SEARCH · Searcharxiv

Search Searcharxiv

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 775 records · Page 43Linked to original sources

arXiv2026

PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformers

Quantization errors in video diffusion transformers can be amplified or attenuated by subsequent denoising updates, making local reconstruction error an incomplete predictor of final impact. We introduce PulseQuant, a 4-bit post-training quantization method that combines trajectory sensitivity with activation geometry to guide offline calibration. Isolated block--step interventions estimate propagation risk, which prioritizes sensitive trajectory states during row-radius selection. With these radii fixed, response-subspace correction uses neighboring-code edits to reduce residual components along dominant activation directions. Both stages preserve the original 4-bit weight representation. Controlled interventions show that short-horizon propagated error predicts final latent error more reliably than immediate block-output error, supporting calibration beyond local reconstruction objectives. Evaluations on Wan models, Self Forcing, and MiniMax-H3 demonstrate improvements in key consistency and dense-reference metrics while remaining competitive on other attributes across model scales and generation paradigms.

cs.CV↗

arXiv2026

SciGen-Verifier: A Multimodal Reasoner for Explainable Verification in Scientific Image Generation

In realistic education, a solution is often expressed not only in words but in a drawing--a circuit, a geometric construction, a function plot--and a teacher must grade the drawing as carefully as the text. Recent advances in unified multimodal models have enabled scientific image generation, yet verifying the correctness of these specialized visual outputs remains a critical bottleneck: errors often arise from intricate domain knowledge, structural reasoning, and multi-step instruction rather than surface-level artifacts. Existing verifiers mainly target natural images and compress judgement into scalar scores, leaving scientific coverage and explainable feedback for error correction underexplored. To bridge this gap, we make three main contributions. (1) We construct SciGen-Verify, a benchmark dedicated to explainable verification of scientific image generation, spanning instruction following, multidisciplinary reasoning, and world knowledge domains. It contains a three-tier hierarchical protocol over the binary judgement, supporting explanation, and corrective editing instruction. (2) We develop SciGen-Verifier, a reasoning-driven multimodal verifier trained via cold-start supervised fine-tuning followed by a curriculum-based two-stage reinforcement learning pipeline. The rubric-guided process rewards first strengthen scientific reasoning exploration and outcome rewards subsequently align output with ground-truth annotation. (3) On SciGen-Verify, SciGen-Verifier achieves competitive performance against much larger proprietary models. It further serves as a practical online critic for iterative image rectification.

cs.CV↗

arXiv2026

Evaluating System One Models for Agent Security Decisions: Reliability, Calibration, and Selective Automation

Model-based judges support agent security by detecting prompt injections, assessing interaction risks, and screening harmful requests. System One models select from predefined answers and report probabilities that software can use to allow, block, or review inputs, but the reliability of these automated decisions remains unclear. We evaluate Jev, Laya, Decider, and Bespoke Nimble against specialized classifiers and language-model judges, examining decision accuracy, probability calibration, and selective automation. We draw the following conclusions. (1) Strong overall performance and favorable aggregate calibration can hide failures concentrated in particular attack groups, including attacks classified as safe with high confidence. (2) The evaluated adapted configurations do not consistently improve classification over their base models across tasks. (3) Under the strictest evaluated error limits, the policies allow few inputs automatically, and separate allow and block thresholds increase automation mainly through more blocks. Passing confirmation does not ensure that these limits hold on test. (4) Judges can detect attacks missed by another model, but may also falsely flag more benign inputs and share the other model's high-confidence errors. These findings support evaluating model accuracy, probability calibration, and the resulting allow/block/review decisions together.

cs.CR↗

arXiv2026

Supergaussian pulse distortion in single-mode fibers with arbitrary dispersion

Marcuse theory of pulse distortion in singlemode fibers provides closed-form results for Gaussian pulses launched from sources of arbitrary spectral width. We extend the theory to supergaussian pulses of arbitrary order with linear or edge-concentrated chirp, single or multiline sources and an arbitrary number of dispersion coefficients. The rms output width is obtained exactly from the moments of the Wigner distribution, and all the pulse moments involved reduce to finite sums of Gamma functions. Supergaussian pulses are considerably more sensitive than Gaussian pulses to higher order dispersion and are compressed less efficiently by chirp. Near the zero-dispersion wavelength their rms width is governed by weak spectral side lobes and overestimates the broadening of the pulse energy. For pulse sequences, interference between neighboring pulses leaves all time moments unchanged when the input pulses do not overlap, but it redistributes energy locally with a visibility set by the source spectrum filtered by the pulse spectrum.

physics.optics↗

arXiv2026

TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining

Comparisons in video self-supervised learning often evaluate complete training recipes rather than isolating the method itself: architecture, objective, data exposure, schedule, scale, and decoder capacity can all vary at once. This makes it hard to identify which choices yield motion-prioritized representations, whose gains concentrate on frame-to-frame change while retaining useful appearance. We address this with a matched $4 \times 6 = 24$ architecture-objective study at roughly 170M ~ 190M encoder scale on $\sim$1.7M OpenVid and Moments-in-Time v2 clips for 8 epochs, and propose TT-VidT. TT-VidT combines a DINOv3-initialized ViT-B/16 per-frame spatial path with a compact Temporal Transfer Layer, trained by Diff Compression to reconstruct target frames from a first-frame appearance anchor and frame-specific motion tokens. The sweep shows that TT3D with Diff Compression, not either component alone, enters the strongest motion-sensitive regime, and decoder ablations favor a compact video-pretrained decoder. In final comparison, TT-VidT leads Jester, Something-Something V2, ARID, and Diving48 fine-tuning simultaneously, improving over the strongest non-TT row by 54% ~ 121%, while using 48% fewer encoder FLOPs than DisMo and 55% fewer than VideoMAE or V-JEPA2. HMDB51, IARD, and EPIC-Kitchens bound the claim.

cs.CV↗

arXiv2026

What Shared Prefixes Hide: Trajectory Dropout for On-Policy Distillation

On-policy distillation (OPD) trains a student model on its own trajectories using dense token-level feedback from a stronger teacher model. Since each update is conditioned on the reasoning prefix already generated by the student, the prefix also shapes how effectively teacher feedback is converted into learning. We find that shared prefixes can lead to weak token-level updates, a phenomenon we call Prefix-Induced Supervision Attenuation (PISA). This attenuation arises in two common cases. (i) High student confidence can weaken corrective gradients even when the teacher disagrees. (ii) Tokens that rely on earlier reasoning can receive learning signals as weak as those for simple local continuations. To solve this problem, we propose Trajectory Dropout, a simple training-time intervention that exposes these weakened signals. The student first performs a standard full-context rollout to generate a complete trajectory. During training, we randomly drop a certain proportion of the student's reasoning trajectory, while the teacher continues to observe the complete trajectory for token-level supervision. This intervention strengthens corrections for overconfident predictions and introduces additional supervision at prefix-sensitive positions. Trajectory Dropout consistently improves average performance across teacher--student model pairs of different scales and six mathematical reasoning benchmarks, while also yielding gains on two out-of-domain benchmarks. It can also be flexibly integrated into existing OPD variants with negligible computational overhead, further improving their performance. These results demonstrate that Trajectory Dropout provides a simple mechanism for strengthening token-level supervision across model scales and OPD objectives.

