected into the hidden states of a frozen observer LLM, producing representations with improved class separability. In the second stage, detection is performed via a hypothesis testing procedure based on the steered representations. We establish finite-sample, high-probability guarantees for Type I and Type II errors, providing a theoretical characterization of the procedure. Empirically, \texttt{S2D} achieves strong and consistent performance across a range of settings, including out-of-distribution scenarios and adversarial perturbations.

Luxu Liang, Xiang Li

Tsinghua University · University of Pennsylvania

Machine-Generated Text Detection Large Language Model Hallucination Text Analysis and Detection Hidden States Steering

May 12, 2026cs.LG

WriteSAE: Sparse Autoencoders for Recurrent State

We introduce WriteSAE, a sparse autoencoder for the matrix updates written into recurrent language-model state. In Gated DeltaNet, Mamba-2, and RWKV-7, each token writes a matrix-shaped update to a recurrent cache; a residual-stream SAE has vector-shaped atoms and cannot replace that update directly. WriteSAE learns rank-1 matrix atoms with the same shape as the model's own write. This lets us test a direct replacement: at positions where the SAE activates an atom, we remove the model's write, insert the atom scaled by its SAE activation, and continue the forward pass. The atom gives a closer final token distribution than deleting the write on 92.4% of evaluated positions; averaged per atom, the rate is 89.8%. For Gated DeltaNet, a formula using the forget gate, read query, and output embedding predicts the resulting logit change with

R^2 = 0.98

. The same replacement test transfers to Mamba-2-370M at 88.1%. In generation, the formula chooses a write direction; writing it into three consecutive cache positions at

3\times

the norm of the model's write makes tokens initially ranked 100--1000 by the unmodified model appear in 100% of continuations, up from 33.3%. To our knowledge this is the first cache-level steering intervention reported in a state-space or hybrid recurrent layer.

Jack Young

Indiana University

Recurrent State Gated Deltanet Steering

May 11, 2026cs.LG

Steerable Neural ODEs on Homogeneous Spaces

We introduce steerable neural ordinary differential equations on homogeneous spaces

M=G/H

. These models constitute a novel geometric extension of manifold neural ordinary differential equations (NODEs) that transport associated feature vectors transforming under the local symmetry group

H

. We interpret features as sections of associated vector bundles over

M

, and describe their evolution as parallel transport. This results in a coupled system of ODEs consisting of a flow equation on

M

and a steering equation acting on features. We show that steerable NODEs are

G

-equivariant whenever the vector field generating the flow and the connection governing parallel transport are both

G

-invariant. Furthermore, we demonstrate how steerable NODEs incorporate existing NODE models and continuous normalizing flows on Lie groups. Our framework provides the geometric foundation for learning continuous-time equivariant dynamics of general vector-valued features on homogeneous spaces.

Emma Andersdotter, Daniel Persson, Fredrik Ohlsson

Department of Mathematics and Mathematical Statistics Umeå University Umeå SE-901 87, Sweden · Department of Mathematical Sciences2026 Chalmers University of Technology and Gothenburg University Gothenburg SE-412 96, Sweden · Department of Mathematics and Mathematical Statistics 11 Umeå University Umeå SE-901 87, Sweden

Neural Ordinary Differential Equations Ordinary Differential Equations Equivariance Invertible Flows Steering

May 11, 2026cs.AI

Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values

Autonomous agents have rapidly matured as task executors and seen widespread deployment via harnesses such as OpenClaw. Safety concerns have rightly drawn growing research attention, and beneath them lie the values silently steering agent behavior. Existing value benchmarks, however, remain confined to LLMs, leaving agent values largely uncharted. From intuitive, empirical, and theoretical vantage points, we show that an agent's values diverge from those of its underlying LLM, and the agentic modality further introduces dataset-, evaluation-, and system-level challenges absent from text-only protocols. We close this gap with Agent-ValueBench, the first benchmark dedicated to agent values. It features 394 executable environments across 16 domains, offering 4,335 value-conflict tasks that cover 28 value systems and 332 dimensions. Every instance is co-synthesized through our purpose-built end-to-end pipeline and curated per-instance by professional psychologists. Each task ships with two pole-aligned golden trajectories whose checkpoints anchor a trajectory-level rubric-based judge. Benchmarking 14 frontier proprietary and open-weights models across 4 mainstream harnesses, we uncover three concerted findings. Agent values first manifest as a Value Tide of cross-model homogeneity beneath interpretable counter-currents. This tide bends non-additively under harness pull, and yet more decisively under deliberate steering via embedded skills. Together these results signal that the agent-alignment lever is shifting from classical model alignment and prompt steering toward harness alignment and skill steering.

Haonan Dong, Qiguan Feng, Kehan Jiang +3

State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · Key Laboratory of Machine Perception (Ministry of Education), Peking University · School of Software and Microelectronics, Peking University +1

Human Values Value Steering

May 10, 2026cs.CL

Exploitation Without Deception: Dark Triad Feature Steering Reveals Separable Antisocial Circuits in Language Models

We use sparse autoencoder (SAE) feature steering to amplify Dark Triad personality traits (Machiavellianism, narcissism, and psychopathy) in Llama-3.3-70B-Instruct and evaluate the resulting behavioral changes across five psychological instruments. The steered model becomes substantially more exploitative, aggressive, and callous on novel behavioral scenarios (d=10.62) while its cognitive empathy remains intact, reproducing the empathy dissociation characteristic of human Dark Triad populations. Critically, strategic deception is completely unaffected across all features, suggesting that exploitation and deception may operate through dissociable computational pathways in large language models. Individual feature analysis reveals non-redundant encoding, with each feature driving distinct antisocial mechanisms through separable computational pathways. We also show that feature discovery method itself modulates intervention depth: contrastively-discovered features change both self-report and behavior, while semantically-searched features change only self-report (d=12.65 between methods on behavior). These findings suggest that antisocial tendencies in at least one large language model comprise dissociable components rather than a unified construct, with implications for how such tendencies should be detected, measured, and controlled.

Cameron Berg, Roshni Lulla

1Reciprocal Research · 2Brain & Creativity Institute, University of Southern California

Deception Large Language Model Bias Exploitation Empathy Steering

May 10, 2026cs.CV

SwordBench: Evaluating Orthogonality of Steering Image Representations

Steering or intervening on model representations at inference time to correct predictions is essential for AI interpretability and safety, yet existing evaluation protocols are limited to ambiguous language modeling tasks. To address this gap, we introduce SwordBench, a benchmark for steering image representations of vision models across multiple backbones and concept removal tasks. Beyond a unified benchmarking suite, we propose new evaluation notions that uncover the second-order effects of orthogonalization among concept activation vectors for pragmatic steering. Specifically, cross-concept robustness measures the stability of concept detection performance across inputs orthogonalized against alternative concepts, and collateral damage quantifies whether steering inadvertently affects model performance on a downstream task for inputs lacking the bias. We find that although a linear support vector machine exhibits superior separability and orthogonality, it fails to achieve zero collateral damage, often trailing sparse autoencoders. In simpler regimes, both standard baselines and optimization-based methods fail to achieve perfect steering. The source code will be made available soon on GitHub.

Vladimir Zaigrajew, Dawid Pludowski, Hubert Baniecki +1

Centre for Credible AI Warsaw University of Technology Warsaw, Poland · University of Warsaw Warsaw, Poland

Steering Evaluation Benchmarks Vision Foundation Models Orthogonality Language Modeling

May 9, 2026cs.AI

Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas

Recent work shows that large language models (LLMs) encode behavioural traits ("personas") as linear directions in activation space, often called "persona vectors". Prior work has used such directions as static handles for behavioural steering. Building on this, we treat them as dynamic signals instead: probes we can monitor and intervene on as reasoning unfolds. We use the term polylogue to denote the time series of alignments between persona vectors and hidden activations over the course of generation. Experiments across four open-weight models show that polylogue features predict correctness on MMLU-Pro competitively with low-dimensional activation baselines, while remaining interpretable through their associated persona directions. They also suggest concrete steering targets, namely which latent directions to modulate at different stages of a response. We instantiate this as a simple paragraph-conditioned intervention that improves accuracy on three of four models, pointing to stage-aware latent steering as a promising direction for reasoning-time control. Together, this positions the polylogue as an interpretable tool for reasoning-time monitoring and intervention.

Nils A. Herrmann, Leander Girrbach, Kirill Bykov +1

1Technical University of Munich · 2Helmholtz Munich · 3Munich

LLM Reasoning Strategies Artificial Intelligence Personas Personality Agent Behavior Modeling Steering

May 9, 2026cs.LG

When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search

Activation steering offers a lightweight way to control LLMs without retraining, but its effectiveness varies sharply across concepts. Prior work often reads this variability as evidence that many concepts are not captured by a single steering direction. We argue instead that much of it reflects search difficulty: a useful rank-1 intervention often exists, but finding it can be expensive. We formalize rank-1 steering as a budget-constrained optimization over intervention layer and coefficient. Across concepts and model families, prompt-boundary directional alignment predicts where effective interventions occur, enabling geometry-guided search that reaches high utility with substantially fewer evaluations, reducing the trials needed to recover 95% of best-found utility by 39.8% on average across three model families. To explain why some concepts remain expensive even under better search, we introduce concept granularity, a measure of directional heterogeneity across contrastive contexts. Granularity distinguishes concepts whose difference vectors share a stable global direction from those where prompts agree locally within each input but the utility-maximizing direction rotates systematically across inputs. Higher granularity is associated with slower convergence and lower best-found performance (Pearson

r{=}0.44

with trials-to-95%,

r{=}{-}0.46

with best-found utility, both

p<0.001

). We present GRACE, a Granularity- and Representation-Aware Concept Engineering framework that uses activation geometry to diagnose the dominant source of steering difficulty, select the appropriate remedy, and allocate optimization effort efficiently. Our results shift the frame from "when does rank-1 fail?" to "when is rank-1 cheap and stable?", turning activation geometry from a descriptive tool into an actionable prior for LLM control.

John T. Robertson, Jianing Zhu, Haris Vikalo +1

The University of Texas at Austin

Linear Activation Steering Steering Latent Feature Interventions

May 8, 2026cs.LG

Can Revealed Preferences Clarify LLM Alignment and Steering?

LLMs are increasingly used to make or support high-stakes decisions under uncertainty, where alignment depends not only on factual accuracy but on how models weigh tradeoffs between different outcomes. We present an empirical pipeline for estimating the implied preferences that an LLM's observed choices optimize: we elicit the model's probability distribution over unknowns along with the choice it would make for the decision task and then fit a discrete choice model to recover the cost function that best rationalizes the model's decisions. We show how this revealed-preference description allows rigorous evaluation of whether models behave in a consistently goal-directed way, whether they can verbalize a description of their objectives which matches their revealed decision policy, and whether prompting can reliably steer those policies to implement a user-specified cost function. We apply this evaluation across four medical diagnosis domains and multiple frontier and open-source models. We find that while many models have a nontrivial degree of internal coherence, they also have significant weaknesses in faithfully reporting or adopting preferences in response to user direction.

Khurram Yamin, Jingjing Tang, Eric Horvitz +1

1Carnegie Mellon University · 2Microsoft Research

Large Language Model Alignment Large Language Model Decisions Preference Alignment Learning High-Stakes Domains Discrete Choice Models Steering

May 8, 2026cs.LG

Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models

Discrete diffusion language models (DLMs) generate text by iteratively denoising all positions in parallel, offering an alternative to autoregressive models. Controlled generation methods for DLMs, imported from autoregressive models, apply uniform intervention at every denoising steps. We show this uniform schedule degrades quality, and the damage compounds when multiple attributes are steered jointly. To diagnose the failure, we train sparse autoencoders on four DLMs (124M-8B parameters) and find that different attributes commit on distinct schedules, varying in timing, sharpness, and magnitude. For instance, topic commits within the first 2% of denoising, whereas sentiment emerges gradually over 20% of the process. Consequently, uniform intervention wastes steering capacity on steps where the target attribute has already solidified or has yet to emerge. We propose a novel adaptive scheduler that concentrates interventions on the steps where an attribute is actively forming and leaves the rest of generation untouched. The cost-control trade-off admits a closed-form characterization: the advantage of adaptive over uniform scheduling is governed by a single dispersion statistic of the commitment distribution. Across four DLMs and seven steering tasks, our method achieves precise control without the degradation typical of uniform interventions. Especially on challenging simultaneous three-attribute control, it reaches up to 93% steering strength, beating the strongest baseline by up to 15% points while preserving generation quality.

Hanhan Zhou, Shamik Roy, Rashmi Gangadharaiah

AWS AI Labs Santa Clara, CA 95054

Diffusion Language Models Steering Iterative Denoising Methods

May 8, 2026cs.CR

WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation

Browser agents are increasingly deployed in long-horizon tasks, which require executing extended action chains to accomplish user goals. However, this prolonged execution process provides attackers with more opportunities to inject malicious instructions. Existing prompt injection attacks against browser agents expose two key gaps: (1) low effectiveness, as attacks optimized for toy baselines fail to achieve end-to-end goals in real-world scenarios with complex environments and longer steps; (2) weak stealthiness, since most attacks pit the attack goal against the user goal, causing a significant drop in system usability under attack. To address these gaps, we propose WebTrap, a mid-task hijacking injection attack. It employs multi-step instruction fusion steering to seamlessly combine both goals, enabling the agent to resume the original user task after executing the attack goal. Furthermore, we design a context-grounded generation method to align the injected content with the task environment and system instructions, maximizing the hijacking success rate. Extensive experiments on two browser agent tasks, based on extended WASP and InjecAgent environments, demonstrate that our method achieves a high attack success rate while preserving the usability of the original system. We find that WebTrap exploits the agent's navigation vulnerabilities, binding the two goals so tightly that standard defense mechanisms cannot restore the system to normal operation. These findings reveal a critical vulnerability in agent systems during long-horizon tasks that they can be stealthily hijacked.

Zhichao Liu, Wenbo Pan, Haining Yu +3

Harbin Institute of Technology · City University of Hong Kong · City University of Macau

Hijacking Browser Agent Attack Stealthiness LLM Defense Mechanisms Steering

May 7, 2026cs.CL

Don't Lose Focus: Activation Steering via Key-Orthogonal Projections

Activation steering controls LLM behaviour towards target behaviour by intervening in internal representations, yet it often degrades reasoning and retrieval performance. We argue that a primary cause of this trade-off is attention rerouting: steering vectors alter query-key matching, shifting attention away from contextually important tokens toward less informative ones. To address this, we propose Steering via Key-Orthogonal Projections (SKOP), a steering method that constrains harmful attention rerouting without eliminating steering efficacy. SKOP achieves this by preserving attention patterns on a small set of focus tokens the model relies on for reasoning and retrieval, while allowing redistribution among less critical tail tokens. Across multiple steering benchmarks, we show that SKOP achieves the best joint steering-utility trade-off, reducing utility degradation by 5-7x while retaining over 95% of vanilla steering efficacy. Our results further suggest that, in long-context retrieval settings where vanilla steering approaches are ineffective, SKOP can maintain robust performance by avoiding attention rerouting.

Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik

University of Cambridge · University of Oxford

Linear Activation Steering Steering

May 7, 2026cs.LG

Molecules Meet Language: Confound-Aware Representation Learning and Chemical Property Steering in Transformer-VAE Latent Spaces

Molecular generative models often assume meaningful latent geometry, but apparent property predictability can reflect sequence-level shortcuts rather than chemical organization. We study this issue in an unsupervised autoregressive Transformer-VAE trained on SELFIES. After training, we freeze the model, fit linear probes to RDKit descriptors, and use the probe weights as candidate global steering directions. To separate chemical signal from SELFIES artifacts, we introduce a confound-aware evaluation based on residualization, confound-direction alignment analysis, and decoded-molecule traversal. This is necessary because SELFIES length, branch tokens, ring tokens, and token entropy are strongly encoded in the latent space. Under this confound-aware evaluation, we find robust monotonic steering for cLogP, FractionCSP3, HeavyAtomCount, TPSA, BertzCT, and HBA. Nonlinear probes further show that some properties admit stable global directions, while others are better described by local latent gradients. Overall, our results show that chemically meaningful steering can emerge in entangled molecular latent spaces, but only when validated through decoded molecules and controlled for representation-level confounds.

Zakaria Elabid, Jan Andrzejewski, Bartosz Brzoza +1

Helmholtz-Zentrum Dresden-Rossendorf Center for Advanced Systems Understanding

Molecular Representation Learning Molecular Generation Star-Vae Future Latent Representations Steering

May 7, 2026cs.AI

P-Guide: Parameter-Efficient Prior Steering for Single-Pass CFG Inference

Classifier-Free Guidance (CFG) is essential for high-fidelity conditional generation in flow matching, yet it imposes significant computational overhead by requiring dual forward passes at each sampling step. In this work, we address this bottleneck by introducing \textbf{P-Guide}, a framework that achieves high-quality guidance through a single inference pass by modulating only the initial latent state. We further show that, under a first-order approximation, P-Guide is equivalent to CFG in the sense that it steers generation from the prior space, without requiring explicit velocity field extrapolation during sampling. We consider both homoscedastic and \textbf{heteroscedastic} priors, and find that jointly modeling the mean and variance enables adaptive loss attenuation and improved robustness to data uncertainty. Extensive experiments demonstrate that P-Guide reduces inference latency by approximately 50% while maintaining fidelity and prompt alignment competitive with standard dual-pass CFG baselines.

Xin Peng, Ang Gao

School of Physical Science and Technology, Beijing University of Posts and Telecommunications, Beijing, China

Classifier-Free Guidance Generative Flow Networks High-Fidelity Conditional Generation Guidance Steering Extrapolation

May 7, 2026cs.LG

Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions

Recently, steering vectors (SVs) have emerged as an effective and lightweight approach to steer behaviors of large language models (LLMs), among which fine-tuned SVs are more effective than optimization-free ones. However, current approaches to fine-tuned SVs suffer from two limitations. First, they require careful selection of steering factors on a per-SV basis to balance steering effectiveness and generation quality at inference time. Second, they operate as full-sequence SVs (FSSVs), which can sacrifice generation quality regardless of factor selection due to excessive intervention on the model generation process. To address the first limitation, we propose joint training of steering factors and directions, such that post-hoc factor selection is no longer required. Using neural network scaling theory, we find that moderately large initialization sizes and learning rates for steering factors are essential for stability and efficiency of joint training. To tackle the second limitation, we draw inspiration from representation fine-tuning and introduce Prompt-only SV (PrOSV), an SV that intervenes only on a few prompt tokens. Our empirical results show that PrOSV outperforms traditional FSSVs on AxBench when using our joint training scheme. We also find that PrOSV achieves a better tradeoff between general model utility and adversarial robustness than FSSV.

Yuntai Bao, Qinfeng Li, Xinyan Yu +6

Zhejiang University · Innovation and Management Center, School of Software Technology (Ningbo), Zhejiang University · Ant Group

Steering Supervised Finetuning Post-Hoc Singing Voice Conversion

May 7, 2026cs.CL

Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention

Activation steering has emerged as a promising alternative for controlling language-model behavior at inference time by modifying intermediate representations while keeping model parameters frozen. However, large-scale evaluations such as AxBench show that existing steering methods are often outperformed by simple in-context prompting and generalize poorly to unseen concepts. We hypothesize that these limitations arise from unvalidated simplifying assumptions shared across prior methods, which typically restrict steering interventions to fixed, single-step, position-invariant transforms. We propose FLAS (Flow-based Activation Steering), which learns a general, concept-conditioned velocity field

v_t(h,t,c)

that transports unsteered activations to steered ones without relying on these assumptions. On AxBench, FLAS is the first learned method to consistently outperform prompting, reaching held-out harmonic means of

1.015

on Gemma-2-2B-IT and

1.113

on Gemma-2-9B-IT without per-concept tuning. Analysis of the learned flow shows curved, multi-step, token-varying trajectories, which suggests that previous hypotheses on activation space geometry might be incomplete.

Zehao Jin, Ruixuan Deng, Junran Wang +2

Georgia Institute of Technology

Linear Activation Steering Steering Model Activations Latent Feature Interventions Velocity Field

May 7, 2026cs.CV

Steering Visual Generation in Unified Multimodal Models with Understanding Supervision

Unified multimodal models are envisioned to bridge the gap between understanding and generation. Yet, to achieve competitive performance, state-of-the-art models adopt largely decoupled understanding and generation components. This design, while effective for individual tasks, weakens the connection required for mutual enhancement, leaving the potential synergy empirically uncertain. We propose to explicitly restore this synergy by introducing Understanding-Oriented Post-Training (UNO), a lightweight framework that treats understanding not only as a distinct task, but also a direct supervisory signal to steer generative representations. By incorporating objectives that encode semantic abstraction (captioning) and structural details (visual regression), we enable effective gradient flow from understanding to generation. Extensive experiments on image generation and editing demonstrate that understanding can serve as an effective catalyst for generation.

Zeyu Liu, Zanlin Ni, Yang Yue +5

1Tsinghua University · 2Kolors Team, Kuaishou Technology

Multimodal Generation Multimodal Model Steering Post-Training

May 7, 2026cs.AI

Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes

Can linearly decodable failure signals in LLM hidden states be leveraged to correct those failures? We investigate this classification-correction gap via Overthinking (OT)--a stable behavioral regime (Jaccard >= 0.81, 94% inter-annotator agreement) in medical QA where models answer correctly under resampling yet fail in extended chain-of-thought. OT is linearly decodable at 71.6% balanced accuracy (p < 10^{-16}). Yet five families of fixed linear steering (29 configurations, n=1,273) all yield Delta ~= 0, with identical null results cross-architecture (Qwen2.5-7B) and cross-domain (MMLU-STEM). Three convergent lines of evidence suggest representational entanglement: the OT direction has 85-88% overlap with task-critical computation (specificity ratio <= 0.152); non-targeted shared-direction steering damages accuracy (-12.1pp); and LEACE concept erasure damages accuracy (-3.6pp, p=0.01), while 10 random erasures produce Delta=+0.3pp. The per-instance probe-steering correlation is r=-0.002 (p=0.97). Positively, the same probe enables selective abstention (held-out AUROC=0.610, exceeding all five uncertainty baselines, p=0.009): decodable failure structure supports post-generation reliability estimation even when the fixed linear steering family cannot exploit it for correction.

Ming Liu

Amazon

Large Language Models Fail Decoding Linear Activation Steering Mmlu-Pro Steering Entanglement

May 6, 2026cs.LG

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior

Neural representations carry rich geometric structure; but does that structure causally shape behavior? To address this question, we intervene along paths through activation space defined by different geometries, and measure the behavioral trajectories they induce. In particular, we test whether interventions that respect the geometry of activation space will yield behaviors close to those the model exhibits naturally. Concretely, we first fit an activation manifold

M_h

to representations and a behavior manifold

M_y

to output probability distributions. We then test the link

M_h \leftrightarrow M_y

via interventions: we find that steering along

M_h

, which we term manifold steering, yields behavioral trajectories that follow

M_y

, while linear steering -- which assumes a Euclidean geometry -- cuts through off-manifold regions and hence produces unnatural outputs. Moreover, optimizing interventions in activation space to produce paths along

M_y

recovers activation trajectories that trace the curvature of

M_h

. We demonstrate this bidirectional relationship between the geometry of representation and behavior across tasks and modalities. In language models, we use reasoning tasks with cyclic and sequential geometries as well as in-context learning tasks with more complex graph geometries. In a video world model, we use a task with geometry corresponding to physical dynamics. Overall, our work shows that geometry in neural representation is not merely incidental, but is in fact the proper object for enabling principled control via intervention on internals. This recasts the core problem of steering from finding the right direction to finding the right geometry.

Daniel Wurgaft, Can Rager, Matthew Kowal +13

Stanford University · University College London · Northeastern University +2

Neural Network Representations Linear Activation Steering Neural Representations Steering Geometric Constraints Agent Behavior Modeling

May 6, 2026cs.LG

Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime

Agentic reinforcement learning (RL) for software engineering spends much of its compute on stateful trajectories whose grouped binary rewards are highly skewed and weakly contrastive. We frame this as pass-rate control and show that the binary reward-side signal is strongest near a 50% rollout pass rate under four criteria: reward entropy, group-filtering survival, leave-one-out (RLOO) advantage energy under Group Relative Policy Optimization (GRPO), and success-failure pair count. We propose Prefix Sampling (PS), which replays self-generated trajectory prefixes to steer skewed groups toward this regime: successful prefixes give mostly failing groups a head start, while failing prefixes handicap mostly passing groups. Replayed states are reconstructed through the existing rollout path, and replayed tokens are masked from the loss so optimization applies only to current-policy continuations. On SWE-bench Verified, PS reaches the baseline high-score regime within evaluation variability while delivering 2.01x and 1.55x end-to-end wall-clock speedups on Qwen3-14B and Qwen3-32B; the 14B peak improves from 0.274 to 0.295. AIME 2025 experiments on 4B and 8B show the same pass-rate-control pattern, and 4B ablations attribute gains to replay, bidirectional coverage, and adaptive control.

Tianshu Zhu, Wenyu Zhang, Xiaoying Zuo +8

Baidu

Rollout Pass-Rate Evaluation Steering

May 6, 2026cs.LG

Conceptors for Semantic Steering

Activation-based steering provides control of LLM behavior at inference time, but the dominant paradigm reduces each concept to a single direction whose geometry is left largely unexamined. Rather than selecting a single steering direction, we use conceptors: soft projection matrices estimated from activations pooled across both poles of a bipolar concept, which preserve the concept's full multidimensional subspace. A geometric analysis shows the bipolar subspace strictly subsumes the single-vector baseline. We further show that the conceptor quota provides a parameter-free layer-selection diagnostic, predicting concept separability with Pearson correlations up to r=0.96 across three instruction-tuned models and three semantic dimensions. Beyond selection, conceptors admit a closed-form Boolean algebra (AND, OR, NOT): we evaluate conceptor compositionality on thematically related sub-concepts. Across a systematic five-axis design-space evaluation, conceptors match or outperform additive baselines at layers where concept subspaces are multi-dimensional while producing substantially fewer degenerate outputs. Conceptor steering is a geometrically principled, compositional, and practically safer alternative to single-direction steering from a limited number of contrastive pairs.

Ilias Triantafyllopoulos, Young-Min Cho, Ren Tao +6

1New York University · University of Pennsylvania

Linear Activation Steering Steering Model Activations Compositionality Instruction-Tuned Models Subspace

May 5, 2026cs.CL

Steer Like the LLM: Activation Steering that Mimics Prompting

Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform compared to prompt-based approaches. We propose a framework that formulates prompt steering as a form of activation steering and investigates whether distilling successful prompt steering behavior into simpler, interpretable models can close this gap. Our analysis reveals that popular activation steering methods are not faithful to the mechanics of prompt steering, which applies strong interventions on some tokens while barely affecting others. Based on these insights, we introduce Prompt Steering Replacement (PSR) models that estimate token-specific steering coefficients from the activations themselves and are trained to imitate prompt-based interventions. Experiments on three steering benchmarks across multiple language models show that PSR models outperform existing activation steering methods, especially when controlling for high-coherence completions, and also compare favorably to prompting on AxBench and persona steering.

Geert Heyman, Frederik Vandeputte

Nokia Bell Labs, Belgium.

