arXiv subjects

Hao Zhou

Publications and source records attributed to Hao Zhou.

At least 37 records · Page 2Linked to original sources

arXiv2026

Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. However, RL algorithms with PPO-Clip are inherently limited by exploration collapse. Subsequent works remain primarily heuristic and fail to identify the essential cause of PPO-Clip's failure. This work reveals the fundamental flaw of PPO-Clip: it implicitly measures policy discrepancy using Euclidean metric, which is theoretically inconsistent with the intrinsic geometry on the policy Riemannian manifold. This geometric mismatch results in overly conservative updates in low-probability regions while aggressive in high-probability regions, ultimately collapsing exploration. To correct this geometric flaw, we propose Riemannian Isometric Policy Optimization (RIPO), which guarantees isometric policy updates on the Riemannian manifold, effectively balancing exploration and exploitation. We further show that RIPO achieves a favorable bias-variance trade-off, which stabilizes optimization. Extensive experiments demonstrate that RIPO significantly surpasses existing LLM RL algorithms across seven competition-level benchmarks (up to 60% improvement over GRPO on AIME24).

cs.LG↗

arXiv2026

Multi-wavelength study of EP250416a / GRB 250416C: An Optically Dark Long GRB with a Late Jet Break

We present multi-wavelength study of the $γ$/X-ray transient EP250416a (also designated GRB 250416C), triggered by the Einstein Probe (EP) Wide-field X-ray Telescope and also by SVOM and Konus-Wind (KW). Observations spanning the $γ$-ray, X-ray, and optical bands facilitated detailed analysis of the burst's prompt emission, afterglow evolution, and physical origin. GRB 250416C exhibits a burst duration of 30 s in X-ray and 17.7 s in $γ$-rays, with joint spectral fitting of 0.5-5000 keV data gives $E\rm_{peak}=342_{-232}^{+90}$ keV. Optical spectroscopy of the afterglow, acquired with the Gemini Multi-Object Spectrograph (GMOS) on Gemini South, yielded a redshift of $z=0.963$. Accounting for the measured redshift, the isotropic energies are $E\rm_{X,iso}=2.7_{-0.5}^{+0.9}\times10^{50}$ erg and $E\rm_{γ,iso}=7.34_{-2.1}^{+5.1}\times10^{51}$ erg, aligning with the Amati relation for long GRBs. The fluence ratio $\rm S(25-50~keV)/S(50-100~keV)=0.78_{-0.12}^{+0.10}$ classifies GRB 250416C as an X-ray rich (XRR) GRB. The X-ray afterglow shows an initial shallow decay ($α\approx -0.5$) transitioning to a canonical decay phase ($α\approx -1$), with a very late jet break at $t\sim 1.5\times 10^6$ s, corresponding to a jet half-opening angle of $θ_j=10.6_{-1.8}^{+1.9}$ degrees. GRB 250416C is optically dark, as it shows only a faint $r$-band detection ($r=24.16\pm 0.13$ mag) from Gemini South-GMOS and a low optical-to-X-ray spectral index $β_{\rm OX} = 0.3$. This may be attributed to significant host-galaxy extinction, with a required $A_V^{\text{host}}=2.7\pm 0.3\ \text{mag}$ derived from the extinction curve model.

astro-ph.HE↗

arXiv2026

Adam under Generalized Smoothness with Second-Moment-Type Stochastic Gradients

Adam is widely observed to remain stable even when the objective deviates significantly from global smoothness. Under the generalized smoothness framework, however, existing analyses rely on strong tail assumptions on the stochastic gradients, such as almost-sure boundedness or sub-Gaussianity. Whether Adam converges on generalized smooth objectives under only second moment information on the stochastic gradients, without such concentration assumptions, was identified as an important open direction by Li et al. (2023). This paper gives an affirmative answer under fairly general conditions: such tail assumptions are not necessary. Building on the Adam self-normalization framework of Jin et al. (2026), developed for classical smoothness and bounded variance, we extend the stopping-time and de-preconditioning strategy to the $L_0$-$L_p$ generalized smoothness condition and a generalized second moment ABC condition. Even when the stochastic-gradient condition provides only second moment information that may grow along the trajectory, the stochastic trajectory of Adam remains in a locally well-behaved smoothness region, with stretched-exponential tail decay under bounded variance and global smoothness. Consequently, we establish high-probability convergence rate guarantees over the full range $p<2$, with confidence dependence of order $δ^{-1/2}$, while the stepsize prefactor depends on $δ$ only through a single logarithmic factor. We further construct a hard instance showing that, under only second-moment information, this $δ^{-1/2}$-type confidence dependence is sharp. Finally, in the regime $p<1$, we combine the trajectory control with polynomial-growth estimates on rare events to obtain convergence rate guarantees in expectation.

cs.AI↗

arXiv2026

Defense-in-Depth at the Perception-Reasoning Interface of LLM-Centric Agentic UAV Swarms

Large Language Models (LLMs) increasingly support Uncrewed Aerial Vehicle (UAV) swarm operations such as data collection scheduling, where the model reads structured sensor reports and decides which sensors to visit. An adversary who quietly manipulates those reports can redirect the swarm without modifying the model weights or the UAV. Defenses for this interface have been proposed architecturally but rarely implemented or evaluated. We implement and evaluate defense-in-depth at the perception-reasoning interface of LLM-Centric Agentic UAV Swarms. Five layers check the provenance of a report, whether its values are physically admissible, whether they agree with what swarm geometry and service history predict, whether the resulting schedule starves any sensor, and, when these fail, hand control to a deterministic scheduler that ignores the suspect input. We test each layer against an adversary strong enough to defeat the layer before it. For each of the three input-side layers, we derive in closed form how far a report can be distorted before that layer reacts, fixing each boundary from deployment parameters before any attack data is collected; across thirty matched simulation runs, predicted and measured boundaries agree. Separating attack detection from response is a well-established principle, and we quantify the cost of neglecting this distinction at the perception-reasoning interface. When the system rejects a report, it replaces it with the most recent accepted report. This prevents the adversary from controlling the UAV schedule, but it also increases cumulative cost by 79% and 74% for the two detectors, respectively, compared with the undefended system. The safety check does not detect any attacks, but it nevertheless reduces the attack-induced cost by 37.5%.

cs.CR↗

arXiv2026

Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models

Multimodal reward models have advanced substantially in text and image domains, yet progress in video understanding reward modeling remains severely limited by the lack of robust evaluation benchmarks and high-quality preference data. To address this, we propose a unified framework spanning benchmark design, data construction, and reward model training. We introduce Video Understanding Reward Bench (VURB), a benchmark featuring 2,100 preference pairs with long chain-of-thought reasoning traces (averaging 1,143 tokens) and majority voting evaluation across general, long, and reasoning-oriented video tasks. We further construct Video Understanding Preference Dataset (VUP-35K) via a fully automated pipeline, providing large-scale high-quality supervision for video reward training. Building on the data, we train VideoDRM and VideoGRM, a discriminative and a generative reward model, both achieving state-of-the-art performance on VURB and VideoRewardBench. Further analysis confirms that VUP-35K enhances both reward performance and model reasoning capability, while VideoDRM and VideoGRM yield significant gains under best-of-$N$ test-time scaling.

cs.CV↗

arXiv2026

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation

Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression. We take an RL-native perspective: diffusion RL already generates reward-scored finite-step trajectories, whose intermediate states provide distillation supervision. Based on this insight, we propose REST (Reward-Enhanced Scored-Trajectory Distillation), a single-stage co-training framework in which a decoupled student learns from the evolving RL teacher's trajectories without changing teacher optimization. Advantage-Modulated Distillation (AMD) transforms rollout advantages into signed weights, strengthening imitation of preferred trajectories and aligning distillation priorities with task value. The resulting framework is general and lightweight, requires no extra image rollouts, no separate distillation dataset, and no adversarial training. Experiments on compositional generation, visual text rendering, and human-preference alignment demonstrate competitive few-step, CFG-free generation with RAM or DiffusionNFT teachers. With only four sampling steps, REST-RAM achieves a DrawBench PickScore of 23.97, outperforming both the 40-step RAM teacher (23.95) and RTDMD (23.71).

cs.CV↗

arXiv2026

Flow-Matching-Based Protein Structure Tokenizer Made Efficient and Easy

As the bridge between protein modality and discrete modeling, protein structure tokenization still largely relies on heavily engineered training objectives tailored to specific downstream tasks and large training datasets, which hinders its transfer to broader application scenarios. To address this issue, we propose ProFiT, a lightweight flow matching tokenizer. With simple training strategies that encourage healthy codebook utilization, ProFiT can be trained efficiently and naturally learns semantically meaningful representations without any manual semantic alignment, while achieving reconstruction quality and generalization that match or surpass those of substantially larger tokenizers. We conduct extensive evaluations across a wide range of settings and demonstrate that ProFiT is a plug-and-play tokenizer adaptable to diverse downstream tasks. This study further reveals the significant potential of the flow matching tokenizer paradigm. Our code is publicly available at https://github.com/QDKStorm/ProFiT.

cs.LG↗

arXiv2026

Fidelity Probes for Specification--Code Alignment

Software modernization often relies on natural-language specifications recovered from an existing implementation. Incorrect or missing requirements can lead to defects in the modernized system. We introduce fidelity probes to check a specification against the code and guide its revision. Each probe pairs a question about program behaviour with a reference answer derived from the code. A language model answers the question using only the specification, and the fraction of agreeing answers defines fidelity. Disagreements flag conflicting claims or missing information and guide proposed corrections and additions to the requirements. An LLM generates probes directly from code or phrases facts selected through control-flow, data-flow, and call-graph analysis. We use an observability rule to focus probe questions on behaviour that the modernized system is intended to preserve, including user-visible outputs, changes to stored business data, and interactions with other systems. We revise the specification using fresh probes and evaluate each version on a fixed held-out set. A repair-regression model describes how new failures can offset the gains from repairs. On CardDemo, held-out fidelity improves from 0.59 to 0.89, exceeding free-form revision from source code. We also evaluate the method on industrial systems and public documentation, and assess probe quality and reported defects through human reviews and comparison with an independent requirements audit.

cs.LG↗

arXiv2026

DCFold: Efficient Protein Structure Generation with Single Forward Pass

AlphaFold3 introduces a diffusion-based architecture that elevates protein structure prediction to all-atom resolution with improved accuracy. This state-of-the-art performance has established AlphaFold3 as a foundation model for diverse generation and design tasks. However, its iterative design substantially increases inference time, limiting practical deployment in downstream settings such as virtual screening and protein design. We propose DCFold, a single-step generative model that attains AlphaFold3-level accuracy. Our Dual Consistency training framework, which incorporates a novel Temporal Geodesic Matching (TGM) scheduler, enables DCFold to achieve a 15x acceleration in inference while maintaining predictive fidelity. We validate its effectiveness across both structure prediction and binder design benchmarks.

cs.LG↗

arXiv2026

SWE-MILE: Asynchronous Potential-Induced Milestone Credit Assignment for Long-Horizon Software Engineering Agents

Long-horizon software engineering (SWE) agents trained with reinforcement learning with verifiable rewards (RLVR) typically receive only terminal outcome supervision, making it difficult to distinguish productive actions from redundant exploration or functional regressions. We propose SWE-MILE, an asynchronous potential-induced milestone credit assignment framework that derives fine-grained process supervision from workflow runtime, without auxiliary reward models or external evaluators. SWE-MILE quantifies task-relevant file exposure and test-state alignment as navigation and verification potentials, respectively. Differences in these potentials attribute milestone progress and regressions to individual actions, while discounted backward credit propagates supervision to preceding steps. To efficiently acquire intermediate verification states, SWE-MILE further introduces asynchronous shadow probing, which replays repository-changing actions in an isolated sandbox and runs verification in parallel with the agent's primary interaction, largely hiding verification latency. The resulting process credit augments terminal outcome advantages and provides informative learning signals. Experiments on two representative long-horizon SWE tasks demonstrate substantial improvements in agent performance, highlighting workflow runtime signals as a practical source of process supervision for long-horizon SWE agents.

cs.AI↗

arXiv2026

VCRE-Fib: View-Conditioned Regional Evidence for Fine-Grained Ultrasound Grading of Schistosoma japonicum-Associated Liver Fibrosis

Accurate assessment of Schistosoma japonicum-associated liver fibrosis is essential for disease management and long-term follow-up in endemic regions. Ultrasound provides non-invasive imaging, but complex local echogenic patterns and anatomical structures make fine-grained grading challenging. Existing deep learning methods can predict fibrosis scores, yet directly incorporating acquisition views and regional cues into grading while retaining spatial information for inspection remains an open problem. Here we present VCRE-Fib, a view-conditioned regional evidence framework that integrates anatomical context, local information, and global image assessment for fine-grained ultrasound grading. The framework forms view-conditioned local grading evidence before spatial pooling, uses weak localization to guide its aggregation, and combines it with global predictions. Image-only inference jointly returns a fibrosis score, acquisition view, and candidate abnormal-region map. We developed and evaluated the method on a re-curated cohort of 108,709 ultrasound images from 6,373 patients across 35 centers. On a patient-disjoint test set of 4,107 images from 240 patients across four centers, VCRE-Fib reduced the prespecified composite grading risk by 7.115% relative to SFibAI trained and evaluated on the same data split. Image-level mean absolute error decreased from 0.391 to 0.378, alongside lower patient-max, patient-median, and center-balanced risks. The full model also achieved lower composite grading risk than variants that separately removed view conditioning or weak localization. These results support incorporating anatomical context and regional evidence into ultrasound grading while exposing spatial predictions for inspection alongside severity estimates.

cs.CV↗

arXiv2026

TriDrive: Joint Driver, Vehicle, and Road Modeling for Forecasting and Driver Monitoring

Predicting how drivers, vehicles, and road scenes interact and evolve together is central to driver monitoring. Prior work models in-cabin activity or traffic-conditioned driver motion in isolation, motivating joint driver, vehicle, and road modeling with real-time on-vehicle evaluation. We introduce TriDrive, to our knowledge the first unified framework that jointly forecasts driver kinematics, vehicle dynamics, and road demands through an automation-conditioned transition model. Modality-specific encoders (an anchored kinematic representation of the driver, causal CAN-bus dynamics, and frozen V-JEPA 2 road latents with structured road margins) are connected by directed residual connections through which driver and road context refine vehicle forecasts. We evaluate TriDrive on three downstream tasks. On the public AIDE benchmark, its kinematic encoder recipe sets a new full-set state of the art (SOTA) among published baselines (48.05 versus 71.47 All-MPJPE). On 197.2 hours of naturalistic BATON subset, directed connections and road margins raise assistance-engaged PR-AUC by 0.084 for steering onset and 0.286 for time-to-collision drops. For real-time use, we distill the road encoders and run TriDrive on a comma four with an external 8 GB GPU, where a lightweight current-state warning probe updates at 5 Hz with 177 ms p95 latency while the joint model forecasts concurrently. The probe is above an openpilot-based baseline on human-labeled manual-driving warnings (AUROC 0.725 versus 0.563), and in a paired on-road study 14 drivers rate its warnings as more appropriate (+1.79) and timely (+2.67) than those of openpilot's driver-monitoring system.

cs.RO↗

arXiv2026

More Programs or More Rolls? Separating Coverage from Specialization in LLM Harnesses

Automated generation of LLM harnesses promises to improve inference through task specialization. Yet additional answer coverage can arise from repeated execution of the same program, making specialization difficult to identify. We introduce a controlled evaluation that separates answer coverage, repeatable task advantages, and gains from pre-execution selection. On 386 MATH-500 tasks, we compare eight generated harnesses plus a baseline with nine byte-identical baseline copies, using three executions per member. Identical programs yield 2.16 percentage points of repeat-averaged oracle headroom. Generated programs exhibit substantially more repeatable score patterns, but these chiefly reveal persistent weaknesses: losses relative to the baseline persist across all three repeats on 100 tasks, while persistent wins occur on only one task and are sensitive to answer extraction. The frozen selector gains 0.00 percentage points, and both populations reach 98.70% oracle coverage at 27 harness executions. Stable complementarity remains unresolved at three repeats. Supporting BIRD traces locate failures in mechanism implementation, activation, and output validity. Together, these findings establish why coverage and repeatability alone cannot justify claims of useful specialization. They motivate an evaluation standard for harness diversity: task advantages should persist across executions, guide usable decisions, and improve on additional fixed-program executions under matched inference budgets.

cs.AI↗

arXiv2026

Self-Evolving Coding Agents

Large language models are increasingly embedded in software engineering workflows as coding agents that can inspect repositories, invoke tools, execute tests, debug failures, and generate patches. Yet most existing coding agents remain largely static after deployment, even though software development is a dynamic, feedback-rich process in which repositories evolve, dependencies change, tests fail, and repair attempts leave reusable experience. This tension has motivated a growing body of work on self-evolving coding agents, where the agent improves its future behavior by persistently updating its framework, memory, skills and tools, components, workflow and topology, or environment and context from prior coding interactions. In this survey, we provide a structured synthesis of this emerging area. We first define the concept of self-evolving coding agents and distinguish it from conventional coding agents and general self-evolving agents. We then develop a taxonomy centered on the targets of evolution, complemented by two orthogonal perspectives: when evolution occurs and which code-specific signals drive it. We further examine the benchmarks used to measure the effect of evolution and related coding products. Across the literature, we find that executable feedback, repository-level context, and coding trajectories make software engineering a natural domain for agent self-evolution, but also introduce challenges in feedback reliability, benchmark overfitting, reversibility, system complexity, safety, cost, and generalization. By organizing existing work around these dimensions, this survey aims to clarify the conceptual boundaries of self-evolving coding agents and provide a foundation for designing more adaptive, reliable, and software-aware agentic systems.

cs.SE↗

arXiv2026

PFArena: Benchmarking Language Models for Protein Modification

Protein modification requires navigating an immense sequence space, yet wet-lab validation remains low-throughput and costly. Although computational paradigms including protein language models (PLMs), large language models (LLMs), and LLM-based agents have shown promise in protein modification, their relative efficacy across realistic experimental decision-making settings remains unclear. To bridge this gap, we introduce PFArena, a benchmark comprising four controlled task interfaces that cover single-mutant generation and multi-mutant ranking. By providing varying levels of mutation fitness data, PFArena reflects four representative research scenarios characterized by differing degrees of prior experimental context. We assess six PLMs, six LLMs, and five LLM-based agents using complementary metrics to measure both peak and overall protein modification performance. Our evaluation reveals that model performance shifts systematically with the availability of target-specific experimental evidence: PLMs demonstrate proficiency in open-ended single-mutant generation by leveraging protein-specific priors, whereas LLMs and agents perform strongly in multi-mutant ranking, particularly when target-specific fitness data are available. Nevertheless, all model families face fundamental challenges with increasing search-space size and mutation depth. We release our code and benchmark suite to facilitate reproducible research in model-assisted protein modification.

cs.AI↗

arXiv2026

SWE-Proof: Can Language Models Resolve Real-World Issues with Machine-Checked Proofs?

Ensuring the correctness of LLM-generated code is a core challenge for modern software engineering. Benchmarks for agentic code generation check correctness with held-out test suites, which are inherently incomplete and increasingly susceptible to memorization. Formal verification avoids both problems, but existing work covers only standalone tasks whose specifications are given as input, not real issues, which touch large repositories and state intent in vague natural language. We present Benchproofer, a pipeline that turns a coding task with a known correct patch into a formally verified one: it writes a specification for the new code, summarizes the existing functions that code calls with axioms, and admits an instance only after mechanical and adversarial gates agree. Applying it to SWE-bench Verified yields SWE-Proof, 500 real issues whose correctness is formally verified rather than tested, and it extends to SWE-bench Pro. Evaluating Claude Opus 4.8, we find that verification catches what tests miss: a quarter of test-passing patches admit counterexamples, which a structured natural-language specification does not fix, while a correct formal one lifts resolution from 85% to 95%. Writing that specification is the hard part: an agent that must write its own gains nothing over an unaided baseline, and only 56% of those specifications pass our audit. The usual failure is faithfulness, a specification that constrains part of the required behavior and leaves the rest free. Specification quality still tracks the outcome, failing on 92% of unresolved instances against 51% of resolved ones, making faithful specification synthesis a concrete open problem.

cs.LG↗

arXiv2026

Delving into Asymmetric Information Dynamics for High-Fidelity Virtual Try-On

Virtual try-on (VTON) requires precise pixel-level fidelity, yet mainstream Diffusion Transformers (DiTs) often suffer from texture degradation and structural drift. We identify symmetric interactions in standard joint-attention mechanisms as a source of these failures. Although such interactions support semantic flexibility in general-purpose editing, they allow stochastic noise to corrupt deterministic garment features in VTON. We analyze this problem through asymmetric information dynamics and introduce two diagnostic indicators: Conditional Attention Entropy (CAE) for feature unbiasedness and Injected Information Flux (IIF) for injection effectiveness. Our analysis suggests that symmetric bidirectional attention can corrupt conditional features and attenuate the conditional signal. To address these limitations, we propose RealFit, a framework that combines Unidirectional Information Flow (UIF) with Decoupled Timestep Modulation (DTM). UIF isolates the garment condition from stochastic noise to preserve garment identity, while DTM optimizes the modulation scale to maintain a strong conditional signal. The resulting time-invariant condition branch enables a conditional KV cache that reduces inference time by approximately 75%. RealFit offers a principled approach to conditional generation with state-of-the-art fidelity and efficiency.

cs.CV↗

arXiv2026

Safety-Critical Control under Uncertainty via Adaptive Conformal Quantile Prediction Intervals

Safety-critical control under uncertainty requires uncertainty representations that are both statistically valid (for certifiable performance) and compatible with enforceable safety constraints. However, existing methods often assume particular distributions of uncertainty for provable safety guarantees or establish symmetric and input-agnostic prediction intervals for robust safety, which can lead to misaligned or overly conservative safety constraints in control synthesis. In this paper, we introduce a novel safe control framework with adaptive uncertainty quantification that constructs calibrated and state-dependent prediction intervals to enable high-probability safety guarantees, while improving constrained control performance. The framework leverages adaptive conformal prediction (ACP) and extends it with conformal quantile regression (CQR) to capture distribution-free, asymmetric uncertainty intervals with certifiable probabilistic coverage, and integrates the resulting uncertainty sets into a probabilistic control barrier function formulation to enforce robust safety with reduced conservativeness. This yields uncertainty-aware safe control constraints that can be incorporated within a model predictive control(MPC) framework to provide provably safe behaviors with high probability. Simulation and theoretical results are provided to demonstrate the effectiveness of our approach.

cs.RO↗