cs.AI↗

arXiv2026

SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera

Omnidirectional or 360 cameras provide embodied AI agents with a holistic, wide field-of-view (FoV) view of their surroundings, motivating the use of Multi-modal Large Language Models (MLLMs) for omnidirectional spatial reasoning. However, most MLLMs are trained on conventional 2D perspective images and struggle with the severe distortions and wrap-around discontinuities induced by spherical geometry. Enabling them to generalize to non-Euclidean 3D spaces without retraining therefore remains challenging. We propose SphMind, a training-free, plug-and-play framework that decouples semantic perception from geometric reasoning. Rather than requiring MLLMs to learn spherical geometry internally, SphMind preserves their semantic capabilities while handling geometry externally. We introduce a Spherical Harmonics-based Spatial Graph (SHSG) that models spatial relationships through equivariant transformations on the sphere, together with Inference-Time Geometric Grounding (IGG), a model-agnostic closed-loop optimization process that aligns MLLM representations with spherical geometric constraints during inference. Experiments on three benchmarks show that SphMind achieves over 21.4% average improvement in directional reasoning on MP3D and Stanford2D-3D, outperforms prompt-engineering baselines by 8.7% on the real-world ODI-Bench, and improves rotational invariance by 5.9% under panorama rotations, without additional training or dataset-specific tuning. In-the-wild evaluations further show that SphMind resolves directional reasoning queries that baseline vision-language models fail to answer correctly.

cs.CV↗

arXiv2026

Profit Reallocation Mechanisms in Tree-based Data Trading

Markets for data promise to unlock its economic value, yet in practice they remain far less active than expected---one reason is that those who supply data are not rewarded for the value it creates downstream. A defining feature of data is its \emph{replicability}: a buyer can refine purchased data into a new product and resell it to \emph{many} downstream buyers, so a single source seeds a branching cascade of resales that naturally forms a \emph{tree}. Because an upstream seller captures none of this downstream value, its incentive to trade is weakened. Existing works propose \emph{profit reallocation}---returning part of downstream revenue to upstream contributors---as a natural remedy. But whether profit reallocation works on the tree-structured markets that replicable data actually induces has remained open. To bridge this gap, we develop a principled framework for profit reallocation on tree-structured data markets. We introduce a sequential trading game on a tree and a general class of budget-feasible profit reallocation mechanisms (PRMs) over it. We derive efficient algorithms to compute the induced equilibria---a polynomial-time exact algorithm for discrete valuations and a fully polynomial-time approximation scheme (FPTAS) for continuous ones---via a subtree decomposition technique that tames the potential coupling across a seller's children. We then prove that, under mild assumptions, \emph{any} budget-feasible PRM weakly expands the trades that occur in equilibrium, and any budget-balanced PRM additionally weakly improves social welfare, relative to the baseline that reallocates nothing. Experiments on synthetic markets confirm that these benefits are substantial, persist even when the assumptions fail, and grow with the depth and branching of the tree.

cs.GT↗

arXiv2026

A Disk-Shaped Magnetoelastic Torque Sensor for Robotic Joints Using Permanent Magnetization

Direct torque sensing is a growing need in the robotics community to enable precise control and interactions where torque estimation from motor current is not sufficient. This paper presents a novel disk-shaped magnetoelastic torque sensor with a compact axial envelope of about 1 cm, suitable for integration in robotic joints. A four-magnetometer architecture is used to measure the field modulated by the stress affecting a narrow magnetized region while rejecting the effects of parasitic cross forces. A custom-designed magnetic shield enhances the torque sensitivity while reducing the external stray fields by a factor 7x. The device measures the torque with an accuracy of 1.34 %FS relative to the 50 Nm full scale (FS). The paper details the development of the sensor through the mechanical design, the magnetization procedure, and the experimental validation. The results demonstrate the potential of the proposed sensor for robotic applications.

cs.RO↗

arXiv2026

PGL-3D: Towards Progressive Geometric Learning for 3D Visual Query Localization

3D Visual Query Localization (3DVQL) retrieves the latest contiguous occurrence of a queried object in an RGB--point-cloud sequence and predicts a 9-DoF cuboid for every response frame. The query is captured independently of the search sequence, so its annotated pose may differ from how the object appears in the search frames. The benchmark baseline predicts cuboids after feature modeling, leaving their geometry unused for subsequent feature refinement. We investigate whether complete intermediate cuboids can improve query and proposal representations before final decoding. We introduce Progressive Geometric Learning for 3DVQL (PGL-3D), a predict--select--refine--re-predict framework that uses intermediate cuboids to guide the aggregation of search evidence and update query and proposal representations. A shared head first predicts a complete cuboid for every proposal. Query--Tube--Memory (QTM) then selects reference observations by combining proposal association, cuboid quality, frame response, and target absence, since association confidence alone establishes neither target presence nor geometric accuracy. The center, size, and orientation of each selected cuboid define soft pooling weights over query-conditioned proposal features. The pooled memory updates the query and proposal representations, and the head re-predicts from the updated features. A training-only objective, ST-D9O, supervises cuboid geometry at every stage by adding boundary, signed-distance, and soft-overlap terms to parameter regression. PGL-3D achieves a mean stAP of $0.270 \pm 0.004$ on 3DVQL, compared with $0.044$ reported for LaF. Ablations support the benefits of geometry-guided feature updates, while stage-wise analyses show improved cuboid accuracy. Replacing the geometry objective in our PROT3D reproduction with ST-D9O improves mAO on GSOT3D from $21.63\%$ to $25.78\%$. Our code and models will be released.

cs.CV↗

arXiv2026

Control Data Scheduling over Shared Communication Channels: A Sparse and Collision-Free Mechanism

In systems where controllers operate remotely and communicate with actuators over shared communication channels, it is crucial to efficiently schedule the control data transmission to reduce bandwidth usage and actuator effort. In this article, we investigate a novel scheduling mechanism that jointly coordinates control actions across different controllers and different time steps. We propose an algorithm based on the alternating direction method of multipliers (ADMM) to solve the resulting optimization problem. While ADMM is often treated as a black-box solver, the proposed algorithm offers a clear physical interpretation, ensures convergence to a stationary point, and is computationally efficient. Simulation results validate our theoretical results and demonstrate the effectiveness of our proposed algorithm.

eess.SY↗

arXiv2026

SymbolicLM: Training Language Models as Symbolic Regressors

Large Language Models (LLMs) have shown promising capabilities in scientific reasoning, yet scientific discovery ultimately requires deriving precise laws directly from observational data, known as Symbolic Regression (SR). This poses a challenge for LLMs due to the gap between probabilistic text generation and the exact structural requirements of SR. Existing approaches rely on complex external scaffolds, which are computationally expensive and separate symbolic reasoning from the model itself. To address this limitation, we propose to directly equip LLMs with symbolic regression capabilities through dedicated numerical-symbolic and physical supervision. We introduce PhysSymbArena, a large-scale benchmark containing over 160,000 equations and 1.8B tokens of numerical-symbolic data with physical descriptions, enabling systematic training and evaluation. Based on PhysSymbArena, we develop SymbolicLM, which enhances the symbolic regression ability of LLMs through mathematical and physical supervision. During inference, we further introduce SymbolicSGA, a refinement framework that leverages quantitative feedback to iteratively improve generated equations. Experiments on multiple symbolic regression benchmarks show that SymbolicLM substantially improves structural recovery while maintaining competitive numerical fitting performance. These results demonstrate that symbolic regression can be explicitly learned as an intrinsic capability of LLMs.

cs.CE↗

arXiv2026

Boolean Cumulants and Exact Reduced Descriptions of Renewal-Driven Systems

Reduced descriptions of unresolved fluctuations are commonly based on Gaussian processes, although many realistic forcings have finite correlation times and a renewal structure. For memoryless step (Kubo--Anderson) noise, we show that the reduced dynamics admit two exact and complementary descriptions: a kernel representation governed by the Boolean cumulants of the jump distribution, and a frozen-noise representation adapted to stationary probability densities. For exponentially distributed waiting times, the totally time-ordered $G$-cumulants coincide with the Boolean cumulants of the jump law, and the memory kernel is resummed exactly as the Boolean generator $η$ evaluated on a resolvent operator. Second-order closure is exact if and only if the jump law is symmetric Bernoulli; otherwise, the leading closure error is controlled by $(b_4/b_2)λ^2$. The Boolean hierarchy, however, acts on the kernel, not on the stationary measure. Stationary densities are approximated by replacing the jump law with its $N$-point Gauss quadrature: each surrogate preserves all multi-time correlations up to order $2N-1$ for any waiting-time law, its kernel is a Padé resummation of the Boolean one, and it is itself an exactly solvable renewal problem. For the linear system with linear multiplicative interaction (LIMI/CAM), the frozen-noise representation reduces the dynamics to a random affine recursion and yields exact support boundaries, singularity exponents and Kesten tail indices, confirmed numerically. Rates, moments and closure errors are governed by the Boolean hierarchy, whereas stationary densities are determined by the geometry of the jump distribution. For memoryless renewal noise, the combinatorial structure controlling finite-correlation reductions is Boolean.

cond-mat.stat-mech↗

arXiv2026

Climbing the Hill: Prompt Injection Red-Teaming Against Frontier Models with Curriculum Reinforcement Learning

Prompt injection is a leading security risk for LLMs and LLM-based applications such as agents. State-of-the-art red-teaming methods for prompt injection leverage reinforcement learning (RL) to train an attacker LLM to generate effective injected prompts. However, when targeting frontier LLMs such as GPT-6-Luna, a major challenge is the cold-start problem: every attack attempt by the attacker LLM fails and thus receives zero reward, providing no signal for learning. In this work, we propose a curriculum learning-based method to address the cold-start problem. In particular, we propose to train the attacker LLM against a sequence of increasingly robust target LLMs, with each stage warm-starting from the attacker LLM obtained in the previous one. However, simply training against a weak target (e.g., GPT-4o-mini) may not sufficiently prepare the attacker LLM to obtain useful learning signals against a frontier LLM (e.g., GPT-5.6-Terra). Instead, we find that the design of the curriculum is critical: after each stage, the attacker LLM needs to partially succeed against the next target LLM such that it can learn from successful attempts to attack the new target. Our extensive evaluation shows that our method can effectively red-team frontier LLMs, achieving an attack success rate (ASR@10) of 93.8\% and 45.0\% against GPT-5.6-Luna and GPT-5.6-Terra on AgentDyn, whereas state-of-the-art RL methods such as RL-Hammer and PISmith achieve 0\% ASR under the same setting. Moreover, we find that the attacker LLM transfers across targets, e.g., an attacker LLM trained to defeat one strong LLM (GPT-5.6-Terra) also succeeds against six other frontier LLMs (e.g., GPT-6-Luna) it was never trained on. Our code is available at https://github.com/albert-y1n/PIForge.

cs.LG↗

arXiv2026

Quantifying Behavioral Tails in Black-Box Language Models

We introduce RareTrap, a framework for estimating the probability of severe behaviors in black box large language models (LLMs). A key challenge for probability estimation is defining a tractable distribution over the input space. To accomplish that, RareTrap uses a surrogate LLM and constructs a geometry-aware mapping from a lower-dimensional latent reference space into its token-embedding space to induce an explicit and reproducible distribution over input prompts. A response-level performance function is utilized on the response to quantify behavior severity. This enables sequential rare event simulation that concentrates evaluations on progressively more severe behaviors while preserving probability under the induced prompt distribution, which would otherwise be prohibitive to measure. Across 10 open-weight and two frontier models (GPT-5.4 and Claude Sonnet 4.6), we find that RareTrap successfully induces severe resource consumption behaviors and computes their probability with as few as 200 evaluations. RareTrap provides model developers a principled approach for evaluating language models under a common distribution, and prioritizing alignment effort to improve safety and mitigate risks.

