arXiv subjects

Jie Zhang

Publications and source records attributed to Jie Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

OwlSight: A Panoramic Monitor for Chain-of-Thought Reasoning

Chain-of-Thought (CoT) monitoring offers actionable evidence for oversight AI systems, with the potential to enable early detection and intervention. However, existing approaches are focused on specific tasks, whereas the regulation of AI, particularly reasoning models, requires monitoring a broader range of tasks. We introduce Factor for CoT monitoring, a strategy that supports customizing monitoring requirements in the prompt, which enables a single monitor to cover different tasks by relying on different factors. Furthermore, we introduce two types of factors, fine-grained and coarse-grained (e.g., monitoring whether a specific email address has been leaked versus monitoring privacy leakage), to accommodate diverse user monitoring needs. Based on this, we develop a CoT monitor named OwlSight that relies solely on factor to monitor behaviors related to multiple dimensions, including capability, safety, and trustworthiness. Experiments across 15,971 reasoning trajectories show that OwlSight surpasses general-purpose LLMs by 1.32-30.57 and 11.71-27.81 points at fine and coarse granularity, respectively, and achieves state-of-the-art results on OpenAI's CoT monitorability benchmark. It also generalizes to unseen models' CoTs and remains robust to Factor rephrasings, CoT compression, and obfuscation, offering a promising paradigm for CoT monitoring that can contribute to the oversight of frontier AI.

cs.AI↗

arXiv2026

VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse

Flow-matching vision-language-action (VLA) models generate an action chunk by iteratively denoising Gaussian noise, but typically execute only a short prefix before replanning with updated observations. Under this receding-horizon paradigm, the unexecuted remainder---the action tail---is discarded, and the next chunk is regenerated from fresh noise. We show that this discarded tail retains transferable denoising progress: action-tail initialization can match or outperform a native 10-step Gaussian baseline using fewer denoising steps. However, the optimal denoising budget varies substantially across samples, indicating that tail reuse should be adapted to the updated environment. Based on this observation, we introduce VLA-Rolling, a lightweight inference framework that reuses action tails through three stages: action-tail inheritance, per-action confidence estimation, and confidence-guided refinement through renoising and denoising budget allocation, while the underlying VLA remains frozen. Across $π_{0.5}$, SmolVLA, X-VLA, and MolmoAct2 on LIBERO, MetaWorld, LIBERO-Plus, and RoboTwin 2.0, VLA-Rolling reduces action-chunk inference cost in all 16 model--benchmark pairs, achieving up to a $1.48\times$ speedup, while improving success rate in 14 pairs by up to $15.08$ percentage points. These results show that action tails are not merely discarded predictions, but reusable intermediate states that enable more efficient and accurate VLA inference. These results demonstrate that the action tail can support the generation of better actions with fewer denoising steps. Our project is available at https://chenbao123ww.github.io/VLA-Rolling/.

cs.AI↗

arXiv2026

Differentially Private Sparse Reward Estimation with Preference Feedback

Reinforcement Learning with Human Feedback (RLHF) has become a central paradigm for aligning Large Language Models with human values. However, the reliance on sensitive preference data necessitates rigorous differential privacy (DP) guarantees to prevent user information leakage. Existing private alignment methods typically assume dense reward parameterizations, resulting in estimation error bounds that scale polynomially with the ambient {model size $d$}. Such dependence is prohibitive in modern {overparameterized models} where $d$ is vast. In this work, we study \emph{Private Sparse RLHF} problem to address this limitation, assuming that human preferences (reward model) are governed by a subset of $s^* \ll d$ relevant features. We provide the first comprehensive theoretical framework for differentially private sparse reward estimation from pairwise preference feedback under the Bradley-Terry-Luce model, and introduce efficient algorithms for both Sample-DP and Label-DP settings. Theoretically, under the squared $\ell_2$ parameter estimation error, we establish upper bounds of $\widetilde{O}(s^*/n + {s^*}^2/n^2\varepsilon^2)$ for $(\varepsilon,δ)$-Sample-DP and $\widetilde{O}(s^*/n + s^*/n\varepsilon^2)$ for $\varepsilon$-Label-DP based on randomized response, where $n$ is the training data size. For the lower bounds, we show that the Sample-DP rate is nearly optimal, and that the guarantee for our Label-DP method cannot be further improved within the randomized-response framework. We also provide a general lower bound for the problem with Label-DP. Empirically, our framework demonstrates superior efficacy over dense baselines across sentiment generation and safety alignment benchmarks, offering a significantly more favorable privacy-utility trade-off.

cs.LG↗

arXiv2026

The Show-Up Attack: When Subagents Win Over Their Supervisor

Multi-agent systems are increasingly deployed to coordinate multiple large language model (LLM) agents. However, this also creates new attack surfaces: malicious agents may have chances to exploit the coordination. In this paper, we propose and study the \textit{show-up attack}, in which a malicious subagent manipulates the supervisor into involving it in tasks beyond its assigned scope. To evaluate this risk, we propose SUA-Arena, which implements 6 attack strategies and contains 188 test cases. Then, we evaluate 6 frontier LLMs and find that all of them are vulnerable to show-up attacks. For example, GPT-5.6-Sol as a supervisor suffers an ASR of up to 0.93. Mitigation strategies such as prompting and restricted communication fail to reduce the risk consistently. These results show that multi-agent systems need explicit mechanisms for enforcing authority boundaries.

cs.AI↗

arXiv2026

PI-MLLM: Psychophysics-Inspired Multimodal Large Language Model for Oddly Satisfying Video Emotion Analysis

Oddly Satisfying Videos (OSVs) can evoke strong viewer responses through repetitive motion, visual tactility, and ASMR-like sounds despite containing few explicit semantic emotion cues. This makes OSVs a challenging setting for Video Emotion Analysis (VEA), since most existing methods focus on semantic video content and under-model the physical sensory dynamics that shape viewer responses. To support Oddly Satisfying Video Emotion Analysis (OSVEA), we construct the Oddly Satisfying Video Dataset (OSVD), comprising 12,000 annotated 5-second clips. Each clip provides viewer-emotion labels under video-only, audio-only, and audio-visual conditions, together with explanations grounded in visual and acoustic sensory evidence. Building on OSVD, we propose PI-MLLM, a psychophysics-inspired multimodal large language model that integrates Modality-Specific Dynamics Alignment (MSDA) and Coalition-Based Audio-Visual Attribution (CAVA). MSDA uses auxiliary prediction objectives to align modality representations with visual motion and acoustic energy-onset dynamics. CAVA evaluates emotion scores across modality coalitions and applies Shapley attribution to identify the dominant modality and determine whether visual and auditory evidence is synergistic or conflicting. Experiments show that PI-MLLM improves both viewer-side emotion prediction and sensory-grounded explanation quality, suggesting the value of physical sensory cues to video emotion analysis.

cs.CV↗

arXiv2026

LLM-Driven Autonomous Vehicles Can Inherit Human Driver Biases in Pedestrian Yielding: Results and Implications From a New Benchmark

Public trust in Autonomous Vehicles (AVs) may depend not only on technical success but also on the fairness of their decision making. While a recent trend in AV research involves using general purpose "common sense" models to guide AV decision making, the degree to which these inherit human biases in driving is still understudied. Given that psychology studies have shown human driver biases exist, such as lower pedestrian-yielding rates to Black pedestrians in the US, we argue that analyses of model bias should also be part of AV evaluation. Concretely, in this paper we propose two new bias testing methodologies for Large Language Models (LLMs) and Visual-Language Models (VLMs), "All Else Being Equal" tests and "Self-Consistency" tests, and a new benchmark (FairYield) to assess bias in pedestrian-yielding decisions. Our findings show that the yielding decisions of both LLMs and VLMs can be influenced by models' predictions of pedestrian gender, ethnicity, religion, disability, age, skin tone, and socio-economic status. While the type and degree of bias is different from model to model, we highlight common patterns, and raise questions about the "common sense" model paradigm, particularly the need to either revise the paradigm or address issues of downstream bias.

cs.AI↗

arXiv2026

Hardness Amplification for Approximate Nash Equilibrium with Constantly Many Players

For every fixed $\varepsilon\in(0,1)$ and $η\in[0,1)$, we prove that computing an $(\varepsilon,η)$-weak approximate Nash equilibrium requires quasipolynomial time assuming deterministic PPAD-ETH, even in symmetric binary-payoff games with a constant number of players. The games are given by complete payoff tables, and the player count depends only on the tolerances. The weak approximate Nash equilibrium allows at most an $η$ fraction of players to gain more than $\varepsilon$ by deviating unilaterally. The main technical result is an unconditional error-amplification reduction from bimatrix games. For every fixed $δ\in(0,1)$, it transforms a rational bimatrix game with payoffs in $[0,1]$ into a symmetric binary-payoff game with a polynomial-size complete table and a player count depending only on $δ,\varepsilon,η$. Every $(\varepsilon,η)$-weak approximate equilibrium of the constructed game yields a $δ$-approximate Nash equilibrium of the bimatrix game. Construction and recovery take polynomial time in their explicit inputs. Combining this reduction with the bimatrix hardness result of Rubinstein [FOCS 16] gives a deterministic worst-case running-time lower bound of $N^{(\log N)^{1-o(1)}}$, where $N$ is the constructed table's binary encoding length.

cs.GT↗

arXiv2026

From Retrieval to Recognition:Knowledge-Enhanced Post-training of Time Series Foundation Models for Classification

Time series foundation models (TSFMs) have achieved notable progress in classification tasks through large-scale pretraining. However, their post-training practice mainly focuses on implicit parameter fine-tuning, where task-relevant information is entangled with abundant irrelevant knowledge in vast parameter spaces. This may hinder TSFMs from precisely activating useful knowledge for downstream classification. To this end, we propose Retrieval-to-Recognition (R2R), a plug-and-play post-training paradigm that adapts pretrained TSFMs to time series classification. Rather than pretraining a new foundation model, R2R improves how existing TSFMs are post-trained: it introduces a decoupled query encoder to extract discriminative patterns and retrieve instance-level numerical knowledge from a constructed knowledge base. The retrieved explicit knowledge is then fused with the TSFM's implicit parametric embeddings, enabling joint knowledge transfer at both the parameter and feature levels. In this way, R2R allows TSFMs to recall task-relevant patterns learned during pretraining, improving the efficiency of knowledge utilization in downstream classification transfer. Experiments on 158 time series datasets show that R2R consistently improves the classification performance of state-of-the-art TSFMs. Ablation and knowledge-enhanced studies further validate the effectiveness of the proposed framework.

cs.LG↗

arXiv2026

Voronoi-guided Bilateral 2D Gaussian Splatting for Arbitrary-Scale Hyperspectral Image Super-Resolution

Most existing hyperspectral image super-resolution methods require modifications for different scales, limiting their flexibility in arbitrary-scale reconstruction. 2D Gaussian splatting provides a continuous representation that is compatible with arbitrary-scale super-resolution. Existing methods often rely on rasterization strategies, which may limit flexible spatial modeling. Extending them to hyperspectral image super-resolution remains challenging, as the task requires adaptive spatial reconstruction while preserving spectral fidelity. This paper proposes GaussianHSI, a Gaussian-Splatting-based framework for arbitrary-scale hyperspectral image super-resolution. We develop a Voronoi-Guided Bilateral 2D Gaussian Splatting for spatial reconstruction. After predicting a set of Gaussian functions to represent the input, it associates each target pixel with relevant Gaussian functions through Voronoi-guided selection. The target pixel is then reconstructed by aggregating the selected Gaussian functions with reference-aware bilateral weighting, which considers both geometric relevance and consistency with low-resolution features. We further introduce a Spectral Detail Enhancement module to improve spectral reconstruction. Extensive experiments on benchmark datasets demonstrate the effectiveness of GaussianHSI over state-of-the-art methods for arbitrary-scale hyperspectral image super-resolution.

cs.CV↗

arXiv2026

Structure-Aligned History Learning with Subspace-Structured Semantic IDs for Generative Recommendation

Generative recommendation constructs semantic IDs for catalog items and predicts the next ID from user interaction histories. However, existing methods face limitations in both stages. First, conventional quantizers may produce imbalanced code assignments and lack coherent intermediate semantic units between individual tokens and complete items, limiting history reconstruction. Second, recommendation models remain dominated by next-item prediction, treating historical interactions mainly as conditioning context and providing limited supervision for recovering persistent preferences across the historical path, particularly when relevant preference signals are distributed over distant interactions. To address these limitations, Structure-Aligned History Learning (SAHL) reconnects the two stages by using the structure created during quantization directly for history reconstruction. Its Semantic Residual Balanced Quantization (SRBQ) forms a balanced token-subspace-item hierarchy, and SAHL reconstructs history at these same granularities. Predictive entropy prioritizes uncertain transitions, while curriculum optimization progressively shifts training to inference-aligned next-item prediction. On four Amazon Review categories, SAHL improves NDCG@10 by 18.6%-30.0% over RPG and 2.7%-6.0% over strong method MHL. Controlled analyses verify balanced code use, the benefit of following quantizer-defined groups during reconstruction, and dependence on user history. The relevant code is available at https://github.com/CQU-MM-Intelligent-Lab/SAHL.

cs.IR↗

arXiv2026

Measuring the Dependency Gap: Diagnosing Inter-Column Fidelity in Tabular Generative Models

Synthetic tabular data are valued for preserving inter-column dependency, yet a routine fidelity score says neither where it is lost nor why. Equipping a classifier two-sample test (C2ST) with a gradient-boosted discriminator, we decompose it by controlled permutation into marginal, dependency and numerical--categorical cross components, read against a fully-factorized reference that destroys all dependency while keeping every marginal, and a real-data oracle. The linear detection score in common use rates that reference as nearly real, a known weakness we replicate on four benchmarks. On a flow-matching (TabbyFlow) and a diffusion (TabDiff) generator it exposes a deficit of the same order in both, whose source we narrow by elimination: not a structural limit of the mean-field objective, not mainly sampling discretization, and not closed by a $16\times$ capacity increase where that test has power, while the same measurement responds sharply when capacity is cut eightfold, so the plateau is measured rather than a blind spot. Destroying inter-column dependence while keeping every marginal and every feature--label relation costs between $0$ and $0.22$ minority-class $F_1$ by dataset, and the generators' own shortfalls are not ordered by their deficits. An explicit cross-coupling module and a post-hoc copula leave the deficit in place. Neither generator's objective places a term on the joint at all; that this absence is what sustains the deficit is an explanation we reach by elimination rather than test. A controlled validation calibrates the diagnostic and identifies when it reports a false positive, which none of these generators triggers.

cs.LG↗

arXiv2026

Not All Actions Contribute Equally: Learning Precise Progress Estimation from Imprecise Demonstrations

Progress estimators play an essential role in providing dense reward signals for reinforcement learning in robotic manipulation, but accurately assessing task progress can be much challenging. Existing methods heavily rely on expert data and naively assume that all actions within a demonstration contribute to task success. This assumption often breaks down in real-world scenarios, especially in high-precision manipulation, where subtle geometric errors can lead to task failure. Therefore, these methods can erroneously interpret human mistakes as meaningful progress, further corrupting progress learning. We argue that a key limitation is the lack of a global prior regarding task evaluation criteria, which is crucial for distinguishing meaningful progress from human mistakes. To this end, we propose PRIME, a novel progress estimator capable of learning precise progress estimation from imprecise demonstrations by aggregating experience across trajectories. PRIME constructs a weighted graph over observed states, connecting states across trajectories based on spatial proximity and visual consistency. Edge weights encode spatial distances as transition costs, and shortest-path search approximates the geodesic distance to success. Changes in this distance naturally distinguish advancement, stagnation, and setbacks without assuming monotonic progress over time. Extensive experiments in both simulation and real world on precise manipulation tasks show that PRIME is consistently effective across diverse tasks, and robust to data with varying degrees of suboptimality. Notably, the advantage of PRIME gets more pronounced in higher-precision scenarios, yielding up to a $5\times$ improvement in policy success rate over the SFT baselines on charger insertion.

cs.RO↗

arXiv2026

Quantitative validation of SMBI deposition profiles on EAST using experimentally constrained simulations

Quantitative comparison between SMBI fueling simulations and experiments has long been hampered by the poor constraint on the effective source. Here, the particle increment per pulse is extracted experimentally and used to calibrate the simulation source. For EAST shot 71438, the density evolution from microwave reflectometry is analyzed for nine SMBI pulse groups. The SMBI-induced density increase is isolated from the background by comparing the rising and falling phases around each pulse group. Its radial profile peaks in the mid-pedestal region for every pulse group. Volume integration of this increment provides the experimental reference. The simulations use a multi-fluid model in the BOUT++ framework in which two transport operators are recast into conservative flux form, with the particle balance residual reduced to about 2% of the injected amount, and the perpendicular transport coefficients are constructed from the discrete radial flux balance, with the unphysical changes of the initial density and temperature profiles in source-free evolution reduced by an order of magnitude. For three cases sharing the same nominal molecular flux, the simulated deposition peak agrees with the experimental one in the relative pedestal coordinate. The simulated conversion of the injected particles at the end of the injection is slightly lower than the value inferred from the experiment, while the fraction retained at the end of the pulse is higher. The perturbation thus decays more slowly in the simulation, which we attribute to fast loss channels not represented in the model, such as parallel losses to the scrape-off layer. The edge electron temperature stays on the high-temperature plateau of the dissociation and ionization rate coefficients throughout the pulse, and the inward shift of the deposition with edge cooling reported earlier does not occur under the present conditions.

physics.plasm-ph↗

arXiv2026

3DCodeVerse: Exploring 3D Worlds as Code

We introduce 3DCodeVerse, a research ecosystem that enables coding agents to create editable and verifiable 3D content at scale. 3DCodeVerse comprises large-scale, high-quality datasets of executable 3D code, a coding harness for spatial reasoning and automated verification, and practical guidance for 3D coding. First, we construct 3DCodeVerse-2M, a large-scale curated dataset of standalone 3D executable code. We build this corpus by collecting open-source data, converting specialized representations, and generating new programs with coding agents. Each program is packaged with the source files and associated assets required for execution in its declared environment, along with available descriptions and verification records. Second, we develop the 3DCodeVerse Harness, a multi-agent directed acyclic graph framework for generating and refining 3D content. It uses execution checks, spatial measurements, and visual feedback to automatically evaluate and revise generated programs without human feedback during generation. Third, we conduct systematic empirical studies of 3D coding, establishing baselines with fine-tuned open models and deriving practical guidance through component-level analyses of our harness. Extensive experiments demonstrate that fine-tuning on our dataset significantly improves the 3D coding capabilities of open-source models. Notably, our 3DCodeVerse harness achieves a 90% win rate against Claude Design (3D Object) in pairwise human evaluations, when both are utilized by Claude Opus 5.5.

cs.CV↗

arXiv2026

Integrating 3D Posture Neutralization with Statistical Shape Modeling for Head-Neck-Shoulder Ergonomic Design

The design of ergonomic products and workspaces requires a deep understanding of human anatomy and posture. In particular, the head-neck-shoulder region is critical for many applications such as cervical orthoses, helmets, and other head-worn or neck-worn devices. This paper presents a framework that integrates posture neutralization with statistical shape modeling (SSM) for the head-neck-shoulder (HNS) region. We acquire a single three-dimensional (3D) scan of the head-neck-shoulder region from each of 200 Chinese adults in a natural posture for each subject. Every scan is then posture-neutralized before SSM. We fit a parametric head-neck model to each scan to separate cervical pose from anatomy, and reset the cervical pose to a common neutral configuration, so that the resulting model captures anatomical shape variation rather than posture-induced deformation. The resulting shape space yields a standardized template and population-wide modes of variation, providing baselines for parametric ergonomic design. We further discuss how the model supports population coverage analysis and the design of products that accommodate anatomical diversity while maintaining neutral cervical posture.

cs.GR↗

arXiv2026

TRAP: Tool-result Replay Attack for Probing Misbinding in LLM Agents

As AI agents increasingly act through external tools, tool results are no longer simple outputs but execution artifacts that must remain correctly associated with the context that produced them. Yet as results persist across caches, recovery mechanisms, and shared runtime state, this association can break, causing a real and unmodified result to be consumed in an incompatible execution context and lead the agent to an unsafe action. We characterize this failure as tool-result misbinding. To systematically study this failure, we introduce ReplayBench, a benchmark that uses controlled tool-result replay to evaluate misbinding across 19 representative agent scenarios, 4 failure properties, and 3 replay mechanisms. Across eight LLMs, three agent frameworks, and diverse stateful workflows, we find widespread replay-induced failures, with a mean Final-State Error Rate of 0.649 under cross-task replay. Stage-wise analysis localizes these failures to model-side action generation. Further analyses show that replay susceptibility varies with task similarity, shows little dependence on object similarity, and remains high under result staleness and implicit environment changes. These findings motivate runtime validity mechanisms that eliminate final-state errors in our evaluated settings while preserving legitimate recovery. The results call for explicit contextual binding in tool-using agent runtimes. Our work is public at https://github.com/Phitooo/Replaybench.

cs.AI↗

arXiv2026

StageBreaker: Shifting Video RL Post-Training Scheduling from Stages down to Data Dependencies

Reinforcement learning (RL) post-training has emerged as the key paradigm for improving autoregressive video models. Emerging vision-language reward models further strengthen post-training with accurate rewards, but their long chain-of-thought inference substantially raises the associated costs, while the pursuit of long videos prolongs policy training. Despite these rising costs, existing video RL systems still adopt coarse-grained stage-centric execution, which stalls policy training until all reward evaluation finishes, replays every trajectory twice due to a further barrier within policy training, and induces load imbalance across GPUs. To address the challenges, we propose StageBreaker, a fine-grained data-dependency-driven scheduling framework, which schedules the true dataflow of an RL step rather than its stages. Specifically, StageBreaker overlaps policy training with reward evaluation by exploiting reward-separable policy training, and merges the two trajectory replays into one by leveraging loss-independent back-propagation. It further balances GPU load by scheduling computation at the finer granularity. Our evaluation results show that StageBreaker achieves a speedup of up to 1.41$\times$ over stage-centric execution.

cs.DC↗

arXiv2026

EasyFashion: A Human-AI Co-Creation System for Personalized Fashion Design and Sewing Pattern Generation

People often want garments that reflect their aesthetic preferences, fit their bodies, and meet their sizing needs, yet turning these requirements into physical garments remains difficult. Ready-to-wear options provide limited personalization, while custom tailoring is costly and time-consuming. Recent generative artificial intelligence (AI) systems can visualize garment ideas but often stop short of supporting downstream production. To address this gap, we present EasyFashion, a human-AI co-creation system that enables users to iteratively refine design intent for personalized garment style and size, evaluate designs through virtual try-on on reconstructed personal avatars, and generate sewing patterns for garment production. Using reference images, text descriptions, and body photos as input, EasyFashion translates user intent into structured garment specifications and try-on results. Technical experiments, user studies, and a real-world production case demonstrate the value of EasyFashion for multimodal design expression, body-specific evaluation, and production-oriented outputs in personalized garment design. Our project page is available at https://zoequ.github.io/easyfashion.github.io/.

cs.HC↗