Search research

High-precision heavy-duty grading is a common step in earthworks, traditionally carried out manually by skilled operators. Removing a significant amount of material while achieving a high-precision surface requires substantial machine-specific experience. Different hydraulic architectures react differently to operator inputs and soil interaction forces, which makes generalizable controllers challenging. In this paper, we present an autonomous controller that achieves high-precision grading at expert-operator speed on Load Sensing and Negative Flow Control machines alike. We split our controller into two parts: (1) a hydraulic-aware low-level loop that is hydraulic architecture-specific and (2) a path-tracking layer that coordinates joint motions and responses. Through a calibration process, our technique is applicable to load-sensing and negative-flow-control machinery. To showcase its versatility, we benchmark our approach on two excavators with different hydraulics and compare it against a commercial state-of-the-art solution. Our technique (RMSE 1.8cm) outperforms the commercial solution (RMSE 4.7cm) in precision by a factor of 2.6 and improves machine usage by leveraging the maximum function pressure, as opposed to commercial solutions that stall prematurely.

Metric-induced discrete flow matching (MI-DFM) exploits token-latent geometry for discrete generation, but its practical use is limited by two issues: heuristic schedulers requiring hyperparameter search, and finite-step path-tracking error from its first-order continuous-time Markov chain (CTMC) solver. We address both issues. First, we derive a kinetic-optimal scheduler for prescribed scalar-parameterized probability paths, and instantiate it for MI-DFM as a training-free numerical schedule that traverses the path at constant Fisher-Rao speed. Second, we introduce a finite-step moment correction that adjusts the jump probability while preserving the CTMC jump destination distribution. We validate the resulting method, GibbsTTS, on codec-based zero-shot text-to-speech (TTS). Under controlled comparisons with a unified architecture and large-scale dataset, GibbsTTS achieves the best objective naturalness and is preferred in subjective evaluations over masked discrete generative baselines. Additionally, in comparison with the evaluated state-of-the-art TTS systems, GibbsTTS shows strong speaker similarity, achieving the highest similarity on three of four test sets and ranking second on the fourth. Project page: https://ydqmkkx.github.io/GibbsTTSProject

The Linear Assignment Problem is a fundamental combinatorial optimization task where classical exact solvers ensure optimality but suffer from an $\mathcal{O}(N^{3})$ bottleneck, while recent neural approximations struggle with scalability and exactness. We propose a learning-augmented framework that accelerates exact solvers by predicting dual variables to warm-start the search, backed by a fallback mechanism to preserve worst-case guarantees. Central to our approach is RowDualNet, a lightweight, row-independent architecture that avoids the $\mathcal{O}(N^{2})$ memory bottleneck of graph models, enabling scalable neural warm-starting up to $N=16{,}384$. Feasibility is guaranteed by construction via the Min-Trick mechanism, completely eliminating the need for costly iterative projections. Empirically, our method drastically reduces the search effort of the Jonker-Volgenant (LAPJV) algorithm, yielding robust zero-shot generalization with strict optimality and end-to-end speedups of over 2x on complex synthetic data, 1.25x on real-world tracking, and 1.5x on transportation networks.

Long-horizon video generation has advanced in visual quality, yet existing methods still struggle to maintain knowledge consistency and coherent pedagogical narratives across multi-shot instructional videos, especially in STEM domains. To address these challenges, we propose EduStory, a unified framework for reliable instructional video generation. EduStory integrates pedagogical state modeling to track persistent knowledge states, script-guided structured control to organize multi-shot narratives, and learning-oriented evaluation metrics to assess knowledge fidelity and constraint satisfaction. To support rigorous evaluation, we further introduce EduVideoBench, a diagnostic benchmark with multi-granularity annotations, including pedagogical storyboards, shot-level semantics, and knowledge state transitions, together with baseline tasks for controllable instructional video generation. Extensive experiments demonstrate that domain-aware state modeling and structured control substantially reduce narrative breakdown and improve alignment with instructional intent. These results highlight the significance of domain-specific structural constraints and tailored benchmarks for advancing reliable, controllable, and also trustworthy long-horizon video generation.