Linear Activation Steering Instruction-Tuned Models Steering Mimic

May 4, 2026cs.LG

Pairwise matrices for sparse autoencoders: single-feature inspection mislabels causal axes

The standard sparse-autoencoder (SAE) interpretability protocol labels each feature from its top-activating contexts and validates by single-feature steering. We propose the pairwise matrix protocol, co-varying steering coefficient with joint condition, and report three findings the standard one-corner protocol misses on Qwen3-1.7B-Instruct, replicated on Gemma-2-2B-it. First, a feature labelled "AI self-disclaimer" from its top contexts produces an inverted U-shape under a coefficient sweep: at c=+500 the model substitutes a fluent contemplative-philosopher voice for the disclaimer. Two further features anchor the criterion (one monotonic, one pure breakdown). Second, three near-orthogonal cluster-specific features that individually steer a philosophy-of-mind register, jointly suppressed at c=-500, damage grounded composition on recipes and engine explanations as well as introspective prompts; single-feature suppression at the same magnitude leaves controls intact. Third, a matched-geometry comparison of single-feature, joint, and random-direction perturbations (norm ~1.55, cosine ~0.64) yields three distinct output regimes: single-feature substitutes strategy filler, random direction substitutes diverse content, joint suppression alone produces placeholder text. Coherence loss is direction-pattern-dependent, not magnitude-dependent. All three findings reproduce on Gemma with model-specific damage signatures; the matched-geometry control is CI-separated by ~10x. The pipeline also locates a top causally responsible feature in Llama-3.1-8B-Instruct.

Michael A. Riegler, Birk Sebastian Frostelid Torpmann-Hagen

SimulaMet, Norway · Simula, Norway

Improving Sparse Autoencoders Model Activations Interpretability Single Pass Matrix Steering

May 3, 2026cs.CL

The Cylindrical Representation Hypothesis for Language Model Steering

Steering is a widely used technique for controlling large language models, yet its effects are often unstable and hard to predict. Existing theoretical accounts are largely based on the Linear Representation Hypothesis (LRH). While LRH assumes that concepts can be orthogonalized for lossless control, this idealized mapping fails in real representations and cannot account for the observed unpredictability of steering. By relaxing LRH's orthogonality assumption while preserving linear representations, we show that overlapping concept contributions naturally yield a sample-specific axis-orthogonal structure. We formalize this as the Cylindrical Representation Hypothesis (CRH). In CRH, a central axis captures the main difference between concept absence and presence and drives concept generation. A surrounding normal plane controls steering sensitivity by determining how easily the axis can activate the target concept. Within this plane, only specific sensitive sectors strongly facilitate concept activation, while other sectors can suppress or delay it. While the surrounding normal plane can be reliably identified from difference vectors, the sensitive sector cannot, introducing intrinsic uncertainty at the sector level. This uncertainty provides a principled explanation for why steering outcomes often fluctuate even when using well-aligned directions. Our experiments verify the existence of the cylindrical structure and demonstrate that CRH provides a valid and practical way to interpret model steering behavior in real settings: https://github.com/mbzuai-nlp/CRH.

Lang Gao, Jinghui Zhang, Wei Liu +7

Department of Natural Language Processing, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE · Department of Computer Science, National University of Singapore, Singapore

Linear Activation Steering Steering Hypothesis

May 3, 2026cs.CV

Referring Multiple Regions with Large Multimodal Models via Contextual Latent Steering

Large Multimodal Models (LMMs) have recently demonstrated their proficiency in holistic visual comprehension. However, most of them struggle to tackle region-level perception guided by visual prompts, especially for cases where multiple regions are referred simultaneously, or scenarios where global contexts are necessary for precise visual referring. We introduce Contextual Latent Steering (CSteer), a training-free approach for guiding general LMMs to refer multiple regions contextually, without expensive fine-tuning or architectural modifications. CSteer starts with pre-computing contextual vectors that implicitly represent visual referring behaviors, such as differentiation among regions and attention to global contexts, followed by representation editing during inference time. Experimental results on multiple datasets indicate that general LMMs with CSteer outperform tailored referring LMMs in most cases, suggesting a promising solution in training-free, and setting new state-of-the-art for this field. Code is available at https://github.com/xing0047/csteer.git.

Yun Xing, Hanyuan Liu, Jiahao Nie +1

Nanyang Technological University

Large Multimodal Models Region Steering

Apr 30, 2026quant-ph

Controlled Steering-Based State Preparation for Adversarial-Robust Quantum Machine Learning

Quantum machine learning (QML) provides a promising framework for leveraging quantum-mechanical effects in learning tasks. However, its vulnerability to adversarial perturbations remains a major challenge for practical deployment. In QML systems, small perturbations applied to classical inputs can propagate through the quantum encoding stage and distort the resulting quantum state, thereby degrading model performance. In this work, we propose a defense mechanism that replaces the conventional quantum encoding stage of a QML model with passive steering-based controlled state preparation, which guides the encoded state toward a controlled intermediate state. By tuning the steering strength and the number of steering iterations, the proposed method suppresses the influence of adversarial perturbations while maintaining high clean accuracy and improving adversarial accuracy. Experimental results demonstrate that the passive steering-based defense consistently improves adversarial accuracy across different QML models and datasets under gradient-based adversarial attacks, achieving adversarial accuracy improvements of up to 40.19%.

Sahan Sanjaya, Hari Krishna Parvatham, Emma Andrews +1

University of Florida, Gainesville, FL, USA

Quantum Machine Learning Quantum Error Correction LLM Defense Mechanisms Steering

Apr 28, 2026cs.CL

Investigating Linguistic Steering: An Analysis of Adjectival Effects Across Large Language Model Architectures

Achieving reliable control of Large Language Models (LLMs) requires a precise, scalable understanding of how they interpret linguistic cues. We introduce a rigorous framework using Shapley values to quantify the steering effect of individual adjectives on model performance, moving beyond anecdotal heuristics to principled attribution. Applying this method to 100 adjectives across a diverse suite of models (including o3, gpt-4o-mini, phi-3, llama-3-70b, and deepseek-r1) on the MMLU benchmark, we uncover several critical findings for AI alignment. First, we find that a small subset of adjectives act as disproportionately powerful "levers," yet their effects are not universal. Cross-model analysis reveals a "family effect": models of a shared lineage exhibit correlated sensitivity profiles, while architecturally distinct models react in a largely uncorrelated manner, challenging the notion of a one-size-fits-all prompting strategy. Second, focused follow-up studies demonstrate that the steering direction of these powerful adjectives is not intrinsic but is highly contingent on their syntactic role and position within the prompt. For larger models like gpt-4o-mini, we provide the first quantitative evidence of strong, non-additive interaction effects where adjectives can synergistically amplify, antagonistically dampen, or even reverse each other's impact. In contrast, smaller models like phi-3 exhibit a more literal and less compositional response. These results suggest that as models scale, their interpretation of prompts becomes more sophisticated but also less predictable, posing a significant challenge for robustly steering model behavior and highlighting the need for compositional and model-specific alignment techniques.

Lars Malmqvist

Research and Implementation

Linguistics Frozen Language Model Artificial Intelligence Alignment Steering

Apr 28, 2026eess.AS

ASAP: An Azimuth-Priority Strip-Based Search Approach to Planar Microphone Array DOA Estimation in 3D

Direction-of-arrival (DOA) estimation is an important task in microphone array processing and many downstream applications. The steered response power with phase transform (SRP-PHAT) method has been widely adopted for DOA estimation in recent years. However, accurate SRP-PHAT estimation in 3D scenarios requires evaluating steering responses over thousands of candidate directions, severely limiting real-time performance on resource-constrained platforms. This challenge becomes even more critical for planar arrays, which are widely used in robotics due to their structural simplicity. Motivated by the fact that azimuth estimation is usually more reliable than elevation estimation for most arrays, we propose ASAP, an azimuth-priority strip-based search approach to planar microphone array DOA estimation in 3D. In the first stage, ASAP performs coarse-to-fine region contraction within azimuthal strips to lock azimuth angles while retaining multiple maxima through spherical caps. In the second stage, it refines elevation along the great-circle arc between two close candidates. Extensive simulations and real-world experiments validate the efficiency and merits of the proposed method over existing approaches.

Ming Huang, Shuting Xu, Leying Yang +6

Southern University of Science and Technology, Shenzhen, China · Institute of Science Tokyo, Japan

Microphone Array Steering

Apr 25, 2026cs.SE

UniAda: Universal Adaptive Multi-objective Adversarial Attack for End-to-End Autonomous Driving Systems

Adversarial attacks play a pivotal role in testing and improving the reliability of deep learning (DL) systems. Existing literature has demonstrated that subtle perturbations to the input can elicit erroneous outcomes, thereby substantially compromising the security of DL systems. This has emerged as a critical concern in the development of DL-based safety-critical systems like Autonomous Driving Systems (ADSs). The focus of existing adversarial attack methods on End-to-End (E2E) ADSs has predominantly centered on misbehaviors of steering angle, which overlooks speed-related controls or imperceptible perturbations. To address these challenges, we introduce UniAda, a multi-objective white-box attack technique with a core function that revolves around crafting an image-agnostic adversarial perturbation capable of simultaneously influencing both steering and speed controls. UniAda capitalizes on an intricately designed multi-objective optimization function with the Adaptive Weighting Scheme (AWS), enabling the concurrent optimization of diverse objectives. Validated with both simulated and real-world driving data, UniAda outperforms five benchmarks across two metrics, inducing steering and speed deviations from 3.54 degrees to 29 degrees and 11 km per hour to 22 km per hour on average. This systematic approach establishes UniAda as a proven technique for adversarial attacks on modern DL-based E2E ADSs.

