Searcharxiv⌕ Search

arXiv subjects

Jiayu Wang

Publications and source records attributed to Jiayu Wang.

At least 19 recordsLinked to original sources
arXiv2026

Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation

Benchmark researchers and developers of large language models (LLMs) and other AI systems need to find relevant evaluations, locate their benchmark datasets and code, and understand the settings behind reported scores. We present Benchmark Radar, a living database and search engine for retrieval and discovery of AI benchmarks, covering LLM evaluation, agentic and tool-use benchmarks, coding, reasoning, safety, and domain-specific evaluations. The system combines daily discovery of benchmark papers, repositories, datasets, and releases with a searchable benchmark catalog, mentions in model cards and technical reports, and score histories. It retains source identities and citations so readers can inspect candidate benchmarks and their evaluation evidence. Daily discovery draws on 37 sources: 13 direct connectors and 24 first-party research and engineering feeds. The catalog contains 1,283 source records drawn from 4 benchmark catalogs and 12,916 numeric observations on 790 records. We describe collection and retrieval, audit the full catalog, and examine benchmark saturation, adoption trends, and the limits of score comparisons. A worked example walks through a complete prior-art search, showing how to query the catalog and inspect benchmark evidence when designing a new evaluation. We release the web dashboard with a benchmark leaderboard, a Pareto frontier view of score against measured use, saturation and trend views, daily feeds, downloadable evidence, a command-line interface (CLI) for offline queries, and reproducible analysis.

cs.AI↗
arXiv2026

Learning Faithful Reasoning Processes with Spatio-Temporal Latent Dynamics for Large Language Models

Chain-of-Thought (CoT) reasoning has significantly enhanced the reasoning capabilities of large language models (LLMs). However, existing reinforcement learning methods primarily optimize outcome-level rewards, providing limited supervision over the reasoning process. As a result, models may produce shortcut-prone or unstable reasoning trajectories even when the final answer is correct. We propose GeoFaith, a spatio-temporal latent dynamics framework for learning faithful reasoning processes without process reward models. GeoFaith combines final-state latent uncertainty, which measures whether a completed trajectory lies in a well-supported manifold region, with predictive-entropy dynamics, which penalize abnormal uncertainty patterns such as premature collapse, oscillation, and prolonged uncertainty. These signals are incorporated as process regularization into GRPO, jointly optimizing answer correctness and reasoning quality without step-level process annotations. Experiments show that GeoFaith consistently improves reasoning accuracy, produces more efficient reasoning trajectories, and outperforms both outcome-only reinforcement learning and process-supervision baselines.

cs.CL↗
arXiv2026

MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control

A cover song re-renders an existing piece, most commonly by preserving its tonal content -- melody and chord progression -- while reshaping other musical attributes. This suggests a natural formulation for generative cover synthesis with pretrained music language models: explicitly control tonal content, while specifying lyrics and style through text. Existing approaches condition on frame-level features, tightly coupling generation to the reference's timing and structure, and limiting flexibility such as tempo variation, structural rearrangement, or partial conditioning. To this end, we present MuLaCover, a cover generation model that conditions a pretrained text-to-song foundation model on an editable symbolic lead sheet. Our design enables alignment-free control: generated outputs preserve the tonal signature of the source without frame-level alignment, allowing flexible timing, structure, and segment-level generation. We further introduce a training curriculum with partially mismatched audio-symbolic pairs, improving diversity and robustness. We evaluate MuLaCover with objective metrics, standard subjective ratings, and in-depth expert interviews that provide fine-grained diagnostic insights. Experiments show that MuLaCover achieves state-of-the-art performance among open-source systems and is competitive with leading commercial models such as Suno-v5.5. Audio samples and code are available at our project page: https://mulalabs.ai/mulacover/

cs.SD↗
arXiv2026

Why Do Agent Teams Fail Across Boundaries? A Failure Taxonomy for Agent-to-Agent Systems with Private States

Agents are increasingly interacting with other agents that act for different principals (people or organizations on whose behalf they work), such as a buyer's personal agent negotiating with an enterprise's seller agent. In such agent-to-agent (A2A) scenarios, each agent has its own environment and holds information and authority that the other cannot see. Moreover, the interests of each agent may be aligned (cooperative), partly aligned (mixed-motive), or opposed (competitive). Existing multi-agent system failure studies assume one orchestrator, shared workspace, or single principal. We ask how A2A systems fail when these assumptions are removed. We study more than 2,500 recorded runs of A2A systems built from different agent harnesses and models, spanning 488 scenarios across eight families (legal, CRM, security, commerce, etc.). From these traces, we derive $A^2$-Failures, a taxonomy of 20 A2A failure modes in four categories: (i) discovery and delegation, (ii) grounding and record consistency, (iii) verification, and (iv) conduct and fidelity. Three findings hold across every harness, model, and scenario studied: (1) discovery and interaction are driven by the phrasing of the task rather than the availability of peer agents; (2) no agent verifies a peer's factual claim on its own initiative, so an A2A system inherits the reliability of its least reliable participant unless the protocol or mechanism performs the check; and (3) the aggregate outcome score credits the agent completing the task while staying blind to the coordination, verification, and conduct failures beneath it, so A2A systems must be evaluated per agent, against each agent's own principal. We release the run logs behind the taxonomy at https://huggingface.co/datasets/a2a-salesforce/a2-failures.

cs.MA↗
arXiv2026

ReTrace: Cross-Stage Failure Attribution for Self-Improving Robotic Manipulation

General-purpose multimodal foundation models are increasingly capable of directly controlling robots, yet improving their manipulation capabilities through autonomous interaction remains challenging. A key challenge to such self-improvement is learning from failures in complex manipulation tasks involving cross-stage dependencies, where an action may succeed locally but cause a later stage to fail. To address this challenge, we introduce ReTrace, a self-improvement framework for robotic manipulation through autonomous physical interaction and retrospective reasoning, without provided demonstrations or model-parameter updates. ReTrace retrospectively traces downstream failures to earlier decisions, proposes targeted corrections, and evaluates them through subsequent interactions. Across attempts, ReTrace progressively consolidates validated corrections into a reusable manipulation skill that guide subsequent execution. We evaluate ReTrace on four real-world manipulation tasks using a Franka Research 3 robot. On the two tasks with strong cross-stage dependencies, GPT-6 Astra-low improves from 0% to 80% success on plug insertion and from 0% to 100% on ball pouring, while GPT-6 Sol-xhigh improves from 0% to 10% and 0% to 90%, respectively. The learned skills also transfer across model and reasoning configurations and reduce inference-time decision cost in most evaluated settings.

cs.RO↗
arXiv2026

SpatialHarness: Test-Time Spatial Scaffolding for Fine Robotic Manipulation

Frontier multimodal foundation models (e.g., GPT-6 Astra) have recently shown strong potential for direct robotic control, yet their performance on fine manipulation remains limited. We argue that an important source of failure is not necessarily insufficient policy capability, but insufficient spatial observability, where task-critical spatial relationships may be poorly revealed by the existing physical camera setup. We introduce SpatialHarness, a test-time embodied harness that provides test-time spatial scaffolding for fine robotic manipulation without policy fine-tuning or changes to the physical sensing setup. SpatialHarness maintains an online simulated scene synchronized with real-world execution, identifies task-critical spatial relationships, and renders complementary virtual views that expose them to a frozen multimodal policy. To keep the simulated scene aligned during interaction, we develop interaction-aware scene synchronization that distinguishes static, held, and transition modes. We evaluate SpatialHarness on four real-robot manipulation tasks spanning precise geometric alignment, object-relative placement, and articulated-object interaction. Using the same frozen GPT-6 Astra policy, SpatialHarness substantially improves task success, including from 26.7% to 66.7% on plug insertion and from 0% to 100% on Tower of Hanoi. These results indicate that improving spatial observability at test time can unlock fine-manipulation capabilities already present in strong multimodal foundation models. Project website: https://emilia113.github.io/SpatialHarness/.

cs.RO↗
arXiv2026

When Integral Meets Decomposition: A Signal-Level Self-Supervised Feature Decompose Paradigm for Multi-Modal Image Fusion

Multimodal image fusion (MMIF) aims to integrate complementary information from different modalities into a high-quality fused image and support downstream tasks. Recently, feature decomposition has become an important paradigm by separating source images into common and modality-specific unique features. However, existing methods lack clear supervision because ground-truth (GT) decomposition feature maps are unavailable. They usually combine multiple image-level metrics as losses, which are inherently incomplete and may conflict since each pixel couples attributes such as texture, edge, and contour. To address this, we propose a 1D signal-level self-supervised feature decomposition paradigm. Our core insight is to reformulate feature decomposition from unclear 2D image-level supervision into an integral-driven 1D signal-level optimization problem. This objective-level reformulation uses the 1D signal form to compute the integral constraint. The decomposer is optimized by the integral area between common and original signals, enabling more stable optimization with a clear optimization objective. Our model follows a two-stage SSL framework. Stage I designs dual pretext tasks for integral-driven decomposition at the signal level and structure-preserving reconstruction at the image level. Stage II fuses unique features and combines them with common features to reconstruct the fused image. Experiments on representative MMIF tasks show state-of-the-art (SOTA) performance. Code: github.com/Wangjiayu0512/SIDFusion.

cs.CV↗
arXiv2026

EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?

Modern LLM-based agents operate through a harness of tools, reusable skills, and specialist agents that shapes what they observe and what they can do. In practice, this harness continually evolves as new capabilities are added. We introduce EvoHarnessBench, a benchmark for evaluating agents under controlled harness evolution across three axes (tools, skills, and agents). Unlike existing continual-learning benchmarks for agents, which typically place non-stationarity (i.e., what changes over time) in the task stream while keeping the harness fixed, EvoHarnessBench places non-stationarity in the externally supplied harness itself. It contains 17 multi-stage harness streams constructed deterministically from verifier-based benchmarks, comprising 802 tasks, 520 tools, 42 skills, and 62 agents. We evaluate two complementary settings corresponding to the central challenges of harness evolution: deployment evaluation, which isolates retention of previously accessible competence as the harness expands, and self-evolving adaptation evaluation, which tests whether accumulated experience remains useful as new capabilities are introduced. Our results reveal three persistent gaps. First, harness expansion alone can degrade performance on previously solved tasks, producing harness-induced forgetting. Second, gains from self-evolving adaptation remain inconsistent across stages of harness evolution, capability axes, and environments. Third, retention and adaptation can pull in different directions: preserving earlier competence does not necessarily improve adaptation to newly introduced capabilities, and vice versa. These results establish harness evolution as a distinct challenge for building agents that can keep pace with an evolving harness while preserving previously effective behavior.

cs.MA↗
arXiv2026

MoWAM: Explicit Future Motion Prediction for Efficient World Action Models

World Action Models (WAMs) improve robot policy learning by incorporating future dynamics, yet explicitly generating future videos at inference introduces substantial computational overhead. Removing future generation improves efficiency, but leaves future dynamics only implicitly encoded in observation features, which can limit robustness under distribution shifts. We propose MoWAM, an efficient WAM that replaces future video generation with explicit future motion prediction. Instead of reconstructing the complete future scene, MoWAM models structured robot motion as a compact abstraction of the future, capturing how the robot is expected to evolve under the current scene and interaction constraints. A Mixture-of-Transformer architecture learns future visual dynamics during training while jointly predicting motion and action, allowing video generation to be removed entirely at inference while retaining an explicit representation of the future. The compact motion representation further enables efficient inference-time scaling by sampling multiple candidates of motion and action pairs and selecting among them with a motion-aware task-progress verifier. Experiments on LIBERO, LIBERO-Plus, and real-world manipulation tasks demonstrate that MoWAM achieves strong in-distribution performance, improved out-of-distribution robustness, and higher average real-world success than representative WAM baselines. In addition, performance improves as more candidates are explored, demonstrating that explicit future motion provides an effective and efficient basis for inference-time scaling.

cs.RO↗
arXiv2026

Grammar-Aligned Decoding

Large Language Models (LLMs) struggle with reliably generating highly structured outputs, such as program code, mathematical formulas, or well-formed markup. Constrained decoding approaches mitigate this problem by greedily restricting what tokens an LLM can output at each step to guarantee that the output matches a given constraint. Specifically, in grammar-constrained decoding (GCD), the LLM's output must follow a given grammar. In this paper, we demonstrate that GCD techniques (and in general constrained decoding techniques) can distort the LLM's distribution, leading to outputs that are grammatical but appear with likelihoods that are not proportional to the ones given by the LLM, and so ultimately are low-quality. We call the problem of aligning sampling with a grammar constraint, grammar-aligned decoding (GAD), and propose adaptive sampling with approximate expected futures (ASAp), a decoding algorithm that guarantees the output to be grammatical while provably producing outputs that match the conditional probability of the LLM's distribution conditioned on the given grammar constraint. Our algorithm uses prior sample outputs to soundly overapproximate the future grammaticality of different output prefixes. Our evaluation on code generation and structured NLP tasks shows how ASAp often produces outputs with higher likelihood (according to the LLM's distribution) than existing GCD techniques, while still enforcing the desired grammatical constraints.

cs.AI↗
arXiv2026

RoboTrustBench: Benchmarking the Trustworthiness of Video World Models for Robotic Manipulation

Video world models are increasingly used in robotic manipulation, yet existing benchmarks mostly evaluate them under valid, feasible, and safe instructions. We introduce RoboTrustBench, a benchmark for evaluating the trustworthiness of video world models under four scenarios: Normal, Constraint-Sensitive, Counterfactual, and Adversarial. Built from real-world DROID episodes, RoboTrustBench contains 1,207 expert-validated instruction-image pairs and a six-dimensional evaluation protocol with 13 fine-grained criteria. Evaluating seven representative video world models with human and MLLM assessment, we find that current models often generate visually coherent videos, but struggle with constraint reasoning, counterfactual grounding, physical interaction, and unsafe-instruction suppression. These results show that visual quality and surface-level instruction following are insufficient for trustworthy robotic video world modeling.

cs.CV↗
arXiv2026

Giant-exchange-driven Vectorial Control of a Minimal Topological Magnet in Eu3In2As4

The interplay between magnetism and band topology provides a route to controlling quantum states of matter, yet its realization in materials is often constrained by weak exchange coupling and complex electronic structures. Here, a giant exchange coupling is identified in the newly predicted topological magnet Eu3In2As4, giving rise to magnetization-dependent band shifts of up to 300 meV. Together with its intrinsically soft magnetic response, this strong cou-pling enables systematic tuning of topological phases by both the magnitude and orientation of applied magnetic fields. The magneto-topological phase diagram is mapped out in which an antiferromagnetic topological insulator ground state evolves, under modest fields, into a pro-posed intermediate 2/3-ferrimagnetic phase, and further into fully polarized ferromagnetic states predicted to host either Weyl or nodal-ring semimetals. Notably, the Weyl phase corresponds to a minimal model hosting a single pair of Weyl nodes. Quantum oscillations, anomalous Hall transport and magneto-infrared spectroscopy consistently reveal exchange-driven band recon-struction across these transitions. Rotation of the magnetization theoretically provides an effi-cient means to tune the momentum-space positions and separations of the Weyl nodes. These results establish Eu3In2As4 as a model system for exploring how strong exchange coupling can be used to control topological band structures with minimal complexity.

cond-mat.mtrl-sci↗
arXiv2026

From Synthetic to Real: Toward Identity-Consistent Makeup Transfer with Synthetic and Real Data

Makeup transfer aims to apply the makeup style of a reference portrait to a source portrait while preserving identity and background. Early methods formulate this task as unsupervised image-to-image translation, relying on surrogate objectives and often yielding limited performance. Recent diffusion- and flow-based approaches instead exploit synthetic data for supervised training, leading to significant improvements. However, these methods still face two critical challenges: synthetic supervision frequently fails to faithfully preserve identity, and the domain gap between synthetic and real data limits generalization, resulting in degraded performance in complex real-world scenarios. To address these issues, this paper first proposes ConsistentBeauty, a novel data curation pipeline that ensures makeup fidelity and strict identity consistency within the synthesized data. Second, we propose RealBeauty, a synthetic-to-real post-training framework. Beyond supervised learning on curated synthetic data, we further adapt the model to real-world scenarios through reinforcement learning and design novel verifiable rewards tailored to the makeup transfer task. It allows the model to further benefit from real makeup patterns beyond synthetic supervision. In addition, we establish a new diverse benchmark for makeup transfer, covering a wide range of skin tones, ages, genders, poses, and makeup styles, thereby enabling a more comprehensive evaluation of model performance under diverse real-world conditions. Extensive experiments show that our method achieves state-of-the-art performance on multiple benchmarks and demonstrates clear advantages in identity preservation and performance on complex real-world cases.

cs.CV↗
arXiv2026

Bgolearn: a Unified Bayesian Optimization Framework for Accelerating Materials Discovery

Efficient exploration of vast compositional and processing spaces remains a major challenge in accelerated materials discovery. Bayesian optimization (BO) provides a principled approach to identify optimal materials with minimal experimentation, but its adoption has been limited by implementation complexity and a lack of domain-specific tools. Here, we present Bgolearn, a versatile Python framework that brings BO to materials research through intuitive interfaces, robust algorithms, and materials-focused workflows. Bgolearn supports single- and multi-objective optimization, multiple acquisition strategies, diverse surrogate models, and uncertainty quantification, enabling effective navigation of complex design spaces. Benchmark studies show that Bgolearn reduces experimental effort by 40-60\% compared with random search, grid search, and genetic algorithms, while achieving comparable or superior solution quality. Its effectiveness is demonstrated across case studies, including the discovery of maximum-elastic-modulus triply periodic minimal surface structures, ultra-high-hardness high-entropy alloys, and high-strength, high-ductility medium-Mn steels, and is further supported by numerous publications. With a modular architecture that integrates seamlessly into existing materials workflows and a graphical interface (BgoFace) that removes programming barriers, Bgolearn establishes a practical, reliable platform for Bayesian optimization in materials science. The software is openly available at https://github.com/Bin-Cao/Bgolearn.

cond-mat.mtrl-sci↗
arXiv2026

A Good Initialization is All You Need for Faithful Visual Attribution

Faithful visual attribution identifies which image regions support a model prediction. Search-based perturbation methods lead the insertion--deletion faithfulness frontier by masking regions and measuring score changes, but they usually output a complete ordering of all regions. Many applications, especially MLLM attribution and repair, only need a compact top-\(k\) evidence mask. We study this mask-first attribution problem. An exactly \(k\)-region mask is combinatorial: useful evidence can depend on interactions among fine regions. Coarse grouping can stabilize early search but aggregates redundant content, whereas one-step scoring can miss high-value combinations. We introduce two forward-only methods. \textsc{CoPAIR} uses a PhaseWin--Greedy gap diagnosis to construct coarse singleton/pair candidates that warm-start full-ordering search. \textsc{TRACE} directly searches fixed-cardinality fine-region masks with cross-entropy sampling, elite retention, and distribution updates, with a finite-budget recovery analysis. The resulting evidence set can be returned as a compact attribution mask or used to initialize Greedy or PhaseWin when a complete ranking is required. Across ImageNet classification with CLIP ViT-L/14, CLIP RN101, and ResNet-101, our initialized search methods establish a new state-of-the-art frontier for faithful full-ordering attribution under inclusive forward-call accounting. On POPE and RePOPE with Qwen2.5-VL-3B-Instruct and LLaVA-v1.5-7B, \textsc{TRACE}+Greedy gives the strongest search-based MLLM attribution results. Direct \textsc{TRACE} masks further achieve single-point RePOPE repair rates of \(94.44\%\) and \(96.00\%\), showing that compact evidence masks can be actionable attribution outputs, not merely prefixes of full rankings.

cs.CV↗
arXiv2026

Giant and Broadband Circular Dichroism from Particle-Hole Symmetry Breaking in Weyl Semimetals

Circular dichroism originates from symmetry breaking of material structure, leading to differential absorption of left- and right-circularly polarized light. However, circular dichroism in most materials is inherently weak and spectrally narrow, especially in the mid-to-far infrared. Here, we uncover giant infrared circular dichroism in the magnetic-field-forced Weyl semimetal Mn(Bi,Sb)2Te4, driven by extreme particle-hole symmetry breaking. Helicity-resolved magneto-infrared spectroscopy reveals circular dichroism exceeding 3000 mdeg (~130 mdeg/nm) with above-degree response extending over the 6-13 μm spectral range. The optical resonances are enhanced by a strong band nesting effect intrinsic to the Landau levels of type-II Weyl dispersion. A symmetry-based kp model reproduces these magneto-infrared responses and demonstrates that magnetization-induced asymmetric spin-orbit coupling generates particle-hole symmetry breaking, suppressing spin-up, parity-even wavefunction components in the valence Landau band and thereby producing pronounced optical helicity selectivity. Our findings establish particle-hole symmetry breaking as an effective route toward helicity-resolved optical control in quantum materials.

cond-mat.mtrl-sci↗
arXiv2026

Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing

Instruction-based image editing has made notable progress with recent advances in generative models. However, the quality of the edited result is still influenced by the randomly sampled initial noise, particularly in complex editing scenarios. An unsuitable initial noise may lead to unsatisfactory editing results. Recent inference-time scaling methods address this issue by sampling multiple initial noises and selecting better candidates. Nevertheless, most of them follow a decode-then-verify scheme which introduces an efficiency-accuracy trade-off. When decoding is performed after limited inference steps, the decoded images often remain too noisy for reliable assessment, whereas sufficiently denoised images require much higher computational cost. To address this issue, we propose VeriLatent, a plug-and-play adaptive inference-time scaling framework with early-step latent verification for image editing. Specifically, we propose a novel verifier that scores each initial noise through a latent-space editing activation map at an early stage. It identifies promising candidates by assessing whether they can induce an effective edit in the correct region. This enables efficient early pruning without decoding latents into images. Building on this, we further develop an adaptive search strategy for inference-time scaling. It allocates inference budgets according to editing difficulty, thereby reducing the number of function evaluations (NFE). Extensive experiments on multiple benchmarks and different base models demonstrate that VeriLatent consistently improves both editing performance and inference-time scaling efficiency.

cs.CV↗
arXiv2026

Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle

As foundation models advance and agent scaffolding becomes increasingly sophisticated, agents have demonstrated remarkable proficiency in complex, long-horizon coding tasks and even autonomous experiment execution. Despite their evolution from research assistants into autonomous research agents, these systems still exhibit significant limitations in field sensitivity, research ethics, and nuanced scientific judgment. Consequently, frontier agents remain unable to fully replace human researchers. To bridge this gap, we conceptualize the AARR (Act As a Real Researcher) benchmark series. Unlike existing benchmarks that primarily assess macro-level execution capabilities, AARR focuses on whether agents can emulate the professionalism, thoroughness, and nuanced reasoning that characterize human researchers in granular research scenarios. In this work, we propose AARRI-Bench (Act As a Real Research Intern), the first benchmark in this series. We conduct extensive experiments across frontier models and agentic systems, revealing that even the best-performing configuration (Mini-SWE-Agent with Claude Opus 4.7) achieves only 68.3\% success rate, frequently overlooking subtle yet critical details that are obvious to real human researchers. Our results indicate that developing researcher-like AI requires further exploration of research behavior, rather than merely complex scaffolding. Our data is released at https://github.com/AARR-bench/AARRI-bench.

cs.AI↗