Searcharxiv⌕ Search

arXiv subjects

Ziliang Wang

Publications and source records attributed to Ziliang Wang.

At least 19 recordsLinked to original sources
arXiv2026

Acting in Meters: Learning Metric Interactions for Precise Robotic Manipulation

Vision-Language-Action models and World-Action Models have advanced language-conditioned robotic manipulation, yet often leave metric relations among actions, objects, and scene geometry implicit. Human manipulation combines semantic understanding of task-relevant objects with spatial feedback that guides hand motion relative to objects and their surroundings. Inspired by this, we introduce a metric interaction framework that models object-level and scene-level interactions in physical Cartesian space at a shared metric scale. At the object level, Interaction-Centric Tokens (ICTs) explicitly represent end-effector pose trajectories relative to manipulated objects and are jointly denoised with actions, providing physically grounded interaction supervision. At the scene level, the Metric Action Interaction Field (MAIF) uses action and ICT queries to attend to metric scene point-cloud features and learns geometry-conditioned action corrections. Through two-stage adaptation, our framework improves diverse VLA and WAM baselines with a small number of additional parameters and training steps. Experiments demonstrate average success-rate gains of 0.80 and 3.59 percentage points on LIBERO and RoboTwin~2.0, respectively, alongside gains of 6.80 percentage points on real-world tasks and 7.45 percentage points on their out-of-distribution variants.

cs.RO↗
arXiv2026

Evolving Error States: Failure-Aware Progressive Repair for Ultrasound Lesion Segmentation

Reliability under sparse and heterogeneous failures remains a fundamental challenge for medical image segmentation. High average accuracy can conceal a small set of structurally distinct and clinically consequential errors. Existing post-hoc correction methods alleviate this problem, but typically estimate false-positive and false-negative corrections from the same fixed prediction. This ignores the dynamic evolution of error states and limits the correction of complex cases. Inspired by iterative error feedback in structured prediction, we propose Failure-Aware Progressive Repair (FAPR). FAPR represents the current segmentation mask as a dynamic failure state and models each repair operation as a state-transition operator. Each accepted correction forms a new prediction state for subsequent error diagnosis and repair, enabling later operations to adapt to preceding changes. Conditional routing selectively activates necessary state transitions, while failure replay exposes the model to rare error states. By keeping the base segmentor frozen, FAPR preserves its established segmentation capability while improving difficult cases. Across three public ultrasound lesion segmentation benchmarks, FAPR improves mean DSC by 1.52%. On the very-hard subsets of BUSI and TN3K, the average gain reaches 13.77%.

cs.CV↗
arXiv2026

MechReason: Benchmarking Multi-Image Multi-Hop Reasoning in Mechanical Engineering

Despite significant progress in general visual question answering and cross-modal understanding, multimodal large language models still face a pronounced gap in evaluation for complex reasoning within the mechanical engineering domain. Existing benchmarks predominantly focus on rudimentary tasks such as drawing recognition, CAD interpretation, or single-chart querying, falling short of assessing whether models can integrate multiple images, textual conditions, physical principles, and engineering constraints to perform multi-step reasoning when confronted with authentic, intricate mechanical problems. To address this, we introduce MechReason, a benchmark derived from real mechanical engineering papers, comprising 12k question-answer pairs with explicit reasoning-chain annotations and 21k visual materials spanning nine evidence types, including statistical charts, parameter tables, engineering drawings, microscopic images, simulation images, system architectures, real mechanical scene photos, CAD model images and manufacturing flowcharts. MechReason covers eight task types across four reasoning dimensions: explanation, prediction, design, and diagnosis. We devise a four-stage construction pipeline: we first extract core engineering claims and decompose their supporting evidence into premises, reasoning processes, conclusions, and corroborative evidence; we then generate shortcut-preventing questions by masking posterior verification information; finally, we apply multimodal quality validation to ensure task quality and multi-hop nature. Extensive experimental results demonstrate that MechReason is highly challenging, with even the most advanced models achieving only 62.89\% accuracy.

cs.CV↗
arXiv2026

SafeSceneReason: A Multimodal Reasoning Benchmark Connecting Industrial Hazards with Accident Knowledge

Industrial-safety understanding requires more than detecting workers, equipment, and personal protective equipment. Models must also assess compliance, identify hazardous interactions, explain potential accident mechanisms, and recommend preventive actions. Existing safety datasets primarily focus on visual perception or isolated violation recognition and provide limited supervision for evidence-grounded reasoning. We introduce SafeSceneReason, a multimodal industrial-safety reasoning benchmark and companion training corpus that connects workplace scenes with knowledge from occupational accident investigations. SafeSceneReason combines two complementary data-construction pipelines. The scene-centric pipeline converts annotated workplace images into executable safety scene graphs and generates deterministic answers through program execution over objects, relations, and safety rules. The report-centric pipeline extracts figures and contextual evidence from accident reports and constructs multimodal questions using evidence graphs, explicit information boundaries, multi-step reasoning paths, and iterative verification. The resulting resource contains 110,581 verified scene-centric question--answer pairs and 13,114 refined report-centric question--answer pairs, covering perception, spatial and quantitative reasoning, compliance assessment, evidence synthesis, causal analysis, and mitigation-oriented decision making. Evaluation of representative proprietary and open-source vision--language models reveals substantial performance differences and persistent weaknesses in comparative, technical, and multi-evidence reasoning, demonstrating that strong general visual understanding does not yet guarantee reliable industrial-safety reasoning.

cs.AI↗
arXiv2026

MMArch: Benchmarking Multimodal Reasoning Grounded in Architectural Evidence

Multimodal large language models (MLLMs) perform strongly on engineering imagery, yet existing benchmarks mostly test drawing recognition, information extraction, or compliance checking, leaving open whether models can combine distributed visual evidence with engineering principles to reach a conclusion. We introduce MMArch, a benchmark for architecture and civil engineering spanning ten subdomains and built entirely from figures in peer-reviewed papers. Its $1{,}212$ short-answer items are produced by a decoupled planner--writer pipeline and validated through automated screening, a blind adversarial audit, and expert review, so that answering requires perceiving the relevant evidence, identifying the governing principle, and applying it, not exploiting textual or single-figure shortcuts. Evaluating $18$ open-weight and proprietary MLLMs against a domain-expert panel, we find a wide gap: the strongest open-source model attains about $30\%$ and the best proprietary system $52\%$, while human experts reach $95\%$, more than forty points ahead. Our error analysis shows that failures concentrate in applying principles and combining evidence across figures rather than in locating it, pointing to substantial headroom for future research. Code and data are available at https://dcx-swjtu.github.io/MMArch/.

cs.AI↗
arXiv2026

CircuitReason-1k: Benchmarking Long-Horizon Visual-to-Symbolic Reasoning inElectrical Circuits

Electrical circuit analysis requires more than recognizing components in an image. A solver must ground symbols and labels, recover latent topology, select a physical model, formulate coupled equations, propagate intermediate quantities, and preserve units, signs, directions, and phase conventions. We introduce \benchmark, a benchmark of 1,000 authentic textbook problems for evaluating this complete long-horizon visual-to-symbolic reasoning process. Each problem pairs one or more circuit diagrams with a self-contained question, a typed or semantically specified answer, and a reference worked solution. An evidence-first construction pipeline aligns questions, figures, and solutions, while a reasoning-oriented taxonomy organizes problems by circuit type and dependency depth. Evaluation combines conservative typed scoring with identity-blinded multi-model semantic consensus, retaining every problem in the denominator. Across three commercial chatbot systems and six open-source multimodal large language models, the highest-scoring system reaches 84.8\% accuracy. However, performance consistently deteriorates on long-horizon problems, and qualitative analysis exposes persistent failures in topology-to-target binding, physical conventions, and late-stage output propagation. \benchmark{} provides a focused testbed for measuring whether multimodal models can transform technical visual evidence into sustained, physically valid symbolic reasoning. Code are available at GitHub - CircuitReason/CircuitReason1K.

cs.AI↗
arXiv2026

CARE: Anti-entanglement Ultrasound Image Segmentation via Channel-Aware Region Extrication

Accurate ultrasound image segmentation is fundamentally challenged by target-context entanglement, where lesion cues are easily mixed with surrounding tissues and artifacts of similar appearance. Although existing methods often localize suspicious regions reasonably well, they remain vulnerable to ambiguous predictions because they mainly strengthen feature extraction or context aggregation, rather than explicitly organizing how lesion and interference cues are represented and distinguished. To address this limitation, we propose Channel-Aware Region Extrication (CARE), a segmentation framework that improves ultrasound segmentation by progressively extricating lesion evidence from visually entangled context. Instead of merely reweighting features, CARE explicitly separates encoded responses according to their lesion relevance and then re-evaluates the resulting complementary representations through reciprocal region interaction, so that suppressed lesion cues can be recovered while misleading contextual activations are corrected. In this way, CARE promotes target-context discrimination directly in the learned representation, without sacrificing localization quality. Extensive experiments on BUSI, BUSIS, and TN3K benchmarks show that CARE consistently achieves superior performance, thereby validating representation extrication as an effective solution for addressing the inherent visual ambiguity in ultrasound segmentation.

cs.CV↗
arXiv2026

Registering the 4D Millimeter Wave Radar Point Clouds Via Generalized Method of Moments

4D millimeter wave radars (4D radars) are new emerging sensors that provide point clouds of objects with both position and radial velocity measurements. Compared to LiDARs, they are more affordable and reliable sensors for robots' perception under extreme weather conditions. On the other hand, point cloud registration is an essential perception module that provides robot's pose feedback information in applications such as Simultaneous Localization and Mapping (SLAM). Nevertheless, the 4D radar point clouds are sparse and noisy compared to those of LiDAR, and hence we shall confront great challenges in registering the radar point clouds. To address this issue, we propose a point cloud registration framework for 4D radars based on Generalized Method of Moments. The method does not require explicit point-to-point correspondences between the source and target point clouds, which is difficult to compute for sparse 4D radar point clouds. Moreover, we show the consistency of the proposed method. Experiments on both synthetic and real-world datasets show that our approach achieves higher accuracy and robustness than benchmarks, and the accuracy is even comparable to LiDAR-based frameworks.

cs.RO↗
arXiv2026

Locker-based Truck-Drone Routing with Integrated Considerations of Pickups, Deliveries, and No-Fly Zones

Truck-drone delivery is an emerging last-mile logistics mode combining the long-haul capacity of trucks with the flexible service capability of drones. In locker-based operations, smart lockers serve not only as temporary parcel storage facilities but also as automated drone docking and service nodes. These automated nodes support drone takeoff, landing, parcel handover, and battery replacement, thereby significantly extending the service range and operational flexibility of drone-assisted delivery networks. However, practical locker-based delivery systems face complex real-world challenges, requiring the integrated coordination of not only parcel delivery, return pickup, battery-constrained and load-dependent drone flights, but also necessary detours around restricted airspace. To address this practical and multifaceted challenge, this paper introduces a locker-based truck-drone routing problem with integrated considerations of pickups, deliveries, and no-fly zones (LTDRP-PDNF), with the objective of minimizing the total operational cost of a fleet of drone-equipped trucks. We formulate the route construction process as a Markov Decision Process and develop a two-stage deep reinforcement learning-based neural heuristic. The first stage utilizes an attention-based encoder and a Bidirectional Gated Recurrent Unit decoder to solve the truck-only routing problem, formulated as a capacitated vehicle routing problem. The second stage combines a policy-transfer strategy with a hybrid dispatch assignment heuristic to construct fully coordinated truck and drone routes for LTDRP-PDNF. Experiments on instances of different scales demonstrate that the proposed method outperforms metaheuristic and neural heuristic baselines in most cases while maintaining exceptionally short computation times, offering an effective, scalable solution framework under practical operational constraints.

cs.RO↗
arXiv2026

AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models

Post-training alignment of large language models often combines supervised fine-tuning (SFT) on expert demonstrations with reinforcement learning (RL) from preference or verifiable feedback. SFT provides a useful behavioral anchor but can overfit to static demonstrations, whereas RL encourages exploration but may drift from expert behavior or exploit imperfect rewards. We propose \textbf{AAPA} (\emph{Adversarially Anchored Preference Alignment}), a plug-in framework that augments existing post-training objectives with a sentence-level adversarial anchoring signal. AAPA compares policy rollouts with offline, pre-collected expert responses using a fixed lightweight discriminator, and therefore requires neither online teacher inference nor discriminator co-training during policy optimization. The same anchoring term can be added to SFT, GRPO, and CHORD while preserving their original training pipelines. Experiments on instruction-following benchmarks show that AAPA consistently improves the corresponding base objectives across model scales. In particular, the staged AAPA configuration improves over a strong GRPO baseline by 5.77\% on \texttt{Qwen3-0.6B} and 3.75\% on \texttt{Qwen3-4B}. Further analyses on response length, log-probability distributions, and discriminator variants suggest that adversarial anchoring provides a stable semantic grounding signal for preference optimization. Code is available at \url{https://github.com/IsFaqq/AAPA}.

cs.AI↗
arXiv2026

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs

Although reinforcement learning (RL) has expanded the cognitive boundaries of large language models (LLMs), it often remains vulnerable to the autoregressive curse in long-horizon logical reasoning: small epistemic perturbations introduced early in generation can propagate irreversibly along the Markov decision process flow, triggering cascading failures that drive the reasoning trajectory toward collapse. To overcome this autoregressive cascade, in which a single early mistake can compromise all subsequent reasoning steps, we propose dynamic epistemic entropy orchestrated erasable reinforcement learning ($\text{E}^3\text{RL}$). $\text{E}^3\text{RL}$ eliminates reliance on external signals by grounding the model's endogenous local autoregressive cross-entropy as an intrinsic coordinate of epistemic uncertainty. By introducing segment-level adaptive dynamic thresholds and advantage allocation, $\text{E}^3\text{RL}$ enables the model to precisely excise localized logical defects while reusing historical key-value (KV) cache streams, thereby endowing the reasoning process with a self-healing capability. We train $\text{E}^3\text{RL}$ on the DeepMath-103k dataset. Experimental results show that $\text{E}^3\text{RL}$ reshapes the exploration efficiency of long-sequence reasoning and improves sample efficiency while maintaining linear memory overhead. On mathematical reasoning benchmarks such as AIME, $\text{E}^3\text{RL}$ achieves substantial performance gains, with the 4B and 8B parameter models surpassing previous state-of-the-art (SOTA) results by 5.349\% and 6.514\%, respectively. These findings suggest that $\text{E}^3\text{RL}$ shatters the autoregressive curse in long-sequence reasoning and establishes a theoretical and systems-level foundation for the next generation of self-healing artificial general intelligence (AGI).

cs.AI↗
arXiv2026

Decoupled Residual Quantization for Robust Semantic IDs in Recommendation

Semantic IDs represent items as shared discrete token sequences and have become a practical tool for recommendation and retrieval. Yet it remains difficult to tell why a tokenizer fails: poor quality may come from codebook underutilization, unstable decision boundaries, or geometric distortion of the embedding space. This paper develops a quantitative framework for diagnosing these failures through expected codeword overlap and effective codebook capacity. The former measures expected codeword confusion under retrieval-time perturbation, while the latter converts that confusion into an effective number of usable, well-separated codes. The framework links semantic boundary confusion to both code usage imbalance and Euclidean geometric constraints. As a proof of concept, we present Decoupled Residual Quantization (DRQ), which separates continuous geometry reconstruction from discrete distribution matching. Experiments on a large-scale industrial dataset show that Semantic ID quality is multi-objective: symbolic robustness, reconstruction fidelity, and behavior-aware soft matching each stress different aspects of a tokenizer. These downstream observations are based on one proprietary industrial dataset, so they should be read as a case study rather than a universal benchmark claim.

cs.IR↗
arXiv2026

UniRec: Bridging the Expressive Gap between Generative and Discriminative Recommendation via Chain-of-Attribute

Generative Recommendation (GR) reframes retrieval and ranking as autoregressive decoding over Semantic IDs (SIDs), unifying the multi-stage pipeline into a single model. Yet a fundamental expressive gap persists: discriminative models score items with direct feature access enabling explicit user-item crossing, whereas GR decodes over compact SID tokens without item-side signal. We formalize this via Bayes' theorem: ranking by p(y|f,u) is equivalent to ranking by p(f|y,u), which factorizes autoregressively over item features, showing that a generative model with full feature access matches its discriminative counterpart, with any practical gap stemming solely from incomplete feature coverage. We propose UniRec with Chain-of-Attribute (CoA) as its core mechanism. CoA prefixes each SID sequence with structured attribute tokens:category, seller, brand, before decoding the SID, recovering the item-side feature crossing that discriminative models exploit. Since items sharing identical attributes cluster in adjacent SID regions, attribute conditioning yields a measurable per-step entropy reduction H(s_k|s<k,a) < H(s_k|s<k), narrowing the search space and stabilizing beam search. We further address two deployment challenges: Capacity-constrained SID introduces exposure-weighted capacity penalties into residual quantization to suppress token collapse and the Matthew effect; Conditional Decoding Context (CDC) combines Task-Conditioned BOS with hash-based Content Summaries to inject scenario signals at each decoding step. A joint RFT and DPO framework aligns the model with business objectives beyond distribution matching. Experiments show UniRec outperforms the strongest baseline by +22.6% HR@50 overall and +15.5% on high-value orders. Deployed on Shopee's e-commerce platform, online A/B tests confirm significant gains in PVCTR (+5.37%), orders (+4.76%), and GMV (+5.60%).

cs.IR↗
arXiv2026

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs

While search-augmented large language models (LLMs) exhibit impressive capabilities, their reliability in complex multi-hop reasoning remains limited. This limitation arises from three fundamental challenges: decomposition errors, where tasks are incorrectly broken down; retrieval missing, where key evidence fails to be retrieved; and reasoning errors, where flawed logic propagates through the reasoning chain. A single failure in any of these stages can derail the final answer. We propose Erasable Reinforcement Learning (ERL), a novel framework that transforms fragile reasoning into a robust process. ERL explicitly identifies faulty steps, erases them, and regenerates reasoning in place, preventing defective logic from propagating through the reasoning chain. This targeted correction mechanism turns brittle reasoning into a more resilient process. Models trained with ERL, termed ESearch, achieve substantial improvements on HotpotQA, MuSiQue, 2Wiki, and Bamboogle, with the 3B model achieving +8.48% EM and +11.56% F1, and the 7B model achieving +5.38% EM and +7.22% F1 over previous state-of-the-art(SOTA) results. These findings suggest that erasable reinforcement learning provides a powerful paradigm shift for robust multi-step reasoning in LLMs.

cs.CL↗
arXiv2026

SELF-EMO: Emotional Self-Evolution from Recognition to Consistent Expression

Emotion Recognition in Conversation (ERC) has become a fundamental capability for large language models (LLMs) in human-centric interaction. Beyond accurate recognition, coherent emotional expression is also crucial, yet both are limited by the scarcity and static nature of high-quality annotated data. In this work, we propose SELF-EMO, a self-evolution framework grounded in the hypothesis that better emotion prediction leads to more consistent emotional responses. We introduce two auxiliary tasks, emotional understanding and emotional expression, and design a role-based self-play paradigm where the model acts as both an emotion recognizer and a dialogue responder. Through iterative interactions, the model generates diverse conversational trajectories, enabling scalable data generation. To ensure quality, we adopt a data flywheel mechanism that filters candidate predictions and responses using a smoothed IoU-based reward and feeds selected samples back for continuous self-improvement without external supervision. We further develop SELF-GRPO, a reinforcement learning algorithm that stabilizes optimization with multi-label alignment rewards and group-level consistency signals. Experiments on IEMOCAP, MELD, and EmoryNLP show that SELF-EMO achieves state-of-the-art performance, improving accuracy by +6.33% on Qwen3-4B and +8.54% on Qwen3-8B, demonstrating strong effectiveness and generalization.

cs.AI↗
arXiv2026

Unveiling Mechanisms of SEI Formation and Sodium Loss in Sodium Batteries via Interface Reactor Sampling

The solid electrolyte interphase SEI critically dictates the cyclability and Coulombic efficiency of sodium-metal batteries, yet its dynamic formation mechanisms and atomic-scale evolution during electrochemical cycling remain elusive due to the spatiotemporal limitations of existing techniques. Here, an "Interface Reactor" sampling strategy is proposed to construct a charge-aware neuroevolution potential (qNEP). This approach overcomes the instability bottlenecks of conventional machine learning potentials, enabling stable, first-principles-accurate molecular dynamics simulations of complex electrode-electrolyte interfaces on the hundred-nanosecond scale. Fundamentally distinct SEI formation mechanisms are revealed during the early stage: carbonate-based electrolytes form heterogeneous organic-inorganic matrices via "mixed co-formation," whereas ether-based electrolytes generate dense, self-limiting inorganic barriers through "surface-energy-controlled" NaF crystallization. Metadynamics simulations further elucidate that these compositional disparities govern sodium-ion storage dynamics: NaF-rich SEIs facilitate efficient metallic deposition, while carbonate-dominated interphases induce irreversible sodium trapping and continuous electrolyte decomposition. These findings establish a comprehensive atomic-scale framework linking solvation structure, interfacial reaction networks, and electrochemical performance, providing mechanistic guidelines for rational SEI engineering in next-generation alkali-metal batteries. Crucially, a general and robust computational framework is established for simulating complex interfacial reactions in electrochemical systems.

cond-mat.mtrl-sci↗
arXiv2026

VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security Specifications

Large language models (LLMs) have achieved remarkable progress in code understanding tasks. However, they demonstrate limited performance in vulnerability detection and struggle to distinguish vulnerable code from patched code. We argue that LLMs lack understanding of security specifications -- the expectations about how code should behave to remain safe. When code behavior differs from these expectations, it becomes a potential vulnerability. However, such knowledge is rarely explicit in training data, leaving models unable to reason about security flaws. We propose VulInstruct, a specification-guided approach that systematically extracts security specifications from historical vulnerabilities to detect new ones. VulInstruct constructs a specification knowledge base from two perspectives: (i) General specifications from high-quality patches across projects, capturing fundamental safe behaviors; and (ii) Domain-specific specifications from repeated violations in particular repositories relevant to the target code. VulInstruct retrieves relevant past cases and specifications, enabling LLMs to reason about expected safe behaviors rather than relying on surface patterns. We evaluate VulInstruct under strict criteria requiring both correct predictions and valid reasoning. On PrimeVul, VulInstruct achieves 45.0% F1-score (32.7% improvement) and 37.7% recall (50.8% improvement) compared to baselines, while uniquely detecting 24.3% of vulnerabilities -- 2.4x more than any baseline. In pair-wise evaluation, VulInstruct achieves 32.3% relative improvement. VulInstruct also discovered a previously unknown high-severity vulnerability (CVE-2025-56538) in production code, demonstrating practical value for real-world vulnerability discovery. All code and supplementary materials are available at https://github.com/zhuhaopku/VulInstruct-temp.

cs.SE↗
arXiv2026

Quantifying Non-linearity in Topology Optimization with similarity based Visualization

Topology optimization (TO) can be viewed as seeking an optimal solution in the design space of a given TO problem. For weakly non-linear TO problems, e.g., compliance minimization, sensitivity-based methods typically converge well, whereas for strongly non-linear problems, e.g., maximum stress minimization, stabilization strategies such as stabilization terms and projection functions are often required to enhance convergence. Especially in scenarios with massive design variables, it is difficult to intuitively demonstrate the non-linear complexity of different TO problems and to elucidate the mechanisms by which stabilization strategies affect convergence. To address this challenge, we propose a visualization framework and a quantitative non-linearity index for objectives with varying complexity. We employ a multi-start fixed-gradient sampling tailored to similarity-based dimensionality reduction while keeping the computational cost under control. The samples are then parameterized via cosine similarity to obtain a low-dimensional visualization surface of the objective function. Based on this visualization, we construct a dimensionless complexity index with a clear geometric interpretation by measuring the gap between the visualization surface and the discrete approximation of its convex envelope, which enables quantitative comparisons of non-linearity across TO tasks, parameter choices, and stabilization strategies. Extensive comparative experiments show that the proposed approach is both adaptable and discriminative on a variety of representative TO problems, and it provides intuitive and measurable guidance for parameter selection.

math.OC↗