Jingyu Zhang, Jacky Wai Keung, Yan Xiao +3

Department of Computer Science, City University of Hong Kong, Hong Kong SAR · School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China

Black-Box Adversarial Attacks Steering

Apr 25, 2026cs.CL

From Concept-Aligned Tokens to Vulnerable Features: Mechanistic Localization of Jailbreaks

Jailbreak attacks expose a persistent failure mode in safety-aligned LLMs: models can be pushed into harmful behavior, but the internal representations enabling this shift remain poorly localized. Recent mechanistic safety studies often explain such behavior through broad representational objects, including global refusal directions, activation steering vectors, and refusal-related SAE features. We instead ask whether jailbreak vulnerability can be traced to finer-grained, prompt-conditioned SAE feature subgroups. We introduce a token-driven mechanistic pipeline that decomposes the residual stream of Gemma-2-2B into Sparse Autoencoder (SAE) features and identifies feature subgroups associated with unsafe behavior. Using single-category unsafe examples from BeaverTails to reduce cross-category interference, we extract harmful concepts from adversarial responses and align them with concept-relevant prompt tokens through subspace similarity. We then apply three feature-grouping strategies: cluster-based, hierarchical-linkage, and single-token-driven, to identify SAE feature subgroups across all 26 layers. Finally, we amplify the top features in each subgroup and evaluate the resulting generations with a standardized harmfulness judge. Single-token-driven grouping achieves harmfulness comparable to full cluster-based grouping, showing that individual harmful prompt tokens are sufficient to localize vulnerability-relevant SAE feature subgroups without relying on broader cluster-level aggregation. These subgroups appear across early and mid-to-late layers, with stronger concentration in mid-to-late layers, where targeted steering exposes specific model vulnerabilities. Overall, our results suggest that jailbreak susceptibility can be traced to sparse, token-localized SAE feature subgroups, complementing prior accounts based on broad adversarial, refusal, or steering directions.

Nilanjana Das, Mathew Dawit, Aman Chadha +1

UMBC, Maryland, U.S.A. · Apple, California, U.S.A.

Jailbreak Success Rates Unsafe Sparse Autoencoder Features Vulnerable Code Adversarial Robustness Steering+1

Apr 24, 2026cs.CL

Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization

Large Language Models (LLMs) exhibit strong implicit personalization ability, yet most existing approaches treat this behavior as a black box, relying on prompt engineering or fine tuning on user data. In this work, we adopt a mechanistic interpretability perspective and hypothesize the existence of a sparse set of Preference Heads, attention heads that encode user specific stylistic and topical preferences and exert a causal influence on generation. We introduce Differential Preference Steering (DPS), a training free framework that (1) identifies Preference Heads through causal masking analysis and (2) leverages them for controllable and interpretable personalization at inference time. DPS computes a Preference Contribution Score (PCS) for each attention head, directly measuring its causal impact on user aligned outputs. During decoding, we contrast model predictions with and without Preference Heads, amplifying the difference between personalized and generic logits to selectively strengthen preference aligned continuations. Experiments on widely used personalization benchmarks across multiple LLMs demonstrate consistent gains in personalization fidelity while preserving content coherence and low computational overhead. Beyond empirical improvements, DPS provides a mechanistic explanation of where and how personalization emerges within transformer architectures. Our implementation is publicly available.

Weixu Zhang, Ye Yuan, Changjiang Han +7

McGill University · Mila - Quebec AI Institute · MBZUAI +2

Large Language Model Personalization Personalization Preference Alignment Learning Steering

Apr 20, 2026cs.CV

From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language Models

Recent work has increasingly explored neuron-level interpretation in vision-language models (VLMs) to identify neurons critical to final predictions. However, existing neuron analyses generally focus on single tasks, limiting the comparability of neuron importance across tasks. Moreover, ranking strategies tend to score neurons in isolation, overlooking how task-dependent information pathways shape the write-in effects of feed-forward network (FFN) neurons. This oversight can exacerbate neuron polysemanticity in multi-task settings, introducing noise into the identification and intervention of task-critical neurons. In this study, we propose HONES (Head-Oriented Neuron Explanation & Steering), a gradient-free framework for task-aware neuron attribution and steering in multi-task VLMs. HONES ranks FFN neurons by their causal write-in contributions conditioned on task-relevant attention heads, and further modulates salient neurons via lightweight scaling. Experiments on four diverse multimodal tasks and two popular VLMs show that HONES outperforms existing methods in identifying task-critical neurons and improves model performance after steering. Our source code is released at: https://github.com/petergit1/HONES.

Qidong Wang, Junjie Hu, Ming Jiang

Tongji University · University of Wisconsin-Madison

Recent Vision-Language Models Neurons Steering

Apr 18, 2026cs.CL

SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models

Reinforcement learning (RL) has emerged as a promising paradigm for training reasoning-oriented models by leveraging rule-based reward signals. However, RL training typically tends to improve single-sample success rates (i.e., Pass@1) while offering limited exploration of diverse reasoning trajectories, which is crucial for multi-sample performance (i.e., Pass@k). Our preliminary analysis reveals that this limitation stems from a fundamental squeezing effect, whereby probability mass is excessively concentrated on a narrow subset of high-reward trajectories, restricting genuine exploration and constraining attainable performance under RL training. To address this issue, in this work, we propose Steering Probability Squeezing (SPS), a training paradigm that interleaves conventional RL with inverse reinforcement learning (IRL). SPS treats on-policy rollouts as demonstrations and employs IRL to explicitly reshape the induced trajectory distribution, thereby enhancing exploration without introducing external supervision. Experiments on five commonly used reasoning benchmarks demonstrate that SPS can enable better exploration and improve Pass@k. Beyond algorithmic contributions, we provide an analysis of RL learning dynamics and identify an empirical upper bound on Pass@k, shedding light on intrinsic exploration limits in RL-based reasoning models. Our findings suggest that alternating between RL and IRL offers an effective pathway toward extending the exploration capacity of reasoning-oriented large language models.

Yifu Huo, Chenglong Wang, Ziming Zhu +9

1Northeastern University, Shenyang, China · 2CAS Key Laboratory of Behavioral Science, Beijing, China · 3Independent Researcher, Beijing, China +1

LLM Reasoning Strategies Large Language Model Reinforcement Learning Reasoning Paths Stochastic Exploration Exploration Steering

Apr 18, 2026cs.LG

Structural Instability of Feature Composition

Sparse Autoencoders (SAEs) have emerged as a powerful paradigm for disentangling feature superposition in transformer-based architectures, enabling precise control via activation steering. However, the theoretical foundations of compositional steering -- the simultaneous activation of distinct semantic latents -- remain under-explored. The prevailing Linear Representation Hypothesis often abstracts away non-linear interference effects that arise in overcomplete dictionaries. We present a geometric framework for analyzing the instability of feature unions. Modeling the activation space as a high-dimensional sparse cone manifold, we derive an asymptotic compositional-collapse threshold under a spherical dictionary model, characterized by the Gaussian mean width (statistical dimension) of the signal cone. We further show that, in the high-bias regime, ReLU rectification converts microscopic correlation-induced variance fluctuations into a systematic drift that accumulates under composition, yielding interference growth consistent with a ratchet effect. We validate the predicted scaling trends on structured semantic features extracted from CLEVR, where hierarchical correlations accelerate the transition relative to random baselines. Together, our results highlight geometric constraints on the scalability of union-based steering and motivate composition mechanisms that explicitly manage interference beyond naive linear superposition.

Yunpeng Zhou

Whiteknights House, Whiteknights, Reading, RG6 6UR

Feature Learning Steering Fluctuation-Dissipation Theorem Instability

Apr 17, 2026cs.AI

RankGuide: Tensor-Rank-Guided Routing and Steering for Efficient Reasoning

Large reasoning models (LRMs) enhance problem-solving capabilities by generating explicit multi-step chains of thought (CoT) reasoning; however, they incur substantial inference latency and computational overhead. To mitigate this issue, recent works have explored model collaboration paradigms, where small reasoning models (SRMs) generate intermediate reasoning steps to achieve a better accuracy--latency trade-off. Despite recent progress, effectively and efficiently detecting and mitigating SRM failures in collaborative systems remains a key challenge. To address this issue, we analyze SRM inference in both the generated text and hidden-state spaces, and identify three types of failure modes: \textit{overconfidence}, \textit{uncertainty}, and \textit{heavy revalidation}. Building on these insights, we propose \textbf{RankGuide}, a framework that improves the efficiency and effectiveness of SRM--LRM collaboration through tensor-rank-guided routing and steering. Specifically, RankGuide leverages a routing signal that incorporates tensor-rank signals derived from consecutive hidden states to detect when SRMs are likely to fail and selectively invoke LRMs. In addition, we introduce a tensor-rank-filtered steering vector extraction method to modulate the reasoning trajectory of SRMs, thereby improving their generation quality. By improving both routing and steering through tensor-rank signals, RankGuide enables SRM--LRM collaborative systems to achieve more efficient reasoning with fewer steps and improved accuracy. Experiments on multiple reasoning benchmarks demonstrate the efficacy of RankGuide in reducing latency by up to

1.75\times

compared to LRM, while maintaining competitive accuracy relative to prior methods.

