arXiv subjects

Wei Yang

Publications and source records attributed to Wei Yang.

At least 55 records · Page 3Linked to original sources

arXiv2026

NavArena: Automated Construction of Goal-Oriented Navigation Benchmarks from 3D Gaussian Splatting Reconstructions

Fixed 3D Gaussian Splatting (3DGS) reconstructions provide realistic novel views but lack the traversability constraints, valid goals, and closed-loop protocols required for navigation evaluation. We introduce NavArena, an automated framework that transforms fixed 3DGS reconstructions into benchmarks for goal-oriented visual navigation. NavArena integrates a frozen 3DGS model for egocentric RGB-D rendering, an occupancy costmap derived from Gaussian density and height statistics for reachability and collision queries, and semantic goal candidates lifted from multi-view open-vocabulary masks. These components support the automatic generation and unified closed-loop evaluation of goal-oriented navigation episodes. Across more than 2{,}000 scenes, NavArena generates 22.2 million expert trajectories. Spatial and semantic evaluations assess the derived navigation representations, while policy rollouts demonstrate the diagnostic value of the unified evaluation protocol. NavArena enables scalable and reproducible navigation evaluation on large-scale 3DGS reconstructions, and all benchmark-generation tools, evaluation protocols, and derived assets will be released publicly.

cs.RO↗

arXiv2026

Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge

Multi-agent systems (MAS) can substantially extend the reasoning capacity of large language models (LLMs). Most MAS frameworks aggregate agent outputs via simple majority voting, discarding the evidential structure of reasoning traces. Majority voting is brittle under confabulation consensus, where agents share correlated biases and converge on the same incorrect rationale. We introduce AgentAuditor, which moves beyond frequency-based aggregation by organizing agent traces into a Reasoning Tree that explicitly represents agreements and divergences in their reasoning. AgentAuditor resolves conflicts by comparing branch-level evidence at critical divergence points, turning global adjudication into efficient, localized verification. We further propose Anti-Consensus Preference Optimization (ACPO), which trains the adjudicator with evidence-verified preference supervision to reduce conformity to misleading majority cues. Across four MAS frameworks and multiple reasoning benchmarks, AgentAuditor consistently improves aggregation performance over majority voting, with gains of up to 5% absolute accuracy while remaining token-efficient.

cs.AI↗

arXiv2026

Pooling Mobility Obscures Epidemic Invasion Routes

Epidemic models often pool air travel, commuting, and other mobility layers into a single weighted network. Pooling keeps the total imported infections into a region but discards the transport mode and route that delivered them, the information a mode-specific intervention needs. We make this precise for directed multilayer flows with heavy-tailed variation. Pooling acts as an asymmetric filter. The magnitude of an extreme importation, its radial tail index, is an exact invariant of sampling and nonnegative aggregation, whereas its composition across layers and routes, the angular part, is reweighted by layer-specific sampling and can be irrecoverably merged. We give a necessary and sufficient condition for recovering route composition, attach a surveillance decision cost to the loss, and show that the first established route need not be the busiest. A controlled metapopulation study calibrates the cost, and two contrasting reconstructions show where it bites. In US pandemic influenza, air adds fitted information beyond commuting, and a layer-resolved ranking targets more air-import burden than a pooled one. In the early Italian COVID-19 wave, commuting improves onset reconstruction while air attribution stays unresolved. Pooling can therefore support total-importation surveillance but cannot in general identify the mode or route behind an importation.

math.ST↗

arXiv2026

Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation

Reinforcement learning in open-ended long-form generation is challenging because reliable reference answers and automatic metrics are often unavailable. Existing rubric-based methods typically rely on pointwise LLM-as-a-judge scoring, but absolute scores are difficult to calibrate across complex responses, may provide weak discrimination among same-query rollouts, and can become saturated during optimization. We propose Tournament-GRPO, a group-wise reward framework that converts rubric-guided LLM judgments into relative rewards through repeated multi-round tournaments among same-query rollouts. Tournament-GRPO compares candidates within groups, accumulates tournament outcomes, and normalizes them into group-wise rewards for GRPO training. Experiments on Deep Research Bench show that Tournament-GRPO consistently outperforms existing reward-design baselines, achieving a 4.52-point overall-score improvement over the strongest baseline. Further analyses show that tournament rewards provide a favorable effectiveness--efficiency trade-off and that tournament design affects training dynamics. These results suggest that rubric-guided tournament comparison provides an effective reward signal for reinforcement learning in open-ended long-form generation.

cs.CL↗

arXiv2026

Dual-Manifold Geometry Guided Representation Learning: Adaptive Coupling between Kernel and Data Spaces

Deep representation learning has primarily focused on how features evolve across network layers, while largely overlooking the structured geometry embedded in network parameters. We introduce a dual-manifold perspective in which each convolutional layer contains two coupled geometric spaces: a Kernel Manifold induced by convolutional filters and a Data Manifold characterized by intermediate feature representations. Because these manifolds share the same channel space, parameter geometry can provide complementary structural information to guide feature evolution. Based on this insight, we propose Kernel-Guided Feature Transform (KGFT), a lightweight module that derives a geometric guidance matrix from the kernel Gram matrix and uses it to transform the covariance structure of feature representations. Unlike conventional attention mechanisms that reweight feature responses, KGFT explicitly reshapes feature relationships by transferring geometric information from the kernel manifold to the data manifold. To accommodate network hierarchy, we further introduce Exploit and Explore modes with a depth-aware scheduling strategy and a learnable guidance strength that adaptively controls the contribution of geometric transformation. This design promotes geometric alignment in shallow layers while encouraging feature diversity in deeper layers, without imposing excessive constraints on representation learning. Theoretical analysis establishes the validity of the proposed transformation and characterizes its effect on feature covariance. Extensive experiments across CNN- and Transformer-based architectures, including ResNet, ViT, and LLaMA-7B, demonstrate consistent improvements on image classification and arithmetic reasoning tasks, validating the generality and effectiveness of kernel-guided dual-manifold representation learning. Code will be publicly available.