Video MLLMs face a persistent tension between spatial fidelity and temporal coverage: preserving fine-grained visual details requires many spatial tokens, while capturing short-lived events requires dense temporal sampling. We propose \textbf{Fre-Res}, a budget-adaptive dual-track video-token compression framework that separates these two forms of evidence. Fre-Res preserves sparse high-fidelity spatial anchors and represents dense temporal evolution through compact residual-frequency tokens. Specifically, it applies temporal 1D-DCT to inter-frame residual trajectories in vision-latent space, where we observe strong low-frequency concentration. To align frequency-domain dynamics with native visual embeddings, Fre-Res introduces a Spatial-Guided Absorber that injects temporal residual information into spatially corresponding anchor tokens. Across fine-grained short-video and long-video reasoning benchmarks, Fre-Res achieves a favorable accuracy--efficiency trade-off, matching or approaching full-token performance while substantially reducing visual-token length. Extensive ablations further show that temporal-frequency residuals preserve causal transition cues, while spatial anchors remain essential for fine-grained object and layout reasoning.

Large language models fail at counting repeated tokens despite strong performance on broader reasoning benchmarks. These failures are commonly attributed to limitations in internal count tracking. We show this attribution is wrong. Linear probes on the residual stream decode the correct count with near-perfect accuracy at every post-embedding layer, across all model depths. This holds even at the exact layers where the wrong answer crystallizes while the model simultaneously outputs an incorrect count. Attention patterns show no evidence of collapse over repeated tokens and tokenization artifacts account for none of the failure. Instead, a format-triggered multi-layer perceptron (MLP) block overwrites the correctly-encoded count with a fixed wrong answer at roughly 88--93,% network depth. This prior fires for repeated word-tokens in space-separated list format and is absent for repeated digit-tokens. It is suppressed by comma-separated delimiters in larger models but persists in smaller ones. The finding holds across Llama-3.2 (1B and 3B) and Qwen2.5 (1.5B, 3B and 7B) at consistent relative depth. Counting failure is a failure of routing not of representation and the two require different interventions.

We investigate the geometry of predictive information across the layers of large language models (LLMs). We repurpose representation lenses-learned affine maps trained to predict the next token from intermediate residual streams-as geometric diagnostic tools. Rather than asking what the model predicts at each layer, we ask where predictive information resides and how it evolves across depth. We define at each layer a predictive readout subspace as the dominant k-dimensional singular subspace of such a map on the d-dimensional residual stream (where k is a resolution parameter), and track its trajectory on the Grassmann manifold as a similarity profile across layers. The profile is well described by unimodal distributions exhibiting a rise, near-plateau, and descent; varying k from 1% to 50% of d traces a Pareto frontier between visibility and energy retention, yet the same structure emerges at all scales. Across eight models from two families (Qwen2.5 and OLMo2, 1B-32B), we identify three geometric phases. Updates are approximately orthogonal to the residual stream throughout; what distinguishes the phases is their effect on the effective rank, which expands, stabilizes, and concentrates. In the first, Seeding Multiplexing, feed-forward memories and attention layers seed a candidate set in superposition in family-specific proportions, with the final token rising as leading candidate from 20% to 35% of positions across this phase. In the second, Hoisting Overriding, updates override existing subspaces to concentrate the candidate distribution without expanding the rank. In the third, Focal Convergence, high-energy low-rank updates write the winner into a form aligned with the unembedding direction. Phases 1 and 3 grow slowly with model depth, while Phase 2 expands linearly. The additional capacity of deeper LLMs is largely absorbed by candidate disambiguation.

Self-evolving agents present a promising path toward continual adaptation by distilling task interactions into reusable knowledge artifacts. In practice, this paradigm remains hindered by two coupled bottlenecks: data inefficiency, where costly rollout effort is disproportionately spent on low-value samples rather than informative ones, and knowledge interference, where heterogeneous knowledge stored in shared repositories leads to noisy retrieval and task-misaligned guidance. Together, these issues form a self-reinforcing failure loop in which uninformative rollouts yield noisy knowledge, which in turn degrades subsequent rollouts. In this work, we introduce Ace-Skill, a co-evolutionary framework that jointly optimizes rollout allocation and knowledge organization for self-evolving multimodal agents. Specifically, Ace-Skill combines aprioritized sampler with lazy-decay proficiency tracking to focus rollouts on informative and insufficiently mastered samples, and a clustered organizer that semantically clusters knowledge for cleaner retrieval and more reliable adaptation. By improving sampling and organization together, Ace-Skill turns self-evolution into a virtuous cycle in which more informative rollouts produce higher-quality knowledge that supports stronger subsequent rollouts. Across four multimodal tool-use benchmarks, Ace-Skill delivers strong gains (e.g., +35.46% relative improvement in Avg@4 accuracy), enabling an opensource 35B MoE model to match or surpass proprietary models. The acquired knowledge also transfers effectively in a zero-shot manner to smaller 9B and 4B models, allowing resource-constrained agents to inherit advanced capabilities without additional training. The code has been publicly available at https://github.com/AMAP-ML/Ace-Skill.