cs.LG↗

arXiv2026

Pruned CTC for Memory-Efficient Large-Vocabulary ASR Training

Connectionist temporal classification (CTC) naturally supports offline and streaming speech recognition with utterance-level supervision, but conventional implementations materialize frame-by-vocabulary activations in memory, making CTC training with native LLM vocabularies prohibitively memory-intensive. A key observation is that every valid CTC alignment uses only target tokens and blank, and their union across a batch typically forms a small subset of the full vocabulary. We introduce Pruned CTC, which restricts alignment computation to this subset while retaining full-vocabulary normalization. We prove that this vocabulary reduction is exactly equivalent to full-vocabulary CTC in loss and gradients. Head-and-loss activation memory no longer scales linearly with vocabulary size. We further apply finite-beam alignment pruning. Building on Pruned CTC, we develop LLM-CTC, which adapts pretrained LLMs for non-autoregressive ASR while retaining causal attention and native vocabularies, and extend it to bounded-history streaming, avoiding chunk-level speech--text alignments. Experiments show that, with Zipformer-M encoder and 180K vocabulary, Pruned CTC reduces full-step memory by 5.1$\times$ with only 17% step-time overhead. Across three corpora, it matches standard CTC accuracy. On GigaSpeech, across six Qwen3 model sizes from 0.6B to 32B, LLM-CTC remains within 7% relative WER of LLM-CE with 7 to 10$\times$ faster recognition; when fine-tuning Qwen3-ASR for bounded-history streaming, LLM-CTC remains within 3% relative WER of matched offline models on the test set. Together, these results establish Pruned CTC as a scalable sequence objective for native-vocabulary LLM ASR across offline and streaming settings.

eess.AS↗

arXiv2026

Who Blocks Whom? Probabilistic Pass-Blocking Assignments for Evaluating Blockers and Pass Rushers in American Football

Historically, statistical analysis of offensive lineman has been hindered by the lack of easily measurable quantities. More recently, with the introduction of player tracking data new methodological advances are now possible. Using high-dimensional spatio-temporal data, we adapt the defensive-matchup hidden Markov model of \cite{franks2015characterizing} from basketball to football pass protection, producing frame-by-frame probabilistic assignments of each pass blocker to the rushers. We show how this probabilistic assignment is a usable modeling artifact that augments existing player-evaluation frameworks. We directly quantify the attention a rusher commands, upgrade adjusted plus-minus \citep{Macdonald+2012} from all-or-nothing stints to partial, continuous blocking credit in continuous time, yield block-shedding survival metrics, and measure the space a rusher generates for his teammates. Fit to the first eight weeks of the 2021 NFL season, the resulting metrics recover widely-recognized elite rushers and pass protectors and align with independent charting.

stat.AP↗

arXiv2026

Implicit-Explicit time integration scheme with Physics-based preconditioning for two-fluid tokamak boundary simulations

In this work, a globally stiffly accurate Implicit-Explicit (IMEX) Runge-Kutta scheme is developed and implemented in the GBS code [Ricci et al., Plasma Phys. Control. Fusion, 2012], for two-fluid plasma turbulence simulations. The stiffest phenomena, governed by shear Alfvén waves and parallel diffusion, are treated implicitly, while the remaining non-stiff terms are advanced explicitly. This splitting enables time steps well beyond the Courant-Friedrichs-Lewy limit, without incurring the full computational cost of a globally implicit formulation. To efficiently solve the implicit subsystem at each time step, a three-dimensional physics-based preconditioner, inspired by techniques developed in the magnetohydrodynamic (MHD) context, is used. The resulting framework is verified through the method of manufactured solutions and exhibits both algorithmic and parallel scalability. Significant advantages in numerical stability and computational efficiency are demonstrated with respect to an adaptive explicit Runge-Kutta scheme.

physics.plasm-ph↗