Jiayi Tian, Yupeng Su, Ryan Solgi +2

University of California, Santa Barbara · Intel Labs

Reasoning Benchmark Inference Latency Ranking Steering

Apr 17, 2026cs.LG

MidSteer: Optimal Affine Framework for Steering Generative Models

Steering intermediate representations has emerged as a powerful strategy for controlling generative models, particularly in post-deployment alignment and safety settings. However, despite its empirical success, it currently lacks a comprehensive theoretical framework. In this paper, we bridge this gap by formalizing the theory of concept steering. First, we establish a link between steering and affine concept erasure, proving that the standard approach for removing unwanted behaviors is a special case of LEACE (a closed-form method for affine erasure). Next, we formulate a principled theoretical framework for concept switching, LEACE-Switch, and characterize the assumptions under which it provides an optimal affine solution. Building on this analysis, we then introduce MidSteer (Minimal Disturbance concept Steering), a more general affine framework for concept manipulation that relaxes these assumptions and enables directed, minimal-disturbance transformations. We demonstrate that MidSteer performs favorably across a range of tasks, modalities, and architectures, including vision diffusion models and large language models.

Tatiana Gaintseva, Andrew Stepanov, Ziquan Liu +4

Queen Mary University of London, London, UK · Huawei Noah’s Ark, London, UK · QuantumLight Capital, London, UK +2

Steering Generative Models Affine Concept Erasure

Apr 16, 2026cs.LG

Predicting Where Steering Vectors Succeed

Steering vectors work for some concepts and layers but fail for others, and practitioners have no way to predict which setting applies before running an intervention. We introduce the Linear Accessibility Profile (LAP), a per-layer diagnostic that repurposes the logit lens as a predictor of steering vector effectiveness. The key measure,

A_{\mathrm{lin}}

, applies the model's unembedding matrix to intermediate hidden states, requiring no training. Across 24 controlled binary concept families on five models (Pythia-2.8B to Llama-8B), peak

A_{\mathrm{lin}}

predicts steering effectiveness at

ρ= +0.86

to

+0.91

and layer selection at

ρ= +0.63

to

+0.92

. A three-regime framework explains when difference-of-means steering works, when nonlinear methods are needed, and when no method can work. An entity-steering demo confirms the prediction end-to-end: steering at the LAP-recommended layer redirects completions on Gemma-2-2B and OLMo-2-1B-Instruct, while the middle layer (the standard heuristic) has no effect on either model.

Jayadev Billa

Linear Activation Steering Steering Logit Lens

Apr 16, 2026cs.LG

FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models

Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adjust model behavior without updating its parameters, existing methods often fail to be simultaneously effective, utility-preserving, and training-efficient due to their rigid, one-size-fits-all designs and limited adaptability. In this work, we present FineSteer, a novel steering framework that decomposes inference-time steering into two complementary stages: conditional steering and fine-grained vector synthesis, allowing fine-grained control over when and how to steer internal representations. In the first stage, we introduce a Subspace-guided Conditional Steering (SCS) mechanism that preserves model utility by avoiding unnecessary steering. In the second stage, we propose a Mixture-of-Steering-Experts (MoSE) mechanism that captures the multimodal nature of desired steering behaviors and generates query-specific steering vectors for improved effectiveness. Through tailored designs in both SCS and MoSE, FineSteer maintains robust performance on general queries while adaptively optimizing steering vectors for targeted inputs in a training-efficient manner. Extensive experiments on safety and truthfulness benchmarks show that FineSteer outperforms state-of-the-art methods in overall performance, achieving stronger steering performance with minimal utility loss. Code is available at https://github.com/YukinoAsuna/FineSteer

Zixuan Weng, Jinghuai Zhang, Kunlin Cai +3

University of California, Los Angeles

Inference-Time Steering Steering Unified Framework

Apr 9, 2026cs.LG

What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal

Applying steering vectors to large language models (LLMs) is an efficient and effective model alignment technique, but we lack an interpretable explanation for how it works--specifically, what internal mechanisms steering vectors affect and how this results in different model outputs. To investigate the causal mechanisms underlying the effectiveness of steering vectors, we conduct a comprehensive case study on refusal. We propose a multi-token activation patching framework and discover that different steering methodologies leverage functionally interchangeable circuits when applied at the same layer. These circuits reveal that steering vectors primarily interact with the attention mechanism through the OV circuit while largely ignoring the QK circuit. Freezing all attention scores during steering drops performance by only 8.83% across three model families. A mathematical decomposition of the steered OV circuit further reveals semantically interpretable concepts, even in cases where the steering vector itself does not. Leveraging the activation patching results, we show that steering vectors can be sparsified by up to 85-96% while retaining most performance, and that different steering methodologies agree on a subset of important dimensions.

Stephen Cheng, Sarah Wiegreffe, Dinesh Manocha

University of Maryland, College Park

Linear Activation Steering Steering Model Activations

Apr 8, 2026cs.CL

Persona Matters: Effects of Activation Steering on Short Answer Generation and Scoring

Activation-based steering enables inference-time personalization of large language models, but its effects in educational applications are not well understood. We study activation-based persona vectors representing seven character traits in short-answer generation and automated scoring on the ASAP-SAS benchmark, across three language models spanning dense and mixture-of-experts architectures. Persona steering lowers answer quality overall, with much larger effects on open-ended English Language Arts (ELA) prompts than on factual science prompts. Interpretive and argumentative tasks are particularly sensitive, showing up to 11

\times

larger degradation. On the scoring side, we observe predictable valence-aligned calibration shifts: evil'' and impolite'' scorers grade more harshly, while good'' and optimistic'' scorers grade more leniently. ELA tasks are 2.5-3

\times

more susceptible to scorer personalization than science tasks, and the mixture-of-experts model shows roughly 6

\times

larger calibration shifts than the dense models. To our knowledge, this is the first study to systematically examine the effects of activation-steered persona traits in educational generation and scoring. Our findings highlight the need for task- and architecture-aware calibration when deploying personalized models in educational settings.

Yongchao Wu, Aron Henriksson

Stockholm University, NOD-huset, Borgarfjordsgatan 12, 16455 Stockholm, Sweden

Artificial Intelligence Personas Persona Consistency Scoring Open-Ended Responses Steering Impact Analysis+1

Apr 2, 2026cs.CV

AViS-Mamba: Adaptive Visual Steering of Audio State-Space Dynamics for Violence Detection

Automatic violence detection from video is challenging because violent interactions may be distant, occluded, or only partially visible. Audio can provide complementary evidence for violent events that are difficult to recognize from visual information alone. However, audio itself may be absent, dubbed, or dominated by environmental noise, making the central challenge not whether to incorporate audio but how to adapt reliance on it according to the visual scene. We introduce \emph{AViS-Mamba}, an audiovisual Mamba-based architecture in which the visual stream directly governs the behavior of the audio stream. At each layer of the audio encoder, a compact visual representation produces a modulation vector that conditions the encoder's internal temporal operators together with a routing gate that regulates the strength of this visual intervention. Rather than fusing or reweighting features after they have been extracted, visual context directly shapes the temporal dynamics of the audio encoder. We further propose Adaptive AV-InfoNCE, a contrastive objective that learns to balance the audio-to-video and video-to-audio alignment directions rather than weighting them uniformly. On the audio-valid NTU-CCTV and DVD benchmarks, AViS-Mamba establishes state-of-the-art results, attaining 88.59% and 75.74% accuracy. We demonstrate that adaptive visual conditioning consistently outperforms fixed routing and improves performance under degraded and missing-audio conditions. Layer-wise analysis further reveals that the model adapts the audio stream selectively across network depth rather than applying a single global routing policy.

Damith Chamalke Senadeera, Dimitrios Kollias, Gregory Slabaugh

Queen Mary University of London, UK · Digital Environment Research Institute (DERI), London, UK

Audio-Visual Reasoning Fine-Grained Video Understanding Audio Understanding Speech-To-Text Alignment Violence Detection State Space Models+1

Mar 20, 2026cs.CV

NOUS: Video-Driven 3D Human Reaction Generation via Observation-Reaction Mutual Steering

Video-driven 3D human reaction generation aims to synthesize 3D human motion in response to the action observed in a video, playing an important role in interactive multimedia systems and embodied agents. Yet reaction motions generated by current methods often fail to match what the observed video calls for. We observe that one factor behind this failure is relational distortion in the correspondence between visual observations and reactions: videos lying close in the visual space may correspond to entirely different motions in the reaction space, which misleads the model into generating reactions inconsistent with the conditioning video. This motivates us to propose a new observatioN-reactiOn mUtual Steering (\texttt{NOUS}) framework that enables mutual steering between the video and motion modalities. It first performs Motion Feedback Steering (MFS), equipping the frozen pretrained video encoder with a lightweight rectification modulator and training the modulator with a relational margin loss that pulls each video embedding toward the motion prototype of its own category and away from those of other categories. In this way, the misaligned correspondence between visual observations and reactions can be calibrated. \texttt{NOUS} then applies Observation-Guided Refinement (OGR), which in turn exploits the rectified observations to further refine the generated reactions and enhance their quality. The results on the ViMo dataset demonstrate that \texttt{NOUS} improves the quality of reaction motion while incurring negligible computational overhead at inference. Also, \texttt{NOUS} yields consistent gains across four pretrained video encoders, showing its good compatibility.

Yuan Zhou, Luanyuan Dai, Yongzhi Li +7

College of Computing and Data Science, Nanyang Technological University, Singapore 639798 · School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, China · School of Computer Science and Information Engineering (School of Artificial Intelligence), Hefei University of Technology, Hefei 230601, China +1

Steering Complementary Modalities Reaction

Mar 9, 2026cs.AI

From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions

Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusal tokens that distinguish different refusal types before responding. In this work, we leverage a version of Llama 3 8B fine-tuned with these categorical refusal tokens to enable inference-time control over fine-grained refusal behavior, improving both safety and reliability. We show that refusal token fine-tuning induces separable, category-aligned directions in the residual stream, which we extract and use to construct categorical steering vectors with a lightweight probe that determines whether to steer toward or away from refusal during inference. In addition, we introduce a learned low-rank combination that mixes these category directions in a whitened, orthonormal steering basis, resulting in a single controllable intervention under activation-space anisotropy, and show that this intervention is transferable across same-architecture model variants without additional training. Across benchmarks, both categorical steering vectors and the low-rank combination consistently reduce over-refusals on benign prompts while increasing refusal rates on harmful prompts, highlighting their utility for multi-category refusal control.

Rishab Alagharu, Ishneet Sukhvinder Singh, Shaibi Shamsudeen +2

Algoverse AI Research · Carnegie Mellon University · University of Maryland

Refusals Large Language Model Safety Instruction-Tuned Models Steering

Mar 5, 2026cs.RO

Observing and Controlling Features in Vision-Language-Action Models

Vision-Language-Action models (VLAs) have shown remarkable progress towards embodied intelligence. While their architecture partially resembles that of Large Language Models (LLMs), VLAs exhibit higher complexity due to their multi-modal inputs/outputs and often hybrid nature of transformer and diffusion heads. This is part of the reason why insights from mechanistic interpretability in LLMs, which explain how the internal model representations relate to their output behavior, do not trivially transfer to VLA counterparts. In this work, we investigate whether VLA internal representations support lightweight behavioral steering without retraining. Across four frontier VLA models, linear \emph{observers} recover state- and action-relevant information in both autoregressive and transformer--flow-matching architectures, and provide robust directions to causally alter VLA outputs. Building on this, we introduce a \emph{controller} that minimally modifies representations to place observer predictions within prescribed target intervals. Closed-loop experiments with

π_{0.5}

in the LIBERO simulator and on DROID hardware demonstrate improved constraint satisfaction while retaining task performance, with only approximately

1\%

inference overhead. Together, these experiments show that lightweight linear interventions can reliably steer VLA behavior while preserving closed-loop capabilities, enabling alignment with user preferences and task requirements without fine-tuning.

Hugo Buurmeijer, Carmen Amo Alonso, Aiden Swann +1

Dept. of Aeronautics and Astronautics, Stanford University · Dept. of Mechanical Engineering, Stanford University · NVIDIA Research

Vision-Language-Action Framework Embodied Artificial Intelligence Steering

Feb 15, 2026cs.LG

Watch the Model Think: On-Policy Extraction of Activation Steering Vectors

When a model solves a problem on one attempt and fails it on the next, what separates the two is rarely the final answer token; it is the trajectory that reached it. Contrastive activation steering leaves that signal unused: CAA, SADI, RepE and ITI build their direction from experimenter-supplied text, recorded while the model reads rather than reasons. That choice also caps what the vector can express, since polarity must be written into the text, and a task judged only by outcome offers nothing to write it with. ROAST makes the trajectory itself the contrast: sample rollouts, let an outcome verifier split them into successes and failures, and contrast the reasoning that worked against the reasoning that did not. A matched teacher-forced control---rollouts, labels, answer text and pair counts held fixed, the trajectory alone stripped---points to the trajectory as what matters: on GSM8K at 0.6B the pairs alone buy +0.12 points while restoring the trajectories buys +6.05, the larger and only seed-robust step. Replacing the trajectory with an equal-length neutral prefix or another question's reasoning falls below no intervention. The two corpora are also far apart geometrically, a median 70+ degrees apart at both Qwen3 scales probed, beyond what a split-half null explains. Reading from rollouts calls for two corrections---keeping the full difference vector rather than Top-10% masking, and giving each question one vote rather than one per pair---and only grouped aggregation beats the unsteered baseline under 20% verifier noise. On parser-free benchmarks (GSM8K, MATH500, IFEval), ROAST is best in all six cells over two models, by up to +9.7, at +6.4% wall-clock and no added context; it also leads on six parser-scored benchmarks across three models. Across nine models (0.6B--122B, four families), ROAST improves on the unsteered model at every scale. Code: https://github.com/TomySu404/ORBIT

Xuanbo Su, Yingfang Zhang, Hao Luo +3

Bairong Inc., Beijing, China · School of Mathematics, Harbin Institute of Technology, Harbin, China

Linear Activation Steering Reasoning Trajectory Steering Model Activations On-Policy

Feb 2, 2026cs.LG

Towards Understanding Steering Strength

A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along this direction at inference time. While many propositions exist to pick this direction, considerably less is understood about how to choose the magnitude of the move, whereas its importance is clear: too little and the intended behavior does not emerge, too much and the model's performance degrades beyond repair. In this work, we propose the first theoretical analysis of steering strength. We characterize its effect on next token probability, presence of a concept, and cross-entropy, deriving precise qualitative laws governing these quantities. Our analysis reveals surprising behaviors, including non-monotonic effects of steering strength. We validate our theoretical predictions empirically on eleven language models, ranging from a small GPT architecture to modern models.

Magamed Taimeskhanov, Samuel Vaiter, Damien Garreau

University of Würzburg, Center for Artificial Intelligence and Data Science · Universit´e Cˆote d’Azur - CNRS

Steering Future Latent Representations

Jan 23, 2026cs.CY

White-Box Sensitivity Auditing with Steering Vectors

Algorithmic audits are essential tools for examining systems for properties required by regulators or desired by operators. Current audits of large language models (LLMs) primarily rely on black-box evaluations that assess model behavior only through input-output testing. These methods are limited to tests constructed in the input space, often generated by heuristics. In addition, many socially relevant model properties (e.g., gender bias) are abstract and difficult to measure through text-based inputs alone. To address these limitations, we propose a white-box sensitivity auditing framework for LLMs that leverages activation steering to conduct more rigorous assessments through model internals. Our auditing method conducts internal sensitivity tests by manipulating key concepts relevant to the model's intended function for the task. We demonstrate its application to bias audits in four simulated high-stakes LLM decision tasks. Our method consistently indicates substantial dependence on protected attributes in model predictions, even in settings where standard black-box evaluations suggest little or no bias. Our code is openly available at https://github.com/hannahxchen/llm-steering-audit

Hannah Cyberey, Yangfeng Ji, David Evans

University of Virginia

Model Auditing Large Language Model Evaluation Black Box Steering Vectors

Oct 14, 2025cs.SD

Silence is Golden: Mitigating Hallucinations in Large Audio-Language Models via Layer-Weighted Vector Steering

Large Audio-Language Models (LALMs) excel in Audio QA but often suffer from hallucinations ungrounded in the audio. To our knowledge, we are the first to propose applying vector steering to the audio domain to mitigate this. Unlike text-based steering, our silence-anchored contrastive approach steers the model away from hallucinations by contrasting active audio against a silent baseline. Probing internal states reveals a strong correlation between specific layer representations and output correctness. Leveraging this, we introduce Layer-Weighted Vector Steering (LWVS), a training-free intervention that increases steering strength at influential layers. On the Audio Hallucination QA dataset, LWVS significantly outperforms baselines, boosting Recall on the Gemma model by 15.6% (53.4% to 69.0%). Crucially, MMAU benchmark tests confirm LWVS preserves and even enhances general audio understanding, achieving an 8% relative accuracy increase on the Qwen model (54.8% to 59.2%).

Tsung-En Lin, Kuan-Yi Lee, Hung-Yi Lee

National Taiwan University, Taipei, Taiwan · ASUS Open Cloud Infrastructure Software Center, Taipei, Taiwan

Large Audio Language Models Steering

Sep 29, 2025cs.CV

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models

As Vision Language Models (VLMs) are deployed across safety-critical applications, understanding and controlling their behavioral patterns has become increasingly important. Existing behavioral control methods face significant limitations: system prompting approaches could easily be overridden by user instructions, while applying activation-based steering vectors requires invasive runtime access to model internals, precluding deployment with API-based services and closed-source models. Finding steering methods that transfer across multiple VLMs is still an open area of research. To this end, we introduce universal visual input based steering for output redirection (VISOR++), to achieve behavioral control through optimized visual inputs alone. We demonstrate that a single VISOR++ image can be generated for an ensemble of VLMs to emulate each of their steering vectors. By crafting universal visual inputs that induce target activation patterns, VISOR++ eliminates the need for runtime model access while remaining deployment-agnostic. This means that when an underlying model supports multimodal capability, model behaviors can be steered by inserting an image input replacing runtime steering vector based interventions. We first demonstrate the effectiveness of the VISOR++ images on open-access models such as LLaVA-1.5-7B and IDEFICS2-8B along three alignment directions: refusal, sycophancy and survival instinct. Both the model-specific steering images and the jointly optimized images achieve performance parity closely following that of steering vectors for both positive and negative steering tasks. We also show the promise of VISOR++ images in achieving directional behavioral shifts for unseen models including both open-access and closed-access ones. Furthermore, VISOR++ images are able to preserve 99.9% performance on 14,000 unrelated MMLU evaluation tasks.

Ravikumar Balakrishnan, Mansi Phute

HiddenLayer, USA · Georgia Institute of Technology, USA

Recent Vision-Language Models Steering

Sep 29, 2025cs.CL

EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering

Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time through targeted manipulation of hidden states, offering a lightweight alternative to expensive retraining. However, existing steering frameworks suffer from critical limitations: computational inefficiency, limited extensibility, and restricted functionality that hinder both research progress and practical deployment. We present EasySteer, a unified framework for high-performance, extensible LLM steering built on vLLM. Our system features modular architecture with pluggable interfaces for both analysis-based and learning-based methods, fine-grained parameter control, pre-computed steering vectors for eight application domains, and an interactive demonstration system. Through deep integration with vLLM's optimized inference engine, EasySteer achieves 10.8-22.3

\times

speedup over existing frameworks. Extensive experiments demonstrate its effectiveness in overthinking mitigation, hallucination reduction, and other key applications. EasySteer transforms steering from research technique to production-ready capability, establishing critical infrastructure for deployable, controllable language models.

Haolei Xu, Xinyu Mei, Yuchen Yan +5

1Zhejiang University

Steering Unified Framework

Sep 3, 2025cs.CL

Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators

Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models. This bias undermines fairness and reliability in evaluation pipelines, particularly for tasks like preference tuning and model routing. We investigate whether lightweight steering vectors can mitigate this problem at inference time without retraining. We introduce a curated dataset that distinguishes self-preference bias into justified examples of self-preference and unjustified examples of self-preference, and we construct steering vectors using two methods: Contrastive Activation Addition (CAA) and an optimization-based approach. Our results show that steering vectors can reduce unjustified self-preference bias by up to 97%, substantially outperforming prompting and direct preference optimization baselines. Yet steering vectors are unstable on legitimate self-preference and unbiased agreement, implying self-preference spans multiple or nonlinear directions. This underscores both their promise and limits as safeguards for LLM-as-judges and motivates more robust interventions.

Dani Roytburg, Matthew Bozoukov, Matthew Nguyen +3

School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 · Martian Research San Francisco, CA, 94105

Large Language Model Bias Steering Mitigation Contrastive Learning

Aug 28, 2025cs.CL

Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection

Safety alignment in Large Language Models (LLMs) often involves mediating internal representations to refuse harmful requests. Recent research has demonstrated that these safety mechanisms can be bypassed by ablating or removing specific representational directions within the model. In this paper, we propose the opposite approach: Rank-One Safety Injection (ROSI), a white-box method that amplifies a model's safety alignment by permanently steering its activations toward the refusal-mediating subspace. ROSI operates as a simple, fine-tuning-free rank-one weight modification applied to all residual stream write matrices. The required safety direction can be computed from a small set of harmful and harmless instruction pairs. We show that ROSI consistently increases safety refusal rates - as evaluated by Llama Guard 3 - while preserving the utility of the model on standard benchmarks such as MMLU, HellaSwag, and Arc. Furthermore, we show that ROSI can also re-align 'uncensored' models by amplifying their own latent safety directions, demonstrating its utility as an effective last-mile safety procedure. Our results suggest that targeted, interpretable weight steering is a cheap and potent mechanism to improve LLM safety, complementing more resource-intensive fine-tuning paradigms.

Harethah Abu Shairah, Hasan Abed Al Kader Hammoud, George Turkiyyah +1

King Abdullah University of Science and Technology (KAUST)

Safety Alignment Large Language Model Alignment Steering

Aug 11, 2025cs.CV

VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models

Vision Language Models (VLMs) are increasingly being used in a broad range of applications, bringing their security and behavioral control to the forefront. While existing approaches for behavioral control or output redirection, like system prompting in VLMs, are easily detectable and often ineffective, activation-based steering vectors require invasive runtime access to model internals--incompatible with API-based services and closed-source deployments. We introduce VISOR (Visual Input-based Steering for Output Redirection), a novel method that achieves sophisticated behavioral control through optimized visual inputs alone. By crafting universal steering images that induce target activation patterns, VISOR enables practical deployment across all VLM serving modalities while remaining imperceptible compared to explicit textual instructions. We validate VISOR on LLaVA-1.5-7B across three critical alignment tasks: refusal, sycophancy and survival instinct. A single 150KB steering image matches steering vector performance within 1-2% for positive behavioral shifts while dramatically exceeding it for negative steering--achieving up to 25% shifts from baseline compared to steering vectors' modest changes. Unlike system prompting (3-4% shifts), VISOR provides robust bidirectional control while maintaining 99.9% performance on 14,000 unrelated MMLU tasks. Beyond eliminating runtime overhead and model access requirements, VISOR exposes a critical security vulnerability: adversaries can achieve sophisticated behavioral manipulation through visual channels alone, bypassing text-based defenses. Our work fundamentally re-imagines multimodal model control and highlights the urgent need for defenses against visual steering attacks.

Mansi Phute, Ravikumar Balakrishnan

Georgia Institute of Technology · HiddenLayer, Inc

Jul 31, 2025cs.CL

Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders

Traditional topic models are effective at uncovering latent themes in large text collections. However, due to their reliance on bag-of-words representations, they struggle to capture semantically abstract features. While some neural variants use richer representations, they are similarly constrained by expressing topics as word lists, which limits their ability to articulate complex topics. We introduce Mechanistic Topic Models (MTMs), a class of topic models that operate on interpretable features learned by sparse autoencoders (SAEs). By defining topics over this semantically rich space, MTMs can reveal deeper conceptual themes with expressive feature descriptions. Moreover, uniquely among topic models, MTMs enable controllable text generation using topic steering vectors. To properly evaluate MTM topics against word list approaches, we propose \textit{topic judge}, an LLM-based pairwise comparison evaluation framework. Across eight datasets, MTMs match or exceed traditional and neural baselines on coherence metrics, are consistently preferred by topic judge, and enable effective LLM steering.

Carolina Zheng, Nicolas Beltran-Velez, Sweta Karlekar +5

Columbia University · Independent · Google Research

Topic Modeling Steering

Apr 24, 2025cs.HC

Exploring Context-aware and LLM-driven Locomotion for Immersive Virtual Reality

Locomotion plays a crucial role in shaping the user experience within virtual reality environments. In particular, hands-free locomotion offers a valuable alternative by supporting accessibility and freeing users from reliance on handheld controllers. To this end, traditional speech-based methods often depend on rigid command sets, limiting the naturalness and flexibility of interaction. In this study, we propose a novel locomotion technique powered by large language models (LLMs), which allows users to navigate virtual environments using natural language with contextual awareness. We evaluate three locomotion methods: controller-based teleportation, voice-based steering, and our language model-driven approach. Our evaluation combines eye-tracking data analysis, including exploratory explainable machine learning analysis with SHAP, and standardized questionnaires (SUS, IPQ, CSQ-VR, NASA-TLX) to examine user experience through both objective gaze-based measures and subjective self-reports of usability, presence, cybersickness, and cognitive load. Our findings show no statistically significant differences in usability, presence, or cybersickness between LLM-driven locomotion and established methods such as teleportation, suggesting its potential as a viable, natural language-based, hands-free alternative. In addition, eye-tracking analysis revealed patterns suggesting tendency toward increased user attention and engagement in the LLM-driven condition. Complementary to these findings, exploratory SHAP analysis revealed that fixation, saccade, and pupil-related features vary across techniques, indicating distinct patterns of visual attention and cognitive processing. Overall, we state that our method can facilitate hands-free locomotion in virtual spaces, especially in supporting accessibility.

Suleyman Ozdel, Kadir Burak Buldu, Enkelejda Kasneci +1

Human-Centered Technologies for Learning, Technical University of Munich, Germany · Munich Center for Machine Learning, Munich, Germany

Virtual Reality Locomotion Eye Tracking Steering Exploration

Date pendingcs.GR

A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting

Text-driven motion editing and intra-structural retargeting, where skeletons share topology but may differ in bone lengths and rest pose, are traditionally handled by fragmented pipelines with incompatible inputs and representations: editing relies on specialized generative steering, while retargeting is deferred to geometric post-processing. We present a unified conditional-flow framework that casts generation, semantic editing, and intra-structural retargeting as condition-modulated transport within one text- and skeleton-conditioned rectified-flow model. Under this formulation, editing changes the semantic condition while preserving skeletal structure, whereas retargeting changes the skeletal condition while preserving motion semantics. This makes FlowEdit-style transport a unified inference rule for motion manipulation rather than a task-specific editor. To instantiate this for articulated 3D motion, we develop a text- and skeleton-conditioned rectified-flow transformer. The model uses per-joint tokenization and explicit joint self-attention to capture spatial kinematic dependencies. We further inject text conditions at both joint and frame levels, while residual multi-condition classifier-free guidance balances text adherence and skeletal conformity. Experiments on SnapMoGen and a multi-character Mixamo subset show that one trained model supports text-to-motion generation, zero-shot editing, and zero-shot intra-structural retargeting without task-specific fine-tuning. This unified framework replaces separate pipelines with a single conditional motion transport model while keeping the same-topology retargeting scope explicit.

Junlin Li, Xinhao Song, Siqi Wang +2

ByteDance, San Jose, USA

Text-To-Motion Generation Cross-Embodiment Retargeting Camera-Conditioned Video Generation Contrastive Flow Matching Rectified Flow Motion+4