Recent advances in uncertainty quantification for time series forecasting show that conformal prediction can provide reliable prediction intervals, yet standard conformal methods are often inefficient under temporal dependence, drift, and heterogeneous error behavior. Existing methods typically either update miscoverage rates over time or learn unconstrained calibration weights, without explicitly separating two central sources of nonstationarity: smoothly drifting error distributions and co-existing distinct error regimes. We introduce RareCP, a regime-aware retrieval method for adaptive conformal time series prediction. RareCP learns local calibration representations through a mixture of cosine-attention experts that each capture distinct error regimes, while a compact hypernetwork adapts the kernel parameters to track temporal drift. Given a new forecasting context, RareCP retrieves the top-k most relevant calibration examples, assigns similarity weights, and forms a weighted conformal quantile over their signed residuals, yielding asymmetric prediction intervals. The adaptive kernel is trained using a smooth interval score objective, with a parameter-space anchor to a lightweight teacher kernel to preserve stable local representations. On the GIFT-Eval benchmark, RareCP improves interval efficiency over recent conformal baselines and foundation model uncertainty estimates while maintaining empirical coverage. Ablations confirm that regime-specific experts, drift-adaptive kernels, sparse retrieval, and teacher anchoring each contribute to the final performance.

Large language model agents increasingly operate through environment-facing scaffolds that expose files, web pages, APIs, and logs. These observations influence tool use, state tracking, and action sequencing, yet their reliability and authority are often uncertain. Environmental grounding is therefore a systems-level problem involving context admission, evidence provenance, freshness checking, verification policy, action gating, and model reasoning. Existing agent benchmarks mainly evaluate task capability or specific attacks such as prompt injection and memory poisoning, but they under-specify a fundamental reliability question: whether agents remain grounded in the true environment state when observations are stale, incorrect, or malicious. We introduce EnvTrustBench, an agentic framework for benchmarking this failure mode. We define an evidence-grounding defect (EGD) as a behavioral failure in which an agent treats an environment-facing claim as sufficient evidence for action without resolving it against available current evidence, leading to a task-incorrect false path under the true environment state. Given a task scenario, EnvTrustBench generates the workspace, environment, agent-facing objective, and validation oracle, executes the evaluated agent, records its action-observation trajectory and final state, and applies the oracle to produce a verdict. Using 6 LLM backbones and 5 widely used scaffolds, we evaluate 55 generated cases across 11 task scenarios, with each scenario expanded through five feedback-guided generation iterations. Results show that EGDs consistently emerge across operational workflows, highlighting environmental grounding as a core agent reliability problem with important security implications.

AI-assisted bridge defect inspection often produces bounding boxes with crude geometry or raster masks that are costly to store, transmit, and reuse. This study investigates how detected defects can be represented as compact, recoverable contour-level vector records in image space. We propose Frequency-Supervised Fourier Series Detection (FS-FSD), which directly regresses Fourier contour descriptors and evaluates boxes, masks, and contours under a unified polygon-space protocol. On 3,767 UAV-collected bridge images with 42,346 defect instances, FS-FSD achieves higher polygon-space accuracy and better matched-TP geometric quality than representative detection, segmentation, and contour baselines. These results show that, compared with bounding boxes and raster masks, Fourier contour records preserve defect-boundary geometry in a more compact, recoverable, and shareable form for engineering review and downstream information workflows. Future work will study the modeling of multi-region, fragmented, and adjacent bridge-defect boundaries and extend the framework toward long-term bridge-defect tracking and lifecycle-oriented management.