cs.CV↗

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

UniMoFlow: Grounding Instruction-Driven 3D Human Motion Editing in Generation

Instruction-driven editing of 3D human motion requires precise spatiotemporal localization, rich semantic grounding, and strict preservation of unmodified content. Existing methods either resort to training-free adaptation of generative models or rely solely on triplet supervision; however, adaptation often yields suboptimal control, and manually curated triplet datasets remain severely limited in scale and semantic diversity. To overcome this bottleneck, we ground motion editing directly within text-to-motion generation across data, architecture, and inference. At the data level, we develop a closed-loop synthesis-and-verification pipeline that produces Omni-MoEdit, a large-scale dataset spanning body-part, amplitude, temporal, action, and style edits. At the architectural level, we introduce UniMoFlow, a unified latent flow-matching model that shares broad semantic and kinematic knowledge between generation and editing. At the inference level, SAFE (Source-Anchored Flow Editing) complements UniMoFlow with controllable, source-anchored refinement. Furthermore, we augment standard evaluations with semantics-aware metrics to account for valid edits that inherently deviate from a single ground-truth reference. Extensive experiments demonstrate improved target-text alignment, edit effectiveness, and cycle consistency, while maintaining competitive source fidelity and text-to-motion generation quality.

cs.CV↗

arXiv2026

WatchPoint: Executable User Feedback for Real-World Agentic Web Development

When a professional web developer's code fails a test, they do not simply re-read the stack trace. They open the application in a browser, click buttons, inspect computed styles, and run diagnostic commands to understand what went wrong. Existing feedback mechanisms for coding agents rely on screenshots, LLM-as-a-judge scoring, or natural-language corrections, but few interact with the live application the way a developer would. We introduce WatchPoint, a simulated-user system that mimics real developer behavior by generating and executing diagnostic scripts against the running application, producing structured observations that guide the coding model's retry. Unlike prior approaches that target single-file edits or evaluate using non-executable metrics, we operate on Web-Bench, a benchmark of 50 multi-file web projects comprising 1,000 sequentially dependent tasks, verified by deterministic end-to-end tests. WatchPoint recovers 57.6% of the tasks it diagnoses, and a controlled user study confirms the simulation's realism: human testers achieve a comparable recovery rate (54.5%), providing evidence that automated diagnostic scripts can substitute for interactive human testing on sequential web development tasks. We further identify a pattern of capability gaps that governs when simulated-user feedback is helpful and when it should be withheld.

cs.SE↗

arXiv2026

AMD:Anatomical Motion Diffusion with Interpretable Motion Decomposition and Fusion

Generating realistic human motion sequences from text descriptions is a challenging task that requires capturing the rich expressiveness of both natural language and human motion. Recent advances in diffusion models have enabled significant progress in human motion synthesis. However, existing methods struggle to handle text inputs that describe complex or long motions. In this paper, we propose the Adaptable Motion Diffusion (AMD) model, which leverages a Large Language Model (LLM) to parse the input text into a sequence of concise and interpretable anatomical scripts that correspond to the target motion. This process exploits the LLM's ability to provide anatomical guidance for complex motion synthesis. We then devise a two-branch fusion scheme that balances the influence of the input text and the anatomical scripts on the inverse diffusion process, which adaptively ensures the semantic fidelity and diversity of the synthesized motion. Our method can effectively handle texts with complex or long motion descriptions, where existing methods often fail. Experiments on datasets with relatively more complex motions, such as CLCD1 and CLCD2, demonstrate that our AMD significantly outperforms existing state-of-the-art models.

cs.CV↗

arXiv2026

Universal Concept Disruption for SAM3 Image Segmentation

SAM3 extends promptable segmentation from geometry-driven mask prediction to open-vocabulary concept segmentation, where a text-conditioned grounding model decides whether a concept is present and segments all matching instances. While this presence-gated design improves concept-level prediction, its adversarial robustness remains unexplored. In this paper, we introduce Universal Concept Disruption (UCD), the first universal cross-concept adversarial attack tailored to SAM3 image segmentation. UCD learns a single bounded image perturbation from (image, noun-phrase) pairs and attacks SAM3 as an integrated concept-grounding system. It jointly disrupts the text-conditioned input path, maximizes divergence in prompt-shared visual features, suppresses the final presence-gated concept scores, and corrupts the spatial validity of retained masks through area collapse and clean-mask Dice disruption. Across SACo-Gold, LVIS, RefCOCO, PhraseCut, and OpenImages datasets, UCD consistently outperforms all baselines under a matched evaluation protocol, reducing average mask AP from 59.43 to 18.73 and average cgF1 from 50.32 to 20.49. The learned perturbation also transfers to SAM3.1 and to SAM3 video inference without re-optimization, while prompt ensembling, lightweight head fine-tuning, and temporal filtering provide limited recovery.

cs.CV↗

arXiv2026

JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw Puzzles

Jigsaw puzzle solving requires jointly reasoning about visual content and geometric constraints, yet existing benchmarks use rectangular cuts that create ambiguous ground truth in texture-repeated regions. We introduce \textit{\ours{}}, a benchmark with tab-and-blank interