Searcharxiv⌕ Search

arXiv subjects

Chenxi Wang

Publications and source records attributed to Chenxi Wang.

At least 19 recordsLinked to original sources
arXiv2026

Beyond Accuracy: ARIA-Rubrics for Evaluating Audio Reasoning in Large Audio Language Models

Large Audio Language Models (LALMs) have shown strong performance on audio reasoning benchmarks, but accuracy alone cannot distinguish true reasoning from superficial pattern matching, often overestimating reasoning ability since high scores may result from guessing rather than genuine audio understanding. Evaluating the reasoning process itself is essential for improving LALMs' reasoning ability, yet remains challenging. Existing methods either rely on costly human annotation or opaque LLM-as-judge approaches, making them impractical, biased, and lacking transparency. Moreover, audio reasoning introduces unique challenges absent in text-based settings, perceptual hallucination and cross-modal alignment between audio understanding and textual inference, hence text-based evaluation frameworks cannot be directly applied. Therefore, we propose ARIA-Rubrics (Audio Reasoning Integrity Assessment), a lightweight, annotation-free gold reasoning chains, automatic and transparent framework comprising six complementary metrics that evaluate audio reasoning quality across perceptual grounding, reasoning coherence, and answer consistency. We use Chain-of-Thought prompting as an externalization mechanism to make the reasoning process observable. Experiments on 9 models across 2 benchmarks identify three reasoning modes of current LALMs with actionable directions for future development, with ARIA-Rubrics achieving high correlation with human judgments. The code is available at the Github Repository.

cs.SD↗
arXiv2026

Anchored Scenario Coverage for Failure-Aware First-Hit Batch Inverse Design

Early discovery of at least one valid design satisfying a target requirement is a central objective in failure-prone closed-loop inverse design. A natural batch baseline ranks candidates by a product-form marginal valid-hit score, but selecting the highest-ranked candidates independently can produce redundant recommendations under predictive uncertainty and waste the experiment budget. We introduce ARC-SC(Anchored Risk-Constrained Scenario Coverage), a batch acquisition method that preserves strong marginal candidates as anchors and allocates the remaining batch positions by maximizing complementary coverage over predictive target scenarios under a risk-support constraint. In frozen-oracle closed-loop simulations on superconductivity and JARVIS materials-property benchmarks, ARC-SC yields a statistically supported improvement in first-hit discovery and remains competitive with directionally favorable first-hit performance on more challenging design space. These results establish ARC-SC as a POF-anchored, scenario-aware batch strategy for improving early valid-target discovery under structured experimental failure.

math.OC↗
arXiv2026

TIEM: Temporal Integration of Hypergraph Evidence and Skill Memory for Event-Driven Financial Forecasting

Event-driven catalyst-outcome forecasting increasingly uses retrieval- and memory-augmented large language model agents for prediction. However, training-data contamination and temporal leakage can create an Evidence Chasm between reported accuracy and true predictive ability. We propose TIEM, a timestamp-gated framework with three coordinated components: an Event-Evidence Hypergraph (EEH) for timestamp-filtered multi-tier retrieval; a Case-based Skill Memory (CSM) for source-tagged temporal skills; and Heterogeneous Evidence-Experience Fusion Reasoning (HEFR) for evidence-experience fusion and prediction. We also introduce FinPURE, a recent-period A-share holdout benchmark, and use a Name-Date Probe to assess per-model name-date sensitivity rather than assuming training cutoffs. Results on five financial forecasting benchmarks show TIEM outperforms current baselines. Our project is available at https://github.com/QwenQKing/Fin_TIEM.

cs.CE↗
arXiv2026

StrataCL: Fabric-Native Communication Library for Production Supernodes

Modern distributed AI workloads run across hundreds of accelerators, making communication a major bottleneck. Existing communication libraries remain largely buffer-centric because user and communication buffers are managed separately, causing redundant data copies or costly user-buffer registration. This paper presents StrataCL, a zero-redundancy and fabric-native communication library for production supernodes. StrataCL introduces registration-on-allocation to realize user-buffer direct communication, and designs communication operators with workload-balanced NPU-core partitioning and NPU-driven SDMA offloading to exploit supernode architecture features. On the Huawei CloudMatrix384, StrataCL improves collective bus bandwidth by up to 1.6x and improves MoE dispatch/combine bus bandwidth by up to 1.4x. Across three production workloads, StrataCL improves LLM inference throughput by 1.9x, reduces P99 TTFT by 2.2x, and reduces LLM and Recsys training iteration time by 1.4x and 1.3x, respectively.

cs.DC↗
arXiv2026

Decode-Time Grammars: Constrained LLM Generation over a Refinement Order of Grammar Fragments

Large language models now write a growing share of the world's code, increasingly inside agents and serving systems that compile, execute, or dispatch generated code without line-by-line review. This works well for mainstream languages but remains brittle for low-resource programming surfaces such as domain-specific languages, custom library APIs, and command-line tools. Even under grammar-constrained decoding, a model can still produce references invalid in the current environment: a buffer never declared, a column absent from the schema, a function the library does not provide, or an unsupported CLI option. This paper introduces decode-time grammars: grammar fragments instantiated during generation from a runtime environment Gamma. A region-specific policy selects a fragment for each hole, and a tightening operator replaces open reference positions with Gamma-typed slots whose candidates are exactly the names, fields, APIs, or options available at that point. Newly generated declarations enter Gamma before later regions are decoded, so the constraining grammar can depend on the prefix already generated. This ensures not only grammatical correctness but also semantic correctness, by preventing references to undefined symbols. We formalize grammar fragments as environment-indexed grammars ordered by refinement, prove No-Ghost soundness for Gamma-slotted fragments, show that refinement preserves this support-set guarantee, and characterize the boundary of mask-enforceable properties. We implement the approach in gproj with offline grammar induction and online policy resolution. Across TileLang, SQL, and P4, with models from 0.6B to 236B parameters, gproj eliminates ghost references by construction at moderate overhead over standard constrained decoding.

cs.PL↗
arXiv2026

AnyDexRT: Calibration-Free Dexterous Hand Retargeting with Few-Shot Human Guidance

Teleoperation is a key interface for controlling dexterous robotic hands and collecting demonstrations for imitation learning. Its effectiveness largely depends on kinematic retargeting, which maps operator hand motions to feasible and intuitive robot hand motions. Existing methods often require hand-crafted objectives, precise calibration, or global shape matching between human and robot hand spaces, making them sensitive to hand-specific tuning and less reliable across different dexterous hands. We propose AnyDexRT, a calibration-free retargeting method for intuitive dexterous teleoperation across human-like dexterous hands. AnyDexRT combines self-supervised fingertip correspondence learning with few-shot human guidance to anchor the mapping in task-relevant regions, and further refines pinch-related poses using a contact classifier. Experiments on diverse dexterous hands and real-world teleoperation tasks show that AnyDexRT improves retargeting quality, reduces manual tuning, and provides more intuitive and efficient control than prior retargeting methods. Project website: https://chenxi-wang.github.io/projects/anydexrt

cs.RO↗
arXiv2026

Direct observation of interfacial exchange coupling in a magnetic tunnel junction through spin-polarized quasiparticle interference

Interfacial exchange coupling plays a critical role in enabling novel phenomena in magnetic heterostructures, such as spin triplet superconductivity, quantum anomalous Hall effect (QAHE), and advanced spintronic functionalities. While microscopic characterization of this coupling is essential for elucidating the underlying mechanism, it remains technically challenging. Here, using spin-polarized scanning tunneling microscopy (SP-STM) and quasiparticle interference, we directly observed interfacial exchange coupling in a magnetic tunnel junction formed by an Fe coated tip and a Cr(001) surface. We found the ferromagnetic tip induces significant energy shift (up to 10 meV) in the spin-polarized surface state of Cr(001). This shift is highly sensitive to the tip-surface distance and the spin-alignment between Fe tip and Cr surface, which can be switched by external magnetic field. Our results demonstrate that extended 2D surface states can mediate strong exchange coupling across a heterojunction, enabling local control of interfacial exchange interaction induced phenomena.

cond-mat.mes-hall↗
arXiv2026

Demystifying Numerical Instability in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL

As Large Language Models (LLMs) deploy into mission-critical domains (e.g., finance, medicine, and law), output reproducibility has become a strict system requirement. While practitioners use greedy decoding to eliminate algorithmic stochasticity, empirical deployments with 16-bit precisions still exhibit catastrophic output divergence across heterogeneous GPUs. Through SASS-level profiling, we reveal that this inconsistency is fundamentally driven by truncation errors introduced during downcasting at kernel boundaries. However, achieving reproducibility via a global FP32 pipeline incurs prohibitive system penalties: bypassing 16-bit hardware accelerators hurts compute efficiency, while upcasting the KV cache doubles memory overhead. To bridge this gap, we propose Hybrid Error ALleviation (HEAL), a targeted intervention that approximates FP32 precision while resolving hardware constraints through two targeted mechanisms. First, recognizing that floating-point formats underutilize their bit-width for Q, K, V tensors, HEAL applies INT16 quantization that preserves numerical stability without expanding the KV cache footprint. Second, HEAL synthesizes high-precision matrix multiplications via an algebraic error compensation strategy, executing entirely on high-throughput 16-bit Tensor Cores. To evaluate our approach practically, we introduce MCR-Bench, a benchmark targeting reproducibility in mission-critical tasks. HEAL achieves the same level of reproducibility on downstream tasks as the FP32 baseline while reducing the performance overhead by up to 7.1x.

cs.LG↗
arXiv2026

XAI-Grounded Explanation Generation for Speech Deepfake Detection with Training-Free Multimodal Large Language Models

Speech deepfake detection (SDD) systems require trustworthy explanations for reliable decision-making. Existing explanation ways mainly fall into two categories. Traditional explainable AI (XAI), such as gradient-based attribution, produces low-level attribution signals tightly coupled with model decisions, and harder to be understood by human than natural language explanations. Meanwhile, large language model (LLM)-based explanation generation often produces generic and ungrounded descriptions due to the lack of heuristic evidence and task-specific supervision, stemming from limited grounded explanation datasets for SDD. We therefore propose a training-free explanation framework that integrates XAI evidence with multimodal LLMs to generate grounded and specific explanations. Using the PartialSpoof dataset, we construct a grounded explanation dataset and show that methods with XAI increase inside accuracy by over 45\%, verified through human evaluation and faithfulness checks.

cs.CL↗
arXiv2026

SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories

Large language model (LLM) agents increasingly rely on reusable external skills to solve long-horizon interactive tasks. Existing training-free skill adaptation pipelines usually update skills from full trajectories or session-level feedback, which makes failure attribution coarse and often produces unstable or overly broad revisions. We propose SkillAdaptor, a training-free step-level skill adaptation framework with explicit failure attribution, and it can plug into OpenClaw-class agent harnesses. Given a failed trajectory, SkillAdaptor identifies a first actionable fault step, links responsibility to candidate skills, and applies targeted updates under explicit acceptance checks while keeping the backbone frozen. We evaluate on WebShop, PinchBench, and Claw-Eval with Kimi-K2.5, GLM-5, and GPT-5.2. SkillAdaptor improves over no-skill and skill-adaptation baselines on all three suites, with the largest single-metric improvements of +1.5 points on PinchBench Avg Score%, +1.8 on Claw-Eval Avg Score, and +1.7 on WebShop success rate. These results indicate that step-level attribution supports more stable and auditable training-free skill maintenance\footnote{The code will be released at https://github.com/zjunlp/SkillAdaptor.}.

cs.CL↗
arXiv2026

Understanding the Rising Human-AI Affective Bonding: Conceptualization and HAABI Scale Development

As conversational AI becomes capable of sustained, affectively responsive interaction, users may form bonds beyond instrumental use. Existing measures often adapt interpersonal frameworks or focus on specific relational outcomes, leaving limited tools for assessing human-AI affective bonding on its own terms. Across two studies, we developed and validated the Human-AI Affective Bonding Inventory (HAABI). Study 1 used thematic analysis of semi-structured interviews with 52 emotionally engaged conversational AI users to identify cognitive, emotional, and behavioral features of bonding. Study 2 translated these insights into a self-report inventory and validated it among 673 Chinese conversational AI users. Exploratory and confirmatory factor analyses supported a 20-item, four-factor structure: emotional realism, separation anxiety, emotional investment, and romantic intimacy. The HAABI showed good reliability, construct validity, and known-groups validity. The scale therefore provides a neutral, user-centered tool for studying how affective bonds with conversational AI are formed, experienced, and related to users' psychological outcomes.

cs.HC↗
arXiv2026

A Multi-AI-agent Framework Enabling End-to-end Finite Element Analysis for Solid Mechanics Problems

Finite element analysis (FEA) is the most important numerical approach for solid mechanics. Challenges of FEA include a steep learning curve for entry-level users and potential false simulations due to incorrect definitions of key simulation components, such as boundary conditions, load cases, and solution variables. Years of engineering experience are usually necessary for real-world problem-solving. To address these issues, we present AbaqusAgent, a multi-agent framework grounded in large language models (LLMs) for solid mechanics analyses. AbaqusAgent is developed to facilitate analysis case generation and execution using Abaqus, one of the most widely used FEA packages, by turning users' natural-language instructions into executed FEA analyses and result visualization. AbaqusAgent is composed of six agents, including interpreter, architect, input writer, runner, reviewer, and visualizer agents, encompassing all the essential pre-processing and post-processing steps of standard FEA analyses. A wide variety of 50 solid mechanics problems have been successfully validated, achieving an overall success rate of 86%. Beyond improving the efficiency of FEA for solid mechanics problems and lowering the barrier to computational mechanics education, AbaqusAgent advances the human-simulation interaction paradigm and enables integration with AI-empowered optimization and material characterization workflows. The code is available at https://github.com/LIRAM-LIN/AbaqusAgent

cs.AI↗
arXiv2026

Out of Sight, Not Out of Mind: Unveiling Latent Attack in Latent-based Multi-Agent Systems

Latent-based multi-agent systems replace parts of explicit inter-agent communication with hidden representations, offering a new direction for efficient and flexible agent collaboration. However, moving coordination into latent space may also move attacks beyond the reach of visible-text inspection. In this paper, we study whether latent states can carry attack-associated information that remains effective during clean executions. To examine this question, we introduce a latent attack framework that reactivates attack-induced effects through latent interventions without reusing adversarial text. Extensive experiments show that the resulting latent attacks can substantially degrade task performance in clean executions, especially when applied to inter-agent KV-cache handoffs rather than local hidden states. Further control analyses indicate that this degradation cannot be reduced to arbitrary perturbations or invalid generation. Overall, our findings suggest that latent-based collaboration does not remove attack risk. It shifts part of the risk into less observable execution states, calling for safeguards beyond visible-text inspection.

cs.CR↗
arXiv2026

Inference of Component Effect on System Performance

In a computer system, multiple components--such as the CPU, memory, and others--work together as a system whose performance can be directly measured. However, the effect of a component under investigation (CUI), e.g., CPU, on system performance cannot be directly measured and can only be inferred. Accurately inferring CUI effect on system performance is a critical issue. Our experiments reveal that the general-purpose rigorous methodologies, like Design of Experiments (DoE), Randomized Controlled Trials (RCTs), and a single-purpose empirical methodology, like SPEC CPU2017, can not address this issue effectively and efficiently. We propose a rigorous methodology to address this issue: First, we identify a self-contained system (SCS) under the context of which we can completely understand how CUI and other essential components affect the system performance, and then we use a structural causal model methodology to represent and infer the causal effect of CUI on the system performance. We utilize this methodology and verify its correctness in the context of CPU design and evaluation. Through theoretical analysis and pioneering controlled experiments, we systematically compare our methodology against three established methodologies: SPEC CPU2017, DoE, and RCTs. The results show that our methodology can achieve its goal effectively and efficiently, whereas others exhibit inherent limitations.

cs.PF↗
arXiv2026

MatFormBench: A Benchmarking Evaluation Framework for Target-Driven Materials Formulation

Inverse design of materials has significantly advanced target-driven formulation optimization, yet existing materials machine learning benchmarks remain limited to forward property prediction, failing to systematically evaluate inverse optimization and generation algorithms, a critical gap that hinders the progress of target-driven materials design. To address this limitation, we propose MatFormBench, a novel benchmarking ecosystem tailored to evaluate and guide generative strategies for target-driven formulation. MatFormBench integrates a physics-driven formulation generation scheme to generate synthetic samples that faithfully emulate realistic materials structure-property response relationships, complemented by five escalating difficulty levels to quantify the complexity of these relationships. To rigorously assess algorithm performance, we further propose MatFormScore, a multi-dimensional metric that comprehensively quantifies performance across five critical axes: target success, search efficiency, exploratory capacity, robustness, and stability. We validate MatFormBench by evaluating 39 diverse inverse design algorithms, covering classical surrogate-assisted black-box search, state-of-the-art deep generative models, and increasingly popular Large Language Model (LLM)-based recommendation strategies. Across 1170 standardized algorithm-task evaluations, diffusion-based models demonstrate the strongest overall performance, while Variational Autoencoder (VAE)-based and Genetic Algorithm (GA)-based methods exhibit distinct advantages in specific scenarios. By establishing a unified evaluation standard for target-driven materials formulation, MatFormBench enables reproducible benchmarking, principled algorithm comparison, and diagnostic analysis of inverse design strategies, providing a foundational tool for advancing materials inverse design.

cond-mat.mtrl-sci↗
arXiv2026

GenTS: A Comprehensive Benchmark Library for Generative Time Series Models

Generative models have demonstrated remarkable potential in time series analysis tasks, like synthesis, forecasting, imputation, etc. However, offering limited coverage for generative models, existing time series libraries are mainly engineered for discriminative models, with standardized workflows for specific tasks, such as optimizing Mean Squared Errors for time series forecasting. This rigid structure is fundamentally incompatible with the distinct and often complex paradigms of generative models (e.g., adversarial training, diffusion processes), which learn the underlying data distribution rather than a direct input-output mapping. To this end, we proposed GenTS, a comprehensive and extensible benchmark library designed for systematic assessment on generative time series models. GenTS features a unified data preprocessing pipeline, a collection of versatile models, and panoramic evaluation metrics. Its modular design also enables the researchers to flexibly customize beyond our built-in datasets and models. Based on GenTS, we conducted benchmarking experiments under diverse tasks, accordingly offering suggestions for model selection and identifying potential directions for future research. Our codes are open-source at https://github.com/WillWang1113/GenTS. The official tutorials and document are available at https://willwang1113.github.io/GenTS/.

cs.LG↗
arXiv2026

The Cylindrical Representation Hypothesis for Language Model Steering

Steering is a widely used technique for controlling large language models, yet its effects are often unstable and hard to predict. Existing theoretical accounts are largely based on the Linear Representation Hypothesis (LRH). While LRH assumes that concepts can be orthogonalized for lossless control, this idealized mapping fails in real representations and cannot account for the observed unpredictability of steering. By relaxing LRH's orthogonality assumption while preserving linear representations, we show that overlapping concept contributions naturally yield a sample-specific axis-orthogonal structure. We formalize this as the Cylindrical Representation Hypothesis (CRH). In CRH, a central axis captures the main difference between concept absence and presence and drives concept generation. A surrounding normal plane controls steering sensitivity by determining how easily the axis can activate the target concept. Within this plane, only specific sensitive sectors strongly facilitate concept activation, while other sectors can suppress or delay it. While the surrounding normal plane can be reliably identified from difference vectors, the sensitive sector cannot, introducing intrinsic uncertainty at the sector level. This uncertainty provides a principled explanation for why steering outcomes often fluctuate even when using well-aligned directions. Our experiments verify the existence of the cylindrical structure and demonstrate that CRH provides a valid and practical way to interpret model steering behavior in real settings: https://github.com/mbzuai-nlp/CRH.

cs.CL↗
arXiv2026

CombinationTS: A Modular Framework for Understanding Time-Series Forecasting Models

Recent progress in time-series forecasting has led to rapidly increasing architectural complexity, yet many reported State-of-the-Art gains are statistically fragile or misattributed. We argue that progress requires a shift from model selection to modular attribution, identifying which components truly drive performance. We propose CombinationTS, a self-contained probabilistic evaluation framework that decomposes forecasting models into orthogonal modules--Input Transformation, Embedding, Encoder, Decoder, and Output Transformation--and evaluates them under a shared evaluation condition space. By quantifying each component via marginalized performance ($\mu$) and stability ($\sigma$), CombinationTS enables robust attribution beyond fragile point estimates. Through large-scale paired evaluation, we uncover the Identity Paradox: once the data view (Embedding) is well-designed, a parameter-free Identity Encoder often matches or outperforms complex backbones. We further show that explicit structural priors introduced via Input Transformations yield a more favorable performance-stability trade-off than increasing Encoder complexity, establishing a principled baseline for architectural necessity.

cs.LG↗