Mode separation, namely how sharply a distribution fragments into barrier-separated clusters, is a fundamental geometric property of densities, difficult to quantify in high dimensions. It is structurally distinct from dispersion, yet existing tools fall short: differential entropy rises with spread regardless of fragmentation, PCA orders directions by variance regardless of barriers, and mutual information requires a mixture decomposition one usually does not have. We measure mode separation through a single stochastic process intrinsic to the density: a unique reversible diffusion with $f$ as its stationary distribution and constant scalar diffusion coefficient. We extract two readouts from its autocovariance matrix: SSA (Sum of Squared Autocorrelations), a scalar barrier-sensitive measure; and DA (Dominant Autocorrelation directions), linear projections ordered by metastability rather than variance. Under an isotropic-Gaussian null, we derive a closed-form spectrum for the empirical autocovariance that generalizes Marchenko--Pastur, with an analytic upper edge that selects the lag at which DA is read off. Both readouts use only samples and a score function, scaling to high dimensions through pretrained score-based generative models via Tweedie's identity. We apply our framework to three settings: (i) synthetic Gaussian mixtures, where SSA tracks mutual information; (ii) SDXL text-to-image generations, where SSA and DA capture structure that entropy and PCA miss; and (iii) molecular dynamics of alanine dipeptide, where DA recovers the known slow backbone dihedrals from static samples alone.

In training a neural network with gradient descent (GD), each iteration induces a linear operator that governs first-order updates to a model's internal state variables. We define this operator as the Global Empirical Neural Tangent Kernel (NTK). In finite-width networks, the NTK is typically intractable to form, leading prior work to focus on restrictive settings such as tracking outputs only or taking infinite-width limits. Here, we study the structure of the NTK for a range of models. Formulating the model state as the solution to a single global implicit constraint, we derive the NTK as a product of two operators: K, accounting for immediate parameter-to-state interactions, and P, describing internal state-to-state dependencies. For a broad class of weight-based models, including RNNs and transformers, we prove a universal Kronecker-core theorem showing that K admits an exact, computable form given by the Gram matrix of weight-site variables. This core structure reveals that the NTK is structurally bottlenecked, constraining its effective rank and giving rise to a self-referential bias whereby GD preferentially learns within dominant modes of joint hidden and input activity. For recurrent models, we examine the spectrum of the NTK and show when it is biased and low-rank in space or time under the proposed decomposition. We further demonstrate that model dynamics at initialization bias the NTK, restricting learning and preventing task components from being learned effectively. Finally, we show that the NTK associated with a self-attention transformer is likewise structurally constrained to be low-rank. Overall, we show that the NTK possesses tractable structure that explains GD bias toward task solutions and the emergence of low-rank representations. To enable use of the NTK as a practical metric, we build kpflow, a library relying on randomized matrix-free numerical linear algebra.

Action-conditioned surgical video generation is a critical yet highly challenging problem for robotic surgery. The core difficulty is that low-dimensional control vectors must precisely govern complex image-space evolution. In this work, we propose a kinematic-to-visual lifting paradigm that converts articulated kinematics into a unified set of five image-aligned control modalities. Building on this representation, we introduce a hierarchically routed visual control framework that selectively activates the most relevant control modalities and motion scales. Instead of uniformly applying all control signals, our model performs hierarchical routing to dynamically allocate conditioning capacity. We further design kinematic-prior-guided routing loss functions to ensure physically meaningful, temporally stable, and efficient expert utilization. To improve efficiency, we propose a budgeted training and inference scheme that leverages routing-induced sparsity. By selectively discarding low-significance control pathways during training and execution, our approach enables adaptive computation that is complementary to standard distillation. We additionally construct a new benchmark with curated articulated annotations, obtained through human-in-the-loop semantic labeling and differentiable pose tracking, providing realistic supervision for action-conditioned surgical video generation. Extensive experiments demonstrate that our method consistently improves action faithfulness, visual fidelity, and cross-domain generalization over diverse baselines. Moreover, our efficient variant achieves substantial reductions in latency while maintaining strong control accuracy.

Many biological systems evolve through continuous local dynamics while switching between latent regimes defined by learning, stimulus context, internal state, or developmental stage. These processes are often observed only as unpaired longitudinal snapshots: the same cells, neurons, or animals are not tracked as matched trajectories, even though population states are sampled across successive stages. This creates two coupled challenges. First, trajectories must respect curved low-dimensional manifolds embedded in high-dimensional biological measurements. Second, the model must identify when the transport mechanism itself changes. We introduce FLUX (FLow matching for Unpaired longitudinal data with miXture-of-experts), a geometry-aware longitudinal flow-matching framework for joint transport modeling and unsupervised regime discovery. FLUX learns a data-dependent metric from pooled labeled and unlabeled observations, uses that metric to construct geometry-aware conditional paths between adjacent marginals, and decomposes the resulting velocity field into sparse expert vector fields selected by a Straight-Through Gumbel-Softmax router. Across manifold controls, a regime-switching Lorenz system, widefield cortical calcium imaging during associative learning, and embryoid body single-cell differentiation, FLUX reconstructs longitudinal transport while recovering interpretable regime structure. Ablations show that mixture-of-experts routing alone is insufficient: FLUX without geometric learning can fit local transport but fails or weakens regime discovery when regimes are encoded in local dynamics. These results suggest that geometry-aware velocity decomposition provides a general strategy for discovering latent biological state transitions from unpaired longitudinal snapshots.

