Searcharxiv⌕ Search

arXiv subjects

Zhi Wang

Publications and source records attributed to Zhi Wang.

At least 37 records · Page 2Linked to original sources
arXiv2026

Weaponizing Ground Truth: Data Poisoning Attacks by Exploiting Boundary Misalignment Between Antivirus Software and Learning-Based Detectors

Machine-learning (ML)-based malware detectors are commonly trained using labels obtained from antivirus (AV) engines and aggregation services (e.g., VirusTotal). This practice assumes AV-generated labels provide reliable supervision. However, small byte-level modifications can substantially alter AV verdicts while leaving the representations perceived by downstream ML detectors largely unchanged, producing label-feature inconsistencies that can contaminate training datasets and create poisoning opportunities for ML-based malware detection. We present Bi-Iocane, a black-box poisoning framework that exploits the reliance of malware-labeling pipelines on AV-generated labels. Bi-Iocane identifies AV-sensitive bytes and modifies them to induce label changes. It rewrites such bytes in malware to obtain benign labels (evasion-oriented poisoning) and injects malware-associated byte patterns into benign software to obtain malicious labels (defamation-oriented poisoning). These poisoned samples and their lightly modified variants corrupt training data and cause selected targets to be misclassified. We evaluate Bi-Iocane with 13 AV engines simulating AV aggregation services and eight ML detectors. For 30 malware and 30 benign clean targets, Bi-Iocane combines AV-specific manipulations to generate malware-to-benign and benign-to-malware poisoned samples whose all tested AV-based labels are flipped. After these poisoned samples and variants are used for downstream training, the resulting ML models misclassify 92.08% of the original clean targets on average with only a 0.06\% poisoning budget per target. Meanwhile, the poisoned models largely preserve clean-set performance, and six evaluated poisoning defenses show only limited mitigation. VirusTotal evaluation further confirms practical defamation risk and reveals potential evasion risk in real-world AV-to-ML labeling supply chains.

cs.CR↗
arXiv2026

Breaking the Black Box: Byte-Level Boundary Inference of Real-World Antivirus Systems

Existing approaches for understanding the detection logic of real-world antivirus (AV) software infer only binary malware/benign decisions from black-box queries, providing limited insight into the fine-grained decision-critical regions that govern AV detection. In this paper, we present \textbf{AVHunter}, the first framework for inferring byte-level decision-critical regions of real-world AV products under a black-box threat model. AVHunter constructs the first large-scale Byte-Level AV Boundary Dataset (BABD) by systematically probing 11 real-world AV products, revealing that modern AV detections are largely associated with a small number of compact decision-critical byte regions. Leveraging BABD, AVHunter trains AV-specific models that not only reproduce binary AV decisions, but also localize the decision-critical byte regions underlying these decisions, achieving an average boundary prediction recall of 85.07% while maintaining 97.43% detection agreement with the target AVs. We further validate that the predicted regions capture genuine AV decision knowledge through boundary-guided malware evasion, false-positive induction on benign executables, and a seven-month longitudinal study demonstrating that the inferred regions remain largely stable as AV products evolve. Overall, AVHunter moves beyond conventional binary-label AV modeling by enabling fine-grained boundary-region localization and revealing a new form of AV knowledge leakage with important implications for malware analysis, AV security, and boundary-aware defenses.

cs.CR↗
arXiv2026

HelloWorld: Towards Practical Applications of Generative Driving World Models

Driving world models provide a promising route toward scalable counterfactual data generation and interactive simulation beyond recorded driving logs. Realizing this potential requires a system that can generalize across diverse scenes, respond faithfully to prescribed controls, generate coherent multi-sensor observations, and operate efficiently under repeated inference. We present \textbf{HelloWorld}, a 2B driving world model system designed around these requirements. HelloWorld progressively specializes broad visual and motion priors from heterogeneous video data into controllable driving generation using ego pose, HD maps, and 3D boxes. A block-causal generation interface, together with adaptation to self-generated context, aligns the model with sequential simulation. The system further supports synchronized seven-camera RGB generation and conditional LiDAR synthesis, and is distilled toward few-step inference for efficient deployment. Experiments evaluate visual quality, control fidelity, cross-view consistency, robustness under repeated generation, inference efficiency, and LiDAR synthesis. Together, HelloWorld provides a unified framework for scalable driving data generation and interactive simulation.

cs.CV↗
arXiv2026

HarnessPAI: An Evolving Harness for Physical AI

Physical AI aims to build embodied agents that perceive the world, understand and reason about it, and decide how to act. Yet the field has focused primarily on the last component: the action model that maps observations to low-level controls. The prevailing training recipe can erode the perceptual and reasoning capabilities needed for robust behavior, leaving even strong action models vulnerable to scene perturbations and long-horizon tasks. We introduce HarnessPAI, a model- and embodiment-agnostic Harness framework for Physical AI that treats code as the executable and evolvable interface that organizes the underlying action primitive. The framework separates two timescales: within a rollout, it executes open-loop at the program level, with a fixed program guiding and checking execution; across rollouts, it evolves closed-loop, using execution feedback to revise the program and distill failures into reusable skills. Across desktop robot arms, household robots, a robot vacuum, and a legged walking agent, HarnessPAI improves on both pure action models and code-as-policy baselines without retraining the underlying model: a 61.6-point gain over $π_{0.5}$ on LIBERO-PRO and a 27.2-point gain over WorldDreamer on RoboCasa atomic tasks. Once a program is selected, rollout execution requires no online high-level LLM deliberation. Beyond execution, the converged program is also a cheap and reliable expert-data collector, and fine-tuning $π_{0.5}$ on collected expert data lifts success rate on LIBERO-PRO by 38.8 points. Our results suggest that the frontier of Physical AI depends not only on stronger action models, but also on executable harnesses that integrate perception, task understanding and reasoning, and action execution into a unified, verifiable, and feedback-driven system. Website: https://darwin-agent.github.io/HarnessPAI

cs.RO↗
arXiv2026

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

In reinforcement learning for large language models, Proximal Policy Optimization (PPO) commonly uses a critic to estimate state values and reduce the variance of policy updates. However, we uncover a systematic failure mode in PPO critics, which we call Value Flattening: state values, estimated from multiple Monte Carlo continuations, change sharply across intermediate states while critic predictions remain comparatively flat. We further observe this phenomenon in a controlled FrozenLake environment and find that it becomes more pronounced as the state space grows. Our theoretical and empirical analyses relate Value Flattening to an implicit variance penalty in the critic loss and redundant updates from temporally correlated states with similar gradients. Motivated by these findings, we introduce SParse Proximal Policy Optimization (SP$^3$O), which applies the value loss to only a few well-separated states in each response to mitigate both effects. Experiments on Qwen3-Base show that SP$^3$O with only three states supervised per response can mitigate Value Flattening and consistently improve the learned policy across model sizes and evaluation suites. Together, our results identify Value Flattening as an important yet overlooked failure mode of critic learning in standard PPO and show that a simple sparse supervision strategy can mitigate it.

cs.LG↗
arXiv2026

LogICL: Demonstration Retrieval to Bridge the Semantic Gap in Cross-Domain Log Anomaly Detection

Effective log anomaly detection is critical to sustaining reliability in large-scale IT infrastructures. Transformer-based language models have advanced the field but require substantial computational resources and labeled data, exacerbating the cold-start problem in target domains with scarce logs. Cross-domain methods alleviate data scarcity by leveraging source-domain logs, but their reliance on surface lexical similarity limits generalization when structural and terminological differences obscure semantic equivalence. We propose LogICL, a demonstration-retrieval framework for cross-domain log anomaly detection. During training, LogICL constructs a sparse delta matrix by measuring the signed change in a frozen LLM's prediction error between zero-shot and one-shot inference for selected query-demonstration pairs. This outcome-level feedback supervises a lightweight encoder through a demonstration-utility loss, while maximum mean discrepancy and supervised contrastive losses promote domain alignment and anomaly discrimination. At inference, the encoder retrieves similarity-based anchors and expands them with candidates having the highest scores aggregated over precomputed positive delta relations. Thus, LogICL retrieves high-utility demonstrations without candidate-wise LLM evaluation and provides them to a frozen LLM for in-context anomaly prediction. Experiments on few-shot and target-domain zero-shot transfer benchmarks demonstrate strong performance across heterogeneous log systems. In the few-shot setting, LogICL outperforms Random-ICL and kNN-ICL in three of four transfers under the fixed split, while the benefit remains setting-dependent. Further analysis shows that LogICL can identify demonstrations with positive predictive utility despite low surface lexical similarity, helping bridge the semantic gap across logging systems.

cs.SE↗
arXiv2026

HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos

Human egocentric video captures rich manipulation demonstrations without any robot hardware, yet transferring these skills to robots remains challenging due to the embodiment gap between human and robot in both visual appearance and kinematics. We present HumanEgo, a framework that bridges the embodiment gap by lifting each human demonstration to an entity-level representation of hand-object interaction, and training a flow matching policy with dense auxiliary objectives that amplify supervision from every trajectory. HumanEgo is robot-data-free, hardware-agnostic, data-efficient, and zero-shot human-to-robot transferable. With only 30 minutes of human videos per task, HumanEgo achieves 92.5% average success across four real-world tasks (75% with just 15 minutes), outperforms matched-time robot teleoperation by 41%, and robustly transfers zero-shot across novel robots, cameras, and environments. We release HumanEgo as an easy-to-use, open-source framework for learning robot policies directly from human data: https://github.com/TX-Leo/HumanEgo

cs.RO↗
arXiv2026

Where to Compute and How to Interact: Operator-Readable Adaptation with Gauge-Aware Transport

Adaptive meshes enable neural operators for partial differential equations (PDEs) to allocate spatial samples and computation according to local physical structures. Existing approaches, however, mainly address where to compute, with less attention to how information should interact after node relocation. Mesh adaptation changes local sampling scales, neighborhood structures, and geometric contexts, so representations formed at different nodes may not be directly comparable. Direct aggregation can therefore entangle physical variation with discretization-induced representation variation. Because allocation and interaction are jointly optimized through the same output objective, their individual roles are also difficult to distinguish from final errors alone. We introduce operator readability, requiring an adaptive operator to account for and test why computation is allocated to particular locations and how representations interact under the resulting nonuniform discretization. Based on this principle, we propose the Gauge-Aware Adaptive Mesh Neural Operator (GA-AMNO). Physics-informed adaptive allocation answers where to compute, while geometry-conditioned low-rank Gauge transport maps source features into target representation contexts before aggregation, answering how to interact. This makes mesh-to-solver information exchange inspectable and intervenable. We establish sufficient conditions for representation-consistent aggregation and analyze approximate transport errors and continuity under topology-preserving mesh deformations. Experiments on five PDE benchmarks demonstrate improved predictive accuracy, while controlled interventions and geometric-mismatch analyses verify the roles of allocation and interaction and show that Gauge transport improves cross-discretization representation compatibility under strong geometric mismatch.

cs.LG↗
arXiv2026

TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents

Reliable deployment of LLM agents in user-facing products depends not on raw task-solving ability but on consistency and limit-awareness: behaving the same way across repeated trials, and recognizing when a request cannot, or cannot yet, be safely fulfilled. CAR-bench exposes this reliability gap in the domain of in-car assistants: an LLM-simulated user issues incomplete or ambiguous requests, requiring the agent to resolve uncertainty through multi-turn dialogue and tool use while strictly adhering to domain policies. Even frontier models show a substantial gap between what they can solve at least once (Pass@3) and what they solve consistently across trials (Pass^k). We bridge this gap with TRACE (TRAjectory-Contrastive Evolution), which iteratively improves a skill-based agent's behavioral knowledge without modifying model weights. This knowledge is organized as a Skill Bank of modular, retrievable skills, each encoding a self-contained set of tool-use rules and behavioral guidelines. TRACE evolves this bank through an agentic self-evolution loop: after each evaluation round, it groups trajectories by the skills invoked and refines each skill by contrasting successful and failed behaviors. The updated bank then guides subsequent rounds, while during deployment the Actor performs state-conditioned skill orchestration at every turn. On GPT-5.5, TRACE improves consistency (Pass^3) by 34.6 points, from 59.9% to 94.5%, while shrinking the gap between potential and reliable performance to just 4.0 points. On the official hidden set, TRACE achieved first place using GPT-5.6-Sol, attaining a Pass^3 score of 70%-a 40% relative improvement over the baseline. These results show that TRACE converts high model potential into stable, consistent performance gain. Project homepage: https://darwin-agent.github.io/Car-bench-TRACE.

cs.CL↗
arXiv2026

Corrections induced by the GUP to the Lamb shift of an accelerated atom interacting with a quantum scalar field

We investigate the effect of the GUP on the Lamb shift of a two-level atom interacting with a real massless scalar quantum field, within the DDC formalism. For an atom undergoing inertial motion, uniform acceleration, and uniform circular motion, we analyze the separate contributions of vacuum fluctuations and radiation reaction. We first derive the statistical functions of the field along the atom's trajectories for the three types of motion, expressing them as frequency integrals, and then employ them to calculate the vacuum fluctuation and radiation reaction contributions to the radiative level shift. We show that the GUP-modified Lamb shift of the two-level atom arises entirely from vacuum fluctuations and acquires additional corrections proportional to $β$. We focus in particular on the acceleration-dependent GUP corrections. For a uniformly accelerated atom, the GUP corrections comprise thermal and nonthermal parts. At low accelerations, the thermal part exhibits nonmonotonic behavior, and is proportional to $a^4$ in the limit $a/ω_0 \to 0$; the nonthermal part, by contrast, grows nonlinearly and monotonically, exceeding the thermal part by nearly two orders of magnitude at large accelerations. For an atom in uniform circular motion, the GUP corrections are purely nonthermal and also display a nonlinear, monotonic dependence on acceleration, increasing or decreasing steeply according to the sign of $β$. For the same $β$, the corrections are larger in uniform circular motion than in uniformly accelerated motion, since the former involves terms proportional to both $a^2$ and $a^3$, whereas the latter contains only $a^2$ terms.

quant-ph↗
arXiv2026

Bridging Quantum Mechanics to Liquid Properties via a Universal Organic Force Field

Molecular dynamics simulations are essential tools for unraveling atomic-level insights into the structure and behavior of condensed-phase systems. However, the universal and accurate prediction of macroscopic properties based on quantum mechanical calculations remains a significant challenge, often hindered by the trade-off between computational cost and simulation accuracy. Here we present ByteFF-Pol, a polarizable force field parameterized by a graph neural network and trained exclusively on high-level quantum mechanical data. By leveraging physically-motivated force field forms and training strategies, ByteFF-Pol predicts thermodynamic and transport properties for a wide range of small-molecule liquids and electrolytes with high accuracy, surpassing current classical and machine learning force fields. This ability to make predictions without system-specific training bridges the gap between microscopic calculations and macroscopic liquid properties, enabling the exploration of previously intractable chemical spaces. This advancement enables the precise design of new electrolytes and custom-tailored solvents, establishing a robust foundation for data-driven materials discovery.

physics.comp-ph↗
arXiv2026

VGGT-DP: Generalizable Robot Control via Vision Foundation Models

Visual imitation learning frameworks allow robots to learn manipulation skills from expert demonstrations. While existing approaches mainly focus on policy design, they often neglect the structure and capacity of visual encoders, limiting spatial understanding and generalization. Inspired by biological vision systems, which rely on both visual and proprioceptive cues for robust control, we propose VGGT-DP, a visuomotor policy framework that integrates geometric priors from a pretrained 3D perception model with proprioceptive feedback. We adopt the Visual Geometry Grounded Transformer (VGGT) as the visual encoder and introduce a proprioception-guided visual learning strategy to align perception with internal robot states, improving spatial grounding and closed-loop control. To reduce inference latency, we design a frame-wise token reuse (FTR) mechanism that reuses cached VGGT aggregator tokens from overlapping observation frames and computes features only for the latest frame, substantially reducing redundant visual encoding. We further apply random token pruning to enhance policy robustness and reduce overfitting. Experiments on challenging MetaWorld tasks show that VGGT-DP significantly outperforms strong baselines such as DP and DP3, particularly in precision-critical and long-horizon scenarios.

cs.RO↗
arXiv2026

MemFuse: Multi-Source Memory Fusion from Fragmented Observations

Long-term memory is essential for agents that operate across extended interactions, yet existing memory systems and benchmarks predominantly focus on single-source textual histories. In realistic settings, however, relevant information is often fragmented across applications and devices, as well as across users and time, requiring agents to integrate dispersed observations into coherent episodic memories while preserving their source provenance. To address these gaps, we introduce **MemFuseBench**, a benchmark for *multi-source memory fusion*. MemFuseBench is built with a Scene-to-Sensor pipeline that synthesizes controllable scenarios into source-tagged observations, evidence-grounded questions, and adversarial distractors. It enables systematic evaluation of temporal reasoning, cross-source evidence fusion, and robustness to noise. We further propose **MemFuse**, a structured memory system that preserves source-level evidence in event-layer atomic memory and organizes related atomic events into cluster-layer fused memory within a causal fusion graph. During retrieval, MemFuse retrieves and organizes related evidence fragments while maintaining traceability to original source events. Experiments on MemFuseBench show that MemFuse achieves the best overall performance among the evaluated memory systems under all three LLM settings and consistently improves performance on questions requiring cross-source evidence fusion.

cs.CL↗
arXiv2026

Grounding Large Language Models as Generalizable Policies in Network Control

Designing generalizable control policies that operate reliably under changing conditions is essential for robust network services in modern digital infrastructure. Yet network control remains dominated by specialized policies built from handcrafted rules or deep learning models, which struggle to generalize under real-world dynamics. Large language models (LLMs) offer a promising alternative because of their broad pretrained knowledge and emergent generalization abilities, but their practical adoption in network control is hindered by non-textual observations, constrained action spaces, complex optimization knowledge, and strict real-time requirements. Therefore, we introduce Trailblazer, a systematic framework that combines domain alignment to adapt LLMs for network control with adaptive policy collaboration to reduce inference overhead. Simulations across two heterogeneous network control tasks, adaptive bitrate streaming and cluster job scheduling, show that Trailblazer improves performance over conventional policies by 6.5%-36.6% and 3.5%-41.3%, respectively. Moreover, in a large-scale online A/B test of congestion control on Douyin, Trailblazer outperforms a highly optimized industrial policy, corresponding to a projected reduction of approximately 3,145 hours of platform-wide video stall time per day. Further analysis reveals that effective LLM-based control can be achieved by properly aligning compact LLMs and only invoking them for complex conditions, rather than model scaling or extensive invocation. Together, our results establish an LLM-driven paradigm for designing generalizable network policies and offer practical insights into grounding foundation models for real-world network control.

cs.LG↗
arXiv2026

OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories

Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding. The prevailing recipe learns this capability from teacher-generated trajectories filtered for answer correctness, implicitly assuming that every successful demonstration provides effective supervision. We argue this assumption is flawed: a strong teacher often reaches the correct answer without needing its tool calls, and imitating such trajectories teaches a student that tool calls accompany correct answers, not that tool observations ground them. We present OpenVisTool, an open framework for constructing instructive visual tool-use trajectories that provide effective supervision for tool learning. The key insight is that a trajectory should be retained only if its answer is correct (outcome validity) and its tool observations causally contribute to that answer (causal utility). The framework operates in three stages: difficulty screening to select queries that are not reliably answerable without tools, domain-specific trajectory synthesis to elicit coherent tool-use trajectories, and supervision verification to jointly test both conditions. Rather than encouraging models to imitate tool calls, the resulting supervision teaches when and how visual evidence should be acquired. Using this framework, we construct OpenVisTool-42K, a dataset spanning five visual reasoning domains, together with OpenVisTool-Bench, a benchmark covering the same domains. Across four backbones (4B-27B), fine-tuning on OpenVisTool-42K consistently improves visual tool-use performance and yields gains on two out-of-distribution benchmarks; the larger models approach leading closed-source systems. The evidence suggests that effective visual tool use is learned from causally grounded supervision rather than tool-calling patterns.

cs.CL↗
arXiv2026

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents

Rejection sampling fine-tuning (RFT) is widely used to train code agents by generating trajectories on verifiable software engineering tasks, retaining those that pass the tests, and fine-tuning on the successful rollouts. However, even strong code agents repeatedly fail on a substantial fraction of such tasks, and standard RFT simply discards these failures. The discarded samples are precisely the hardest and most informative ones, drawn from verifiable instances that are costly to curate. Stronger base models may reduce the number of failures, but the remaining hard cases still define the frontier for further improvement. We propose FailForge, an agentic framework that converts failed rollouts into training signal. For each failed instance, an agent diagnoses the failure from error feedback and execution traces, distills the diagnosis into a concise and actionable skill, and injects the skill into the agent context for a guided second attempt. Trajectories that succeed under skill guidance are folded back into the RFT corpus. Crucially, the skill is removed at training time, so the model internalizes the recovered behavior rather than relying on external hints at inference. FailForge recovers over 26% of previously failed instances at marginal additional cost, and training Qwen3.5-4B on the augmented corpus improves the SWE-bench Verified resolve rate by 6.6 points over a strong RFT baseline, with gains concentrated on the hardest problems.

cs.AI↗
arXiv2026

Berry curvature effects of chiral superconducting rhombohedral graphene

We study the Berry curvature effects of the Bogoliubov quasiparticles in chiral superconducting rhombohedral graphene. Using a two-band Bogoliubov-de Gennes Hamiltonian to describe the superconducting quasiparticles, we calculate the momentum-space Berry curvature, orbital magnetic moment, and anomalous thermal Hall, spin Nernst, and orbital Nernst transport of chiral $p$-wave superconducting states. We investigate the impact of normal-state band warping in rhombohedral graphene, which can generate Bogoliubov Fermi surfaces for quasiparticle excitations. We find that Bogoliubov Fermi surfaces qualitatively modify the anomalous transport responses, inducing a deviation of the thermal Hall conductivity from the quantized value and strongly enhancing the spin and orbital Nernst responses.

cond-mat.supr-con↗
arXiv2026

Semiclassical theory for the orbital magnetic moment of superconducting quasiparticles

We study the orbital magnetic moment of Bogoliubov quasiparticles in superconductors with the semiclassical approach. We derive the orbital magnetic moment of a quasiparticle wavepacket by considering the energy correction of the wavepacket to the linear order of the magnetic field. The semiclassical result is further verified by a linear response calculation with a full quantum mechanical method. From the analytical expression we find that nontrivial structure in the superconducting pairing gap alone is unable to produce quasiparticle orbital magnetic moment, which is in sharp contrast to the behavior of quasiparticle Berry curvatures. We apply the formula to study a tight-binding model with chiral $d$-wave superconducting gap, and show the influence of orbital magnetic moment on the energy spectrum and local density of states. We also calculate the orbital Nernst effect driven by the interplay between the orbital magnetic moment and the Berry curvature of Bogoliubov quasiparticles.

cond-mat.supr-con↗