Autoregressive Transformer

Follow this topic Ask about this topic

Latest papers

28 papers6 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Oct 16, 2026

Prefix-Tuning for Arbitrary Output Sequences on Pretrained Transformers

Prefix-tuning is a parameter-efficient fine-tuning method for large language models (LLMs) that steers model outputs by prepending task-specific prefix representations to the input sequence. Despite its practical success, the theoretical understanding of the expressiveness of prefixes remains incomplete. In particular, the following question remains open: Given a pretrained autoregressive Transformer, for any input-output sequence pair

(\mathtt{x},\mathtt{y})

, does there always exist a prefix

\mathcal{S}

such that prepending

\mathcal{S}

to

\mathtt{x}

induces the model to generate the target output

\mathtt{y}

? In this work, we prove that under the assumption that

\mathtt{y}

is in the range of the pretrained Transformer, such a prefix

\mathcal{S}

exists and can be explicitly computed by solving multiple linear systems. We further show that this assumption is necessary, in the sense that such a prefix may not exist when the assumption fails, thereby providing a complete answer to the above question. Our analysis is constructive and the obtained theoretical results hold under fairly general assumptions on model architecture. Extensive experiments on GPT-2 and Qwen3-4B demonstrate that our algorithm produces prefixes with strong control over model outputs.

Peter Cho-Ho Lam, Ziyi Wang, Zirui Zhou

Prefix Tuning Parameter-Efficient Fine-Tuning Autoregressive Transformer

Oct 16, 2026

Sampling the XY model with an attention-based neural network

We present a transformer-based variational autoregressive network for sampling lattice systems with continuous degrees of freedom and apply it to the two-dimensional XY model near the Berezinskii-Kosterlitz-Thouless transition. The architecture is combined with physics-informed ingredients: locality-informed attention and approximate probabilities. The resulting sampler significantly outperforms existing neural samplers. We train the model on lattices up to

96\times96

, verify with a mode-dropping estimator that no parts of the configuration space are missed, and reproduce the energy, magnetization and helicity modulus obtained with the traditional Markov Chain Monte Carlo algorithm.

Piotr Białas, Christian D. Morales, Tomasz Stebel +1

Institute of Applied Computer Science, Jagiellonian University, ul. Łojasiewicza 11, 30-348 Kraków, Poland · V. N. Karazin Kharkiv National University, 6 Nezalezhnosti Ave, Kharkiv 61022, Ukraine · Institute of Theoretical Physics, Jagiellonian University, ul. Łojasiewicza 11, 30-348 Kraków, Poland +1

Boltzmann Sampling Autoregressive Transformer Phase Transitions

Oct 13, 2026

PairIT: Autoregressive Transformers for Low-Data Molecule Optimization

Generating novel molecules with desired properties is a central challenge in drug discovery. Although foundational work focused on de novo generation, practical use cases require a more complex setting: conditioning on an initial seed molecule, optimizing multiple properties, and operating in data-sparse regimes. We introduce PairIT, a flexible training framework for autoregressive transformers over SMILES sequences that enables seeded generation by learning from pairs of structurally similar molecules. By leveraging matched pairs, the model learns to generate local, chemically meaningful edits that improve a property of the seed molecule. Prompt tokens extend this framework by specifying the target property, desired direction, and approximate magnitude of change. Multiple prompt tokens can be concatenated to enable multi-property optimization at inference time. For properties where pair supervision alone is insufficient, reinforcement learning post-training can further improve optimization, providing a tunable trade-off between proximity to the seed and the optimization objective. PairIT naturally supports pretraining on a large dataset and fine-tuning on a smaller dataset, which is critical for performance in data-sparse regimes. Surprisingly, we observe diminishing returns to the scale of the pretraining dataset. We demonstrate empirically on MoleculeNet and Therapeutics Data Commons datasets that, with appropriate paired-data curation, a standard transformer model of modest size (68M parameters) can achieve robust seeded molecular optimization in low-data regimes.

Hannah Lawrence, Bodhi P. Vani, Ji Won Park +5

Genentech, South San Francisco, CA, USA · Massachusetts Institute of Technology, Cambridge, MA, USA · Prescient Design, Genentech, Basel, Switzerland +1

Autoregressive Transformer Molecular Optimization Drug Discovery Transformer

Sep 30, 2026

Learning Chaos Without Seeing Chaos: Extrapolation of Global Dynamics in Autoregressive Transformers

Autoregressive models are trained to predict a system's behavior one step at a time, and recursive generation allows the learned dynamics to unfold over long horizons. To what extent can such dynamics learned from local observations recover broader organization of an underlying system that was only partially observed during training? Here we study small autoregressive transformers trained from scratch on trajectories sampled from restricted parameter regimes of several non-linear dynamical systems, including logistic and sine maps, the Lorenz system, and the generalized Hopf system, with control parameters and state trajectories represented as sequences of continuous tokens. Under closed-loop evaluation at parameters far outside the training distribution, the models can recover self-similar period-doubling cascades, chaotic dynamics, and attractor structures with remarkable visual and numerical fidelity. For the logistic map, a transformer reproduces successive period doublings up to period 128, yielding a finite-order scaling ratio of 4.6687, matching the Feigenbaum constant to within

5\times10^{-4}

. We further investigate how these structures emerge over the course of training, and reveal with causal interventions how control-parameter information is processed through attention into state prediction and shapes the resulting closed-loop dynamics. These results suggest that a surprisingly narrow window into a system's local behavior may suffice for autoregressive transformers to generalize to its unseen global dynamical organization.

Yilun Liu, Yi Zhang, Ganyu Wu +5

Ludwig Maximilian University of Munich · Munich Center for Machine Learning · Technical University of Munich

Dynamical Systems Chaotic Dynamical Systems Chaotic Time-Series Prediction Autoregressive Modeling Autoregressive Transformer

Sep 28, 2026

DreamingGoose: Staged Distillation from Autoregressive Transformers to Bidirectional Recurrent Diffusion Language Models

Pretrained autoregressive Transformers represent a large sunk investment in compute. Existing conversion methods reuse that investment by changing either the architecture (attention to recurrence) or the objective (next-token prediction to denoising), never both. We convert Qwen3 teachers at 1.7B and 8B into attention-free, bidirectional, gated-delta-rule diffusion students in three stages, so that each capability can be traced to the stage that kept or lost it. Language modeling transfers only partially and in-distribution; in-context retrieval does not transfer. On a multi-query recall probe where the teachers score 0.34-0.58, both converted students score 0.000, and diffusion pretraining alone does not restore retrieval. A retrieval curriculum in the final stage, which gradually lengthens the gap between a key-value table and the queries that address it, restores it only stochastically: on a fixed schedule, one seed in three learns to retrieve. Advancing the gap only while a running accuracy estimate stays above a threshold works for all three of those seeds, holds on real text, and carries unchanged to 8B, where two of three seeds succeed. The third had not learned within its fixed 16k-step budget: retrieval switches on abruptly at a seed-dependent step (6.5k and 11k in the other two), so a fixed budget can cut a late run off. One boundary survives every intervention: every model that learns retrieval scores 0.000 on tokens that never appeared in a retrieval episode, and an arm that resamples the key and value tokens every batch shows this is a coverage limit, not memorization of particular bindings. Separately, we convert a 7B code model into a 3:1 recurrent-attention block-diffusion hybrid over 85k steps and report two negative training results.

Julian Boesch, Andrew Wee, Alexander Stranzl

Purdue University · Obit Research · State University of New York at Stony Brook.

In-Context Retrieval Recurrent Transformers Language Model Distillation Diffusion Language Models Diffusion Language Model Distillation Autoregressive Transformer

Sep 27, 2026

Decoupling Token Roles in Autoregressive Pretraining

Autoregressive pretraining increasingly draws on heterogeneous data, making it important to understand how a model learns from an individual token. The next-token prediction objective naturally identifies a token's contribution with its own loss. However, each token is not only a prediction target but also context for what follows. Using controlled corruption, we decouple these two roles and find a reversal: making a noisy token easier to predict reduces its damage as a target but increases it as context. The same decoupling helps explain text generated by language models: generation selects each token by its fit to the prefix, while its role as context is never tested against an independently determined continuation, because that continuation is generated to fit it. At known corrupted positions, acting through the context can reduce damage that removing the token's own loss does not. Understanding and controlling what a model learns from a token therefore requires decoupling its roles.

Suqin Yuan, Runqi Lin, Kevin Qinghong Lin +4

University of Sydney · University of Oxford · Southeast University

Language Model Pretraining Autoregressive Language Modeling Causal Interventions in Language Models Language Model Robustness Autoregressive Transformer Sequence Prediction

Aug 27, 2026

Industrial Kinematic Trajectory Model (IKTM): Coordinate-Free Autoregressive Generator

Mobility simulation supports logistics, safety, and communications planning in industrial environments such as ports, mines, and airports. Existing trajectory models, however, rely on absolute coordinates, road-network tokens, or semantic zones: representations that are site-specific and not well suited to unstructured industrial terrain. We introduce the Industrial Kinematic Trajectory Model (IKTM), a coordinate-free trajectory generator that represents industrial vehicle motion through kinematic sequences (speed and heading change) with no absolute spatial reference. IKTM uses an autoregressive causal transformer with probabilistic mixture heads and extends our prior coordinate-free Markovian model with deep sequence modelling and an explicit duration-conditioning signal. Trained on one site and evaluated zero-shot on three unseen sites, it matches the small-turn shape of the empirical turn-rate distributions of held-out telematics; across all four sites, the per-site mean Jensen-Shannon divergence over 100 sampling seeds spans approximately 0.035-0.050 bits under an oracle-length duration-target protocol and approximately 0.032-0.042 bits under a fully zero-shot prior-length protocol, with similar ranges whether out-of-distribution (OOD) duration targets are drawn from each held-out site's empirical length distribution or from the Site A prior. Both protocols stay above the metric's sampling-noise floor (<=0.0049 bits). Paired by site, the oracle-length values are 5.3-6.0x lower than those of a re-implementation of our prior Markovian model under the same 1 Hz protocol. Termination is duration-conditioned rather than spatial: rollouts stop on 100% of trials with a length-tracking error of +0.0 +/- 0.0 s against the sampled target (100 of 100 exactly on target; N=100, T=0.2, untouched in-distribution test split).

Max Amiri, David Eyers

School of Computing University of Otago Dunedin, New Zealand

Autoregressive Transformer Trajectory Generation

Aug 25, 2026

Clearing the Underbrush: AI-Enhanced RF Interference Suppression

AI-based structured interference rejection has grown more popular because deep learning approaches can outperform traditional methods by jointly considering the signal of interest (SOI) and the signal mixture (SOI plus interference). This work builds on a previous AI-enabled approach utilizing autoregressive transformer-based models by adding a Finite Scalar Quantization (FSQ) tokenizer layer which aims to improve the interference rejection performance while keeping overall latency to a minimum. Additionally, we experiment with other inference optimization techniques with the goal of speeding up inference without much accuracy loss. We explore this space with an experiment where the SOI is a digitally modulated radio frequency (RF) signal and the structured interference is a digital television signal, an extremely common type of Orthogonal Frequency-Division Multiplexing (OFDM) transmission. Our results achieve low latency and increased interference rejection over traditional techniques and prior work with other AI-enabled methods. We demonstrate the benefits of the AI-enabled approaches via audio metrics such as Perceptual Evaluation of Speech Quality (PESQ). Additionally, we explore a variety of applications and detail how our interference rejection algorithm may be used in operationally-relevant scenarios.

Rahul Jain, Pierre Trepagnier, Rick Gentile +2

MIT Lincoln Laboratory, Lexington, MA 02421, USA

Finite Scalar Quantization Autoregressive Transformer Wireless Communications Transformer

Aug 19, 2026

WhiteMatter: All-to-All Cross-Layer Connections via KV Source Mixing

When generating text, a Transformer produces representations of past tokens at every layer, but each layer can normally use only representations from the same depth. This restriction prevents the model from fully reusing information it has already computed. We introduce WhiteMatter, which allows every layer to draw on past-token representations from any depth. A learned mixer selects the most useful depths for the current context and combines their representations into shared key-value (KV) cache channels. Sharing these channels across layers can reduce the cache size. Given the same number of training tokens, WhiteMatter with a full-size cache performs comparably to a standard Transformer with 50% more layers. With half the KV cache, WhiteMatter outperforms matched standard Transformers at two model scales, up to 1.3B parameters. Cross-layer connections, however, introduce dependencies that slow training and prompt processing. We address this problem with cyclic iteration, which updates interleaved groups of tokens in turn while processing the tokens within each group in parallel. On a reference model trained with exact autoregressive execution, cyclic iteration converges 12.5x faster than standard Jacobi iteration.

Wenbo Zhang, Xiang Ren

University of Southern California

Efficient Transformer Inference Cross-Layer Attention KV Caching Transformer Attention Autoregressive Transformer

Aug 9, 2026

Full-bandwidth transformer

Autoregressive transformers compute along two axes: horizontally across generated tokens, and vertically through model depth. Dense attention gives each token broad horizontal access to the past, but the vertical feedback channel between decoding steps remains narrow: only the sampled token returns to the bottom of the stack, while the top-layer hidden state is discarded. We introduce the full-bandwidth transformer, which widens this channel with latent feedback: at each decoding step, the previous top-layer hidden state is fused with the sampled token embedding through a gated linear unit and fed back as the next input. Latent feedback lets non-verbalized computation re-enter the stack with a renewed depth budget, while preserving the standard transformer architecture, KV cache, and language-modeling objective. To train full-bandwidth transformers without losing parallel teacher forcing, we use a scheduled multi-pass objective that introduces latent feedback late in pretraining and mixes a small fraction of deeper feedback passes for stability. We train 1B-parameter full-bandwidth transformers on up to 400B tokens and find that latent feedback improves validation loss, 5-shot language-model evaluation, math and coding generation, and instruction-tuned performance. With negligible per-token decoding overhead, full-bandwidth transformers match or approach standard transformers trained with roughly 1.5x more tokens, and manage to produce shorter reasoning when no off-policy templates are provided.

Xi Wang, Ziyang Cai, Zheng Zhan +5

Johns Hopkins University · Princeton University · Microsoft

Autoregressive Language Modeling Recurrent Transformers Autoregressive Transformer

Aug 3, 2026

Maglev: Sliding Recurrent Memory

We introduce \ours{}, a recurrent Transformer architecture with fixed-size memory that generalizes sliding-window attention while remaining parallelizable during training. \ours{} consists of two coupled models: a prefiller

Q

, which leverages full attention\footnote{In practice, we use interleaved full and sliding-window attention for

Q

, as this yields stronger performance. The essential requirement is that

Q

be more expressive than

P

, with access to the full history.} to produce memory targets

m'_t

, and a decoder

P

, which uses only sliding-window attention and recurrent K/V injection to produce decoder memories

m_t

for next-token prediction. We train \ours{} with a memory consistency loss that aligns

m_t

with

m'_t

, allowing inference to use

P

alone. Empirically, \ours{} improves validation loss and downstream pretraining benchmarks over sliding-window and latent recurrent transformer baselines. Moreover, sharing parameters between

P

and

Q

reduces parameter memory while preserving most of the gains.

Bo Liu, Qiang Liu

The University of Texas at Austin

Memory-Augmented Language Models Next-Token Prediction Recurrent Transformers Language Modeling Sliding-Window Attention Autoregressive Transformer

Jul 26, 2026

Multimodal Auto-regressive Transformer Surrogate for Modeling Variable Operations and Quantifying Uncertainty in Geological Carbon Storage

The use of variable well perforation and injection strategies can improve the efficiency of geological carbon storage operations. We develop a new multimodal auto-regressive transformer surrogate to model these operations under geological uncertainty. A modified SEAM CO2 geomodel, which involves a faulted system with three stacked aquifers, is considered. The two injection wells are perforated in stages, from bottom to top, with the stage durations and individual well injection rates treated as control variables. The surrogate model processes three input modalities - the 3D geomodel, scalar parameters characterizing relative permeability functions, and control variables - through separate encoders. These are fused via self-attention in a transformer encoder, and a temporal decoder generates predictions auto-regressively through encoder-decoder cross-attention. The surrogate is trained, using 4000 GEOS flow simulations, to predict saturation and pressure at monitoring locations, total injected and mobile CO2 mass, and saturation footprints. For a new test set, involving randomly sampled geomodels and control variables, the surrogate achieves a median saturation MAE of 0.028 and median relative errors of 0.2-5% for the other quantities of interest. Importantly, it captures the switch from rate to bottom-hole-pressure control. The surrogate model is used within a hierarchical Markov chain Monte Carlo data assimilation procedure for a synthetic true model under three operational strategies. Substantial uncertainty reduction is achieved for key metaparameters, particularly the fault permeabilities. Posterior predictions for saturation footprints and total injected and mobile CO2 mass are also shown to be generally consistent with true model results.

Yifu Han, Louis J. Durlofsky

Department of Energy Science and Engineering, Stanford University, Stanford, CA, 94305, USA

Neural Surrogate Modeling Uncertainty Quantification Transformer Autoregressive Transformer PDE Surrogate Modeling

Jul 25, 2026

CAPT: A Multi-task Continuous Autoregressive Transformer enabling Cross-dataset and Cross-species Transfer for Calcium Population Dynamics

Calcium imaging has enabled large-scale recordings of neural population activity across diverse animals, laboratories, and experimental paradigms. However, these datasets remain highly fragmented: Existing approaches are often designed for individual datasets or tasks, making it unclear whether their learned representations are reusable for new calcium imaging trace datasets. To tackle this gap, we present CAPT, a Continuous Autoregressive Population Transformer for calcium population dynamics. CAPT models continuous calcium traces directly through a continuous patch tokenization strategy and is trained autoregressively with a mean squared error objective, enabling end-to-end training and adaptation to diverse downstream tasks. We first pretrain CAPT on a large-scale mouse calcium imaging dataset and evaluate its transferability across independent mouse, larval zebrafish, and C. elegans datasets collected by different laboratories. In these transfer settings, the pretrained backbone is frozen and only adaptation modules, i.e., neuron and session embeddings or task-specific heads, are updated. Across neural population forecasting and behavior decoding tasks, CAPT consistently outperforms specialized and general-purpose baselines, demonstrating that a single continuous autoregressive backbone can learn representations that transfer beyond the original pretraining distribution. Beyond predictive performance, multimodal analyses using NeuroPAL annotations in C. elegans datasets show that CAPT embeddings form a shared functional space across datasets and capture cell-identity-related structure. Together, these results suggest that continuous autoregressive modeling provides an effective framework for learning reusable calcium population representations that transfer across datasets, experimental paradigms, and species.

Xinhong Xu, Yimeng Zhang, Yuanlong Zhang

Department of Automation, Tsinghua University, Beijing, China · School of Life Sciences, Tsinghua University, Beijing, China

Transformer Neural Decoding Autoregressive Transformer Transfer Learning Time-Series Foundation Models

Jul 16, 2026

T^2MLR: Transformer with Temporal Middle-Layer Recurrence

Transformer reasoning is limited by autoregressive decoding, which repeat edly compresses rich hidden computation through token space and makes it difficult for intermediate reasoning states to persist across time. We in troduce Transformers with Temporal Middle-Layer Recurrence (T2MLR), a transformers-based latent reasoning architecture that fuses a cached middle layer representation from the previous token directly into an earlier layer of the current token position, enabling abstract intermediate computation to persist across decoding steps with little inference overhead. Across natural-language pretraining and multi-hop reasoning finetuning, T2MLR consistently outperforms data- and parameter-matched Transformer base lines. Moreover, applying recurrence to only a localized middle-layer block (as little as 20% of the network) often outperforms full-layer recurrence. Im portantly, T2MLR does not require pretraining from scratch: retrofitting the recurrent pathway into an existing pretrained 1.7B Transformer and briefly finetuning substantially improves math reasoning, lowering the barrier to practical adoption. These results suggest that effective latent reasoning in Transformers does not require looping over all layers as in previous works, but can instead emerge more strongly from targeted middle-layer recurrence.

Ziyang Cai, Xingyu Zhu, Yihe Dong +2

Princeton Language and Intelligence, Department of Computer Science Princeton University

Recurrent Transformers LLM Reasoning Latent Reasoning Autoregressive Transformer

Jun 4, 2026

Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation

We study the transformation of autoregressive models (ARLMs) into diffusion language models (DLMs). Rather than pretraining from scratch, prior work replaces the causal attention in ARLMs with bidirectional attention and then trains the resulting model using a DLM objective. However, these approaches incur two distribution shifts. First, transitioning from a next-token prediction objective to a DLM objective can discard knowledge acquired by the ARLM during training. Second, standard DLMs suffer from a train-inference mismatch, as the training loss is defined on randomly masked sequences rather than the trajectories encountered at inference produced by confidence-based decoding. To address both challenges, we introduce an On-Policy Diffusion Language Model (OPDLM) in which On-Policy Distillation (OPD) is employed for ARLM-to-DLM transformation. Specifically, OPDLM is trained via self-OPD, where the student, an ARLM with bidirectional attention, generates its own trajectories, and the teacher, the original frozen ARLM, distills its knowledge by providing target logits on these trajectories. By training directly in an on-policy manner, OPDLM eliminates the train-inference mismatch in DLMs, while distillation from the original model enhances knowledge retention from the ARLM. Empirical results demonstrate that OPDLM requires 15x to 7,000x fewer training tokens with strong performance across a wide variety of tasks. OPDLM avoids the prohibitive cost of DLM pretraining and positions DLM transformation as a form of ARLM post-training.

Xingyu Su, Jacob Helwig, Shubham Parashar +6

Department of Computer Science and Engineering, Texas A&M University · Department of Bioinformatics and Systems Medicine,2026 University of Texas Health Science Center at Houston · Department of Electrical and Computer Engineering, Texas A&M UniversityJun 4

Language Model Distillation Diffusion Language Models Diffusion Language Model Distillation Autoregressive Diffusion On-Policy Distillation Diffusion Language Model Training+1

Jun 2, 2026

Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking

We introduce Humanoid-GPT, a GPT-style Transformer with causal attention trained on a billion-scale motion corpus for whole-body control. Unlike prior shallow MLP trackers constrained by scarce data and an agility-generalization trade-off, Humanoid-GPT is pre-trained on a 2B-frame retargeted corpus that unifies all major mocap datasets with large-scale in-house recordings. Scaling both data and model capacity yields a single generative Transformer that tracks highly dynamic behaviors while achieving unprecedented zero-shot generalization to unseen motions and control tasks. Extensive experiments and scaling analyses show that our model establishes a new performance frontier, demonstrating robust zero-shot generalization to unseen tasks while simultaneously tracking highly dynamic and complex motions.

Zekun Qi, Xuchuan Chen, Dairu Liu +10

Tsinghua University · Galbot Inc. · Shanghai Jiao Tong University +2

Zero-Shot Learning Transformer Robot Foundation Models Autoregressive Transformer Humanoid Robot Control Humanoid Motion Tracking

May 26, 2026

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior

We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden state from the previous token as recurrent memory for the next token. Because this state is already computed during ordinary decoding, LRT introduces a cross-token, cross-layer latent pathway while preserving the standard attention mechanism, KV-cache interface, and one model forward per generated token. To pretrain this recurrence without sequentially unrolling the full sequence, we introduce interleaved parallel training: one full-sequence initialization forward constructs a shared buffer, followed by sequential refinement of disjoint position subsets with parallel computation within each subset. This provides every token with recurrent-memory-aware supervision at approximately 2x ideal token compute. Across 1.3B- and 2.1B-parameter nanochat-style backbones and a wide range of training budgets, LRT improves both BPB and CORE under matched effective compute. Additionally, LRT outperforms two-forward PonderLM-2 and matches a three-loop Transformer in BPB, while retaining one-forward-per-token decoding with 9% latency overhead over the standard Transformer.

Zeyi Huang, Xuehai He, LiLiang Ren +8

Microsoft · University of Washington · University of Wisconsin-Madison

Language Model Pretraining Transformer Inference Autoregressive Language Modeling Recurrent Transformers Autoregressive Transformer

May 20, 2026

UniT: Unified Geometry Learning with Group Autoregressive Transformer

Recent feed-forward models have significantly advanced geometry perception for inferring dense 3D structure from sensor observations. However, its essential capabilities remain fragmented across multiple incompatible paradigms, including online perception, offline reconstruction, multi-modal integration, long-horizon scalability, and metric-scale estimation. We present UniT, a unified model built upon a novel Group Autoregressive Transformer, which reformulates these seemingly disparate capabilities within a single framework. The key idea is to treat groups of sensor observations as the basic autoregressive units and predict the corresponding point maps in an anchor-free and scale-adaptive manner. More specifically, diverse view configurations in both online and offline settings are naturally unified within a single group autoregression process. By varying the group size, online mode operates over multiple autoregressive steps with single-frame groups, whereas offline mode aggregates a multi-frame group in a single forward pass. Meanwhile, a queue-style KV caching mechanism ensures bounded autoregressive memory over long horizons. This is enabled by reducing long-range dependencies on early frames through anchor-free relational modeling, thereby allowing outdated memory to be discarded on the fly. To improve metric-scale generalization across scenes, a scale-adaptive geometry loss is further introduced within this framework. It couples relative geometric constraints with a partial absolute scale term, implicitly regularizing global scale and inducing a progressive transition from scale-invariant geometry to metric-scale solutions. Together with a dedicated modal attention module for integrating auxiliary modalities, UniT achieves state-of-the-art performance in unified geometry perception, as validated on ten benchmarks spanning seven representative tasks.

Haotian Wang, Yusong Huang, Zhaonian Kuang +4

Intelligent Transportation Thrust of the Systems Hub, The Hong Kong University of Science and Technology (GZ), Guangzhou, P.R.China. · The National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, P.R.China. · Applied Science, Amazon.com, Inc., USA.

Transformer Autoregressive Transformer Depth Estimation Multi-View 3D Reconstruction Geometric Representation Learning Feed-Forward 3D Reconstruction

May 19, 2026

Position: The Turing-Completeness of Autoregressive Transformers Relies Heavily on Context Management

Many works make the eye-catching claim that Transformers are Turing-complete. However, the literature often conflates two distinct settings: (i) a fixed Transformer system setting, in which a fixed autoregressive Transformer is coupled with a fixed context-management method to process inputs of different lengths step by step, and (ii) a scaling-family setting, in which a family of different models (with increasing context-window length or numerical precision) is used to handle different input lengths. Existing proofs of Transformer Turing-completeness are frequently established in setting (ii), whereas real-world LLM deployment and the standard notion of Turing-completeness correspond more naturally to setting (i). In this paper, we first formalize the fixed-system setting, thereby providing a concrete characterization of how real-world LLMs operate. We then argue that results proved in the scaling-family setting provide theoretically meaningful resource bounds but do not establish Turing-completeness, thereby clarifying a common misinterpretation of existing results. Finally, we show that different context-management methods can yield sharply different computational power, and we advocate the position that context management is a central component that critically determines the computational power of real-world autoregressive Transformers.

Guanyu Cui, Zhewei Wei, Kun He

Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China · DEKE Lab, Renmin University of China, Beijing, China

Transformer Expressivity Transformer LLM Context Management Autoregressive Transformer

May 11, 2026

Attention Drift: What Autoregressive Speculative Decoding Models Learn

Speculative decoding accelerates LLM inference by drafting future tokens with a small model, but drafter models degrade sharply under template perturbation and long-context inputs. We identify a previously-unreported phenomenon we call attention drift: as the drafter generates successive tokens within a speculation chain, attention progressively moves from the prompt onto its own recently-generated tokens. We observe this across both EAGLE3 drafters and MTP heads, suggesting drift is a property of drafter designs. We trace this to the un-normalized residual path between chain steps: the drafter's hidden state magnitude grows monotonically with chain depth, which exhibits dynamics consistent with additional pre-norm transformer layers stacked on the target rather than as a standalone autoregressive predictor. In order to limit the growth, we propose two architectural changes: Post-norm on the drafter hidden states and per-hidden-state RMSNorm after capturing target hidden states. Our interventions improve acceptance length over the current leading model, pre-norm EAGLE3, by up to

2\times

under template perturbation,

1.18\times

on long-context tasks, and

1.10\times

on seven standard benchmarks spanning multi-turn chat, math, and coding. Our changes also allow shorter train-time-test depths to generalize over longer drafting sequences.

Doğaç Eldenk, Payal Mohapatra, Yigitcan Comlek +3

Northwestern University · GE Aerospace · fal +1

Long-Context Language Model Inference Speculative Decoding Transformer Attention LLM Inference Acceleration Layer Normalization Autoregressive Transformer

May 7, 2026

Long Context Pre-Training with Lighthouse Attention

Training causal transformers at extreme sequence lengths is bottlenecked by the quadratic time and memory of scaled dot-product attention (SDPA). In this work, we propose Lighthouse Attention, a training-only symmetrical selection-based hierarchical attention algorithm that wraps around ordinary SDPA and can be easily removed towards the end of the training. Our hierarchical selection is also gradient-free, which exempts us from dealing with a complicated and potentially inefficient backward pass kernel. Our contribution is three-fold: (i) A subquadratic hierarchical pre- and post-processing step that does adaptive compression and decompression of the sequence. (ii) A symmetrical compression strategy that pools queries, keys and values at the same time, while preserving left-to-right causality, which greatly improves parallelism. (iii) A two stage training approach which we pre-train for the majority of the time with Lighthouse Attention and recover a full attention model at the end with a short training. We run preliminary small scale LLM pre-training experiments that show the effectiveness of our method compared to full attention training with all other settings matched, where we achieve a faster total training time and lower final loss after the recovery phase. Full code is available at: https://github.com/ighoshsubho/lighthouse-attention

Bowen Peng, Subho Ghosh, Jeffrey Quesnelle

Nous Research

Attention Mechanisms Self-Attention Long-Context Language Modeling Language Model Pretraining Efficient Attention Causal Attention+1

Apr 23, 2026

The Recurrent Transformer: Greater Effective Depth and Efficient Decoding

Transformers process tokens in parallel but are temporally shallow: at position

t

, each layer attends to key-value pairs computed based on the previous layer, yielding a depth capped by the number of layers. Recurrent models offer unbounded temporal depth but suffer from optimization instability and historically underutilize modern accelerators. We introduce the Recurrent Transformer, a simple architectural change where each layer attends to key-value pairs computed off its own activations, yielding layerwise recurrent memory while preserving standard autoregressive decoding cost. We show that the architecture can emulate both (i) a conventional Transformer and (ii) token-to-token recurrent updates under mild assumptions, while avoiding optimization instability. Naively, prefill/training appears bandwidth-bound with effective arithmetic intensity near

1

because keys and values are revealed sequentially; we give an exact tiling-based algorithm that preserves the mathematical computation while reducing HBM traffic from

Θ(N^2)

to

Θ(N\log N)

, increasing effective arithmetic intensity to

Θ(N/\log N)

for sequence length

N

. On 150M and 300M parameter C4 pretraining, Recurrent Transformers improve cross-entropy over a parameter-matched Transformer baseline and achieve the improvement with fewer layers (fixed parameters), suggesting that recurrence can trade depth for width, thus reducing KV cache memory footprint and inference latency.

Costin-Andrei Oncescu, Depen Morwani, Samy Jelassi +3

Harvard University

Autoregressive Language Modeling Self-Attention Attention Mechanisms Efficient Transformer Inference Recurrent Transformers Efficient Attention+1

Apr 22, 2026

A Hybridizable Neural Time Integrator for Stable Autoregressive Forecasting

For autoregressive modeling of chaotic dynamical systems over long time horizons, the stability of both training and inference is a major challenge in building scientific foundation models. We present a hybrid technique in which an autoregressive transformer is embedded within a novel shooting-based mixed finite element scheme, exposing topological structure that enables provable stability. For forward problems, we prove preservation of discrete energies, while for training we prove uniform bounds on gradients, provably avoiding the exploding gradient problem. Combined with a vision transformer, this yields latent tokens admitting structure-preserving dynamics. We outperform modern foundation models with a

65\times

reduction in model parameters and long-horizon forecasting of chaotic systems. A "mini-foundation" model of a fusion component shows that 12 simulations suffice to train a real-time surrogate, achieving a

9{,}000\times

speedup over particle-in-cell simulation.

Brooks Kinch, Xiaozhe Hu, Yilong Huang +6

Mechanical Engineering and Applied Mechanics, University of Pennsylvania, Philadelphia, PA, USA · Department of Mathematics, Tufts University, Medford, MA, USA · Department of Mathematics and Cybernetics, SINTEF Digital, Oslo, Norway +3

Neural Surrogate Modeling Time Series Transformers Chaotic Time-Series Prediction Autoregressive Modeling Neural Network Stability Autoregressive Transformer

Apr 14, 2026

Applied AI-Enhanced RF Interference Rejection

AI-enhanced interference rejection in radio frequency (RF) transmissions has recently attracted interest because deep learning approaches trained on both the signal of interest (SOI) and the signal mixture (SOI plus interference) can outperform traditional approaches which only consider the SOI. The goal is to detect, demodulate, and decode signals over a range of signal-to-interference-plus-noise (SINR) levels without having a detailed, design-level knowledge of the interfering signal or the propagation conditions. Our present AI interference suppression results are based on Autoregressive Transformer Decoder models which exhibit orders of magnitude faster throughput at inference time than WaveNet models developed in earlier work. As a specific example, we investigate an analog FM "Walkie Talkie" radio signal of interest in the presence of an Orthogonal Frequency-Division Multiplexing (OFDM) interferer. This type of interferer is near-ubiquitous in the current RF landscape. Our results clearly show the benefits of transformer-based interference mitigation in tactical settings. We show that unintelligible transmissions become intelligible via metrics such as Perceptual Evaluation of Speech Quality (PESQ), while overall latency is kept to a minimum using readily available lightweight GPUs such as a Jetson AGX Orin. We believe these same techniques can also be applied to a broader set of national security scenarios, as well as having commercial applications.

Rahul Jain, Pierre Trepagnier, Rick Gentile +2

MIT Lincoln Laboratory, Lexington, MA 02421, USA

Autoregressive Transformer Wireless Communications

Apr 8, 2026

MARS: Enabling Autoregressive Models Multi-Token Generation

Autoregressive (AR) language models generate text one token at a time, even when consecutive tokens are highly predictable given earlier context. We introduce MARS (Mask AutoRegreSsion), a lightweight fine-tuning method that teaches an instruction-tuned AR model to predict multiple tokens per forward pass. MARS adds no architectural modifications, no extra parameters, and produces a single model that can still be called exactly like the original AR model with no performance degradation. Unlike speculative decoding, which maintains a separate draft model alongside the target, or multi-head approaches such as Medusa, which attach additional prediction heads, MARS requires only continued training on existing instruction data. When generating one token per forward pass, MARS matches or exceeds the AR baseline on six standard benchmarks. When allowed to accept multiple tokens per step, it maintains baseline-level accuracy while achieving 1.5-1.7x throughput. We further develop a block-level KV caching strategy for batch inference, achieving up to 1.71x wall-clock speedup over AR with KV cache on Qwen2.5-7B. Finally, MARS supports real-time speed adjustment via confidence thresholding: under high request load, the serving system can increase throughput on the fly without swapping models or restarting, providing a practical latency-quality knob for deployment.

Ziqi Jin, Lei Wang, Ziwei Luo +1

Nanyang Technological University · Singapore Management University · Uppsala University

Multi-Token Prediction LLM Inference Acceleration Autoregressive Language Modeling Autoregressive Transformer LLM Fine-Tuning

Mar 16, 2026

Modeling Matches as Language: A Generative Transformer Approach for Counterfactual Player Valuation in Football

Evaluating football player transfers is challenging because player actions depend strongly on tactical systems, teammates, and match context. Despite this complexity, recruitment decisions often rely on static statistics and subjective expert judgment, which do not fully account for these contextual factors. This limitation stems largely from the absence of counterfactual simulation mechanisms capable of predicting outcomes in hypothetical scenarios. To address these challenges, we propose ScoutGPT, a generative model that treats football match events as sequential tokens within a language modeling framework. Utilizing a NanoGPT-based Transformer architecture trained on next-token prediction, ScoutGPT learns the dynamics of match event sequences to simulate event sequences under hypothetical lineups, demonstrating superior predictive performance compared to existing baseline models. Leveraging this capability, the model employs Monte Carlo sampling to enable counterfactual simulation, allowing for the assessment of unobserved scenarios. Experiments on K League data show that simulated player transfers lead to measurable changes in offensive progression and goal probabilities, indicating that ScoutGPT captures player-specific impact beyond traditional static metrics.

Miru Hong, Minho Lee, Geonhee Jo +4

University of Seoul, Seoul, Republic of Korea · Saarland University, Saarbrücken, Germany · KAIST, Daejeon, Republic of Korea +2

Autoregressive Transformer Counterfactual Prediction Sports Outcome Prediction Causal Counterfactual Generation

Mar 3, 2026

Thinking into the Future: Latent Lookahead Training for Transformers

Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to commit at every step, preventing it from exploring or reflecting upon multiple plausible continuations. Furthermore, the compute allocation across tokens is uniform; every token is formed based on a single forward-pass, potentially limiting the model's expressiveness in cases where difficult tokens require inherently more compute. Towards addressing these limitations, we introduce latent lookahead, a training strategy that enables models to "think" before generating: at selected positions in the sequence, before committing to the next token, the model performs a multi-step lookahead in latent space. More precisely, instead of sampling future tokens, we leverage the network's latent space by recursively feeding its hidden states back into the context for

τ

steps, investing more compute on predicting that token. This produces

τ

latent predictions that are supervised against the next

τ

ground-truth tokens, encouraging the model to "lookahead" and refine its prediction. We show that latent lookahead substantially outperforms both autoregressive and non-autoregressive baselines on planning tasks such as maze solving, Sudoku, and ProsQA, where foresight is essential.

Lorenzo Noci, Gregor Bachmann, Seyed-Mohsen Moosavi-Dezfooli +1

Apple

Autoregressive Language Modeling Sequence Prediction Autoregressive Transformer LLM Planning Continuous Latent Reasoning

Nov 4, 2025

STAR-VAE: A Scalable Latent-Variable Transformer for Controllable Molecular Generation

Many molecular Transformers lack probabilistic latent variables for posterior inference and latent interpolation. We introduce STAR-VAE, a SELFIES-encoded, Transformer-based, AutoRegressive Variational AutoEncoder combining a bidirectional encoder with an autoregressive decoder pretrained on 79 million PubChem molecules. A property signal jointly conditions the prior, posterior, and decoder, while LoRA adapters support fine-tuning on small datasets without modifying the backbone. STAR-VAE achieves 100% validity and near-perfect novelty under unconditional MOSES sampling, the lowest KL divergence on five of ten GuacaMol descriptors, Spearman \r{ho} = 0.62 at 98% validity for synthetic-accessibility conditioning, and directional docking-score control for three Tartarus protein targets. Across four ChEMBL targets, seed-based posterior sampling recovers target-associated held-out scaffolds while label-conditioned sampling produces structurally diverse outputs. Code is available at https://github.com/BiomedSciAI/STAR-VAE.

Bum Chul Kwon, Ben Shapira, Moshiko Raboh +7

IBM Research, Cambridge, MA, USA · IBM Research, Haifa, Israel · IBM Research, Yorktown Heights, NY, USA

Molecular Optimization Transformer Autoregressive Transformer AI-Assisted Scientific Research Molecular Generation Conditional Variational Autoencoder+1

Oct 31, 2025

Training LLMs Beyond Next Token Prediction - Filling the Mutual Information Gap

Autoregressive language models are usually trained with next-token prediction under a fixed left-to-right target order. This paper studies target-token organization as a training-time design choice across arithmetic reasoning, multi-label text classification, and text generation. Controlled order studies show that the default NTP order can be far from the best-performing tested organization, while fixed hand-crafted orders such as reverse order do not generalize across tasks. To address this, Max(MI(S;t)) is introduced as a deterministic mutual-information-based heuristic that prioritizes information-rich target tokens. For fixed-length outputs, it constructs task-specific prediction orders; for open-vocabulary text generation, the same principle is applied through lightweight prefix augmentation. Experiments with GPT-style models and pretrained Llama/Qwen variants show that Max(MI(S;t)) often improves over standard NTP and simple baselines such as reverse order, TF-IDF, and conditional-probability selection, without changing model architecture or autoregressive decoding.

Chun-Hao Yang, Bo-Han Feng, Tzu-Yuan Lai +3

National Taiwan University

Autoregressive Language Modeling Sequence Prediction Autoregressive Transformer