Large Language Models (LLMs) are increasingly applied to forecasting. To evaluate this capability while mitigating pre-training data contamination, several living benchmarks have been proposed. However, existing benchmarks either lack the multidimensional events essential for accurate forecasting due to data scarcity, or focus on relatively closed environments. To assess the predictive capabilities of LLMs in complex, real-world scenarios, we propose LEAF, the first living benchmark for event-augmented forecasting tasks, including future event probabilities, trend and time series forecasting. LEAF utilizes a recursive retrieval agent system paired with dual-agent cross-validation to provide comprehensive and relevant auxiliary text for forecasting. Evaluating state-of-the-art proprietary and open-weight LLMs, we find that these models can leverage signals extracted from complex events to enhance predictive performance. In the stock domain, we find that LLMs achieve better performance on equities they confidently identify as more predictable. Furthermore, the events demonstrate a strong correlation with the target equities. To this end, LEAF provides a necessary, dynamically updating testbed to continuously track and drive progress in event-driven forecasting tasks.

Agent benchmarks typically report only final outcomes: pass or fail. This threatens evaluation credibility in three ways. First, scores may be inflated or deflated by shortcuts and benchmark artifacts, misrepresenting capability. Second, benchmark performance may fail to predict real-world utility due to scaffold limitations and recurring failure modes. Finally, capability scores may conceal dangerous or catastrophic actions taken by the agent. We argue that log analysis -- the systematic tracking and analysis of the inputs, execution, and outputs of an AI agent -- is necessary to overcome these validity threats and promote credible agent evaluation. In this paper, we (1) present a taxonomy of threats to credible evaluation documented through log analysis, and (2) develop a set of guiding principles for log analysis. We illustrate these principles on tau-Bench Airline, revealing that pass^5 performance was under-elicited by nearly 50% and surfacing deployment failure modes invisible to outcome metrics. We conclude with pragmatic recommendations to increase uptake of log analysis, directed at diverse stakeholders including benchmark creators, model developers, independent evaluators, and deployers.

Current LLM agents lack principled mechanisms for managing persistent memory across long interaction horizons. We present a biologically-grounded memory architecture comprising six cognitive mechanisms: (1) sleep-phase consolidation, (2) interference-based forgetting, (3) engram maturation, (4) reconsolidation upon retrieval, (5) entity knowledge graphs, and (6) hybrid multi-cue retrieval. Each mechanism addresses a specific failure mode of naive memory accumulation. We introduce a synthetic calibration methodology that derives all pipeline thresholds without benchmark data exposure, eliminating a common source of evaluation leakage. We evaluate on two benchmarks. First, a VSCode issue-tracking dataset (13K issues, 120K events) where deduplication-based consolidation achieves 97.2% retention precision with 58% store reduction (+21.8 pp over baseline). Second, the LongMemEval personal-chat benchmark where we conduct the first streaming M-tier evaluation (475 sessions, ~540K unique turns). At a 200K-token context budget, our pipeline matches raw retrieval accuracy (70.1% vs. 71.2%, overlapping 95% CI) while exposing a tunable accuracy/store-size operating curve. At S-tier scale (50 sessions), dedup-based consolidation yields a +13.3 pp improvement in preference recall.

Due to the system's scale and complex fabrication, the model describing the dynamics of a flapping-wing insect-scale aerial robot is subject to parameter uncertainty; for example, in the inertia matrix and the actuator mapping of the flier. Furthermore, due to its low inertia, this type of robot is greatly affected by stochastic and systematic disturbances during flight, including power-wire tension, gusts, and undesired aerodynamic forces produced by wing misalignment. Therefore, the high-performance execution of complex maneuvers at the subdecigram scale requires the robot to adapt its behavior to counteract disturbances and model uncertainty. Toward this objective, we introduce a model-reference adaptive control (MRAC) architecture for high-performance position control of flapping-wing robotic insects that can be modeled as rigid bodies in the three-dimensional (3D) space. In addition, we demonstrate how the implementation of a hybrid multiplicative extended Kálmán filter for estimating current and desired angular velocities during flight significantly dampens attitude vibrations, especially along the roll and pitch degrees of freedom (DOFs), and also improves flight performance. To show the suitability, functionality, and high performance of the proposed approach, we conducted real-time hovering and trajectory-tracking 6-DOF flight control experiments with a 95-mg insect-scale aerial robot.

LLM-based evolution has emerged as a promising way to improve agents by refining non-parametric artifacts, but its wall-clock cost remains a major bottleneck. We identify that this cost comes from synchronized stage execution and imbalance inside each LLM-heavy stage. We present FlashEvolve, an efficient framework that replaces synchronized execution with asynchronous workers and queues, allowing different stages and steps to overlap. To handle data staleness introduced by asynchrony, FlashEvolve tracks artifact versions and applies different policies to update, discard, or patch stale artifacts. Unlike weight-space staleness in asynchronous RL, language-space staleness is inspectable and repairable: a stale artifact is not just delayed work, but readable evidence that the LLM can reflect on, revise, and turn into useful evolution signal. FlashEvolve further improves throughput and token efficiency with speculative stage completion and adaptive workflow control. On GEPA workloads, FlashEvolve improves proposal throughput by $3.5\times$ on local vLLM and $4.9\times$ on API serving over synchronous GEPA. The same design also applies to ACE and Meta-Harness.

We describe an approach for estimating the statistical risk of deep networks that contain a mix of learned and known operators. Building on the maximal training error bounds previously established for known operator learning, we derive a deep risk estimator that connects the expected error of a layered network to the size of the training sample. The estimator decomposes the total risk into a sum over learned layers; every known operator contributes zero to this sum, while every learned layer adds an approximation term inspired by Barron's classic work and an estimation term that decreases with the number of training samples. We are able to show that the bound shrinks whenever a learned layer is replaced by a known operator and that the corresponding sample requirement scales with the number of trainable parameters of the layer that is replaced. As an application, we use computed tomography as an example and compare an operator-aware filtered backprojection network with a fully connected substitute that collapses the entire reconstruction pipeline into a single learned dense matrix. The predicted parameter ratio coincides with the structural sparsity that the analytic decomposition into a circulant filter and a sparse backprojection exposes. We confirm the predicted scaling on CPU at small image scale and on GPU at medium image scale, all on the same scaling law. Beyond CT reconstruction, the estimator applies to physics-informed neural networks that hardcode a known physical operation in its architecture, and we expect the result to be of interest for a broad community working on operator-aware deep learning. Calibrating the per-layer constants on each sweep yields a bound that tracks the empirical test MSE within a factor of two at every training-set size, so the estimator can be inverted to predict how many training samples are required to reach a target error.

How do LLMs learn in-context? Is it by pattern-matching recent tokens, or by inferring latent structure? We probe this question using a toy graph random-walk across two competing graph structures. This task's answer is, in principle, decidable: either the model tracks global topology, or it copies local transitions. We present two lines of evidence that neither account alone is sufficient. First, reconstructing the internal representation structure via PCA reveals that at intermediate mixture ratios, both graph topologies are encoded in orthogonal principal subspaces simultaneously. This pattern is difficult to reconcile with purely local transition copying. Second, residual-stream activation patching and graph-difference steering causally intervene on this graph-family signal: late-layer patching almost fully transfers the clean graph preference, while linear steering moves predictions in the intended direction and fails under norm-matched and label-shuffled controls. Taken together, our findings are most consistent with a dual-mechanism account in which genuine structure inference and induction circuits operate in parallel.

In structured decision-making workflows such as form filling, compliance checking, and maintenance reporting, LLM outputs must be locally correct, globally consistent, and auditable against task-specific rules. Existing refinement methods often rely on heuristic debate, self-play, or LLM-generated supervision, creating a second-order assurance problem. We propose DPA-GRPO (Dual Paired-Action Group-Relative Policy Optimization), a paired-action training method for a two-player generator--verifier game with structured verifier interventions. The generator proposes outputs and may revise them when challenged; the verifier either remains silent or raises a safety assurance case (SAC) containing a claim, argument, and evidence. These SAC/no-SAC and KEEP/REVISE decisions induce paired counterfactual action groups, which DPA-GRPO uses for role-specific KL-regularized GRPO updates. We analyze the unregularized game and show that positive probability on strictly lower-reward intervention or revision actions creates a profitable unilateral deviation. Under standard stochastic-approximation assumptions, DPA-GRPO tracks the corresponding game ODE, whose isolated asymptotically stable limit points are stationary and candidate local equilibria under role-wise local optimality. Experiments on TaxCalcBench TY24 show that DPA-GRPO improves structured decision accuracy over zero-shot generation and generator-only RL baselines across Qwen3-4B and Qwen3-8B. Training increases correct silent acceptance, reduces missed errors, and improves calibrated revision behavior, indicating gains for both generator and verifier.

We study the evolution of hidden-weight spectra in wide neural networks trained by (stochastic) gradient descent. We develop a two-level dynamical mean-field theory (DMFT) that jointly tracks bulk and outlier spectral dynamics for spiked ensembles whose spike directions remain statistically dependent on the random bulk. We apply this framework to two settings: (1) infinite-width nonlinear networks in mean-field/$μ$P scaling and (2) deep linear networks in the proportional high-dimensional limit, where width, input dimension, and sample size diverge with fixed ratios. Our theory predicts how outliers evolve with training time, width, output scale, and initialization variance. In deep linear networks, $μ$P yields width-consistent outlier dynamics and hyperparameter transfer, including width-stable growth of the leading NTK mode toward the edge of stability (EoS). In contrast, NTK parameterization exhibits strongly width-dependent outlier dynamics, despite converging to a stable large-width limit. We show that this bulk+outlier picture is descriptive of simple tasks with small output channels, but that tasks involving large numbers of outputs (ImageNet classification or GPT language modeling) are better described by a restructuring of the spectral bulk. We develop a toy model with extensive output channels that recapitulates this phenomenon and show that edge of the spectrum still converges for sufficiently wide networks.

Multi-robot systems in automated warehouses must manage continuous streams of pickup-and-delivery tasks while ensuring efficiency and safety. Prior work on Multi-Agent Pickup-and-Delivery (MAPD) has largely focused on the one-to-one variant, where each task has a fixed pickup and delivery location. In contrast, real warehouses often present many-to-many MAPD scenarios, where items, tracked by stock keeping unit (SKU) identifiers, can be retrieved from or stored at multiple locations, resulting in an NP-hard four-dimensional assignment problem. To solve the many-to-many MAPD problem, we contribute our algorithm: Many-to-Many Multi-Agent Pickup and Delivery (M2M). We experiment with two variants of our algorithm: one that minimizes estimated task durations (M2M), and one which incorporates SKU distribution into the objective function (M2M-wSKU). Simulation results over 8-hour warehouse operations show that our method consistently matches or outperforms prior state of the art, with M2M completing up to 22,000 more tasks on average across different environments and warehouse inventory densities.

Accurate truck-to-shipment matching using GPS data is foundational for full truckload supply chain visibility, enabling real-time tracking and accurate estimated time of arrival (ETA) predictions. However, missing or corrupted vehicle identifiers prevent traditional matching approaches, leaving shipments without visibility. This paper presents Intelligent Truck Matching (ITM) 2.0, a machine learning system that addresses this critical gap by formulating matching as a probabilistic ranking problem. Our approach leverages Uber H3 hexagonal spatial indexing to discretize GPS pings into route similarity features, combined with temporal information, then applies LightGBM gradient boosting with threshold-based post-processing. Through rigorous evaluation including offline model selection (SVM, XGBoost, LightGBM), comprehensive ablation studies, and production shadow testing, we demonstrate substantial gains over rule-based baselines. ITM 2.0 achieves 26 percentage point precision improvement in North America and 14 points in Europe, while doubling coverage. Deployed in production at Project44 handling full truckload shipments, the system demonstrates robustness to geocoding errors up to 1 km, multiple candidate trucks, and sparse pings.

Event cameras have emerged as a high-bandwidth, low-latency sensing modality for safety-critical perception in automated driving systems (ADS), offering microsecond temporal resolution, 120-140 dB dynamic range, and intrinsic absence of motion blur. However, no task-agnostic quality metric currently operates directly on the asynchronous event stream: state-of-the-art proxies require a downstream task (e.g., detection accuracy, tracking error) to assess stream integrity, which is incompatible with the certification requirements of ISO 21448 (SOTIF) and ISO/PAS 8800:2024. The recent BiasBench benchmark (CVPR 2025) explicitly identifies this gap. This work proposes a unified algebraic framework that lifts the Pearson Correlation Coefficient (PCC), historically used in two prior works for redundancy filtering and ROI selection on frame-based images, to the three standard event representations: Time Surface, Event Frame, and Voxel Grid. The framework yields three metrics: (i) r-TS for stream integrity monitoring against an ego-motion-predicted Time Surface, (ii) r2-EF for adaptive ROI selection requiring only integer comparisons, and (iii) r-VG for temporal redundancy gating. A structural isomorphism is established between the contrast-threshold mechanism of the event camera (|Delta L| >= C) and the PCC-based change criterion, the three lifted metrics are formalized, and pipeline latency and information loss are analyzed symmetrically against the raw stream. Illustrative behavior of each metric is demonstrated on a procedural-synthetic event stream, generated by direct simulation of the emission model rather than drawn from any real or video-derived dataset, including a tunnel-dip integrity-anomaly scenario in which r_C drops from 0.93 (coherent flow) to below 0 (alarm). An explicit epistemic convention ([ESTABLISHED], [SOLID], [HYPOTH.], [OPEN]) delineates the status of every contribution.

Forecasting future 3D hand pose sequences from egocentric video is essential for understanding human intention and enabling embodied applications such as AR/VR assistance and human-robot interaction. However, this task remains a highly challenging problem because egocentric hand motion is driven by complex human intent, exhibits highly dexterous articulations, and is observed under drastic viewpoint shifts induced by ego-motion. In this work, we introduce EggHand, a foundation-model-based framework for egocentric hand pose forecasting that unifies multimodal semantic reasoning with dynamic motion modeling. Our approach couples an action decoder from a Vision-Language-Action (VLA) model, which captures the structured temporal dynamics of hand motion, with an egocentric video-text encoder that provides viewpoint-aware contextual information learned from large-scale first-person video. Together, these components overcome the brittleness of generic visual encoders under ego-motion and enable joint reasoning over motion, context, and high-level intent-without relying on body pose or external tracking. Experiments on the EgoExo4D dataset show that EggHand sets a new state of the art in forecasting accuracy, remains robust under severe ego-motion, and further enables controllable prediction via language-based task prompts. Project page: https://jyoun9.github.io/EggHand

Recent work has shown that contiguous vision transformer (ViT) blocks (a) can be replaced by a linear map and (b) organize into recurrent phases of computation. We ask whether these observations coincide: does ViT depth implement approximately \textit{autonomous linear} dynamics, admitting a single operator $K$ applied recurrently across a contiguous span? We test this using Dynamic Mode Decomposition (DMD), which fits $K$ from selected, consecutive hidden-state pairs and predicts $p$ steps ahead via $K^p$. On four pretrained DINO ViTs, we study the regularization, rank, and calibration budget required for stable fitting. For short spans ($p \leq 4$), $K^p$ tracks an unconstrained endpoint map to within $0.02$ cosine similarity on DINOv3-H/16+, while also recovering intermediate activations at each skipped block. At early cut starts, the fitted operators compress to rank $\ll d$ with minimal calibration data, and across tokens, \texttt{cls} is most amenable to linearization; both properties decay monotonically with depth. Yet this local fidelity does not transfer downstream. At the final hidden state, after propagating through the remaining blocks, an identity baseline becomes competitive.

Large reasoning models (LRMs) achieve strong performance via extended chain-of-thought (CoT) reasoning, yet suffer from excessive token consumption and high inference latency. Existing reinforcement learning (RL) approaches for CoT compression rely on uniform, static length penalties that neglect model capability dynamics and problem-level difficulty variation. We propose \textbf{ExpThink}\xspace, an RL framework that addresses both dimensions through two complementary mechanisms. First, \emph{experience-guided reward shaping} tracks the shortest correct solution found so far for each problem and applies a three-tier reward: full credit for concise correct responses, discounted credit for verbose correct ones, and zero for incorrect ones. The threshold tightens automatically with model improvement, forming a self-evolving curriculum that requires no manual scheduling. Second, \emph{difficulty-adaptive advantage} replaces standard deviation normalization with correct-count normalization, yielding monotonically difficulty-scaled gradients that amplify learning on hard problems to preserve accuracy while suppressing gradients on easy ones to encourage brevity. Together, these mechanisms enforce an accuracy-first, compression-second training objective. Experiments on multiple mathematical reasoning benchmarks demonstrate that \textbf{ExpThink}\xspace reduces average response length by up to 77% while simultaneously improving accuracy, achieving up to $3\times$ higher accuracy-efficiency ratio (accuracy divided by average token count) than the vanilla baseline and outperforming existing RL-based compression methods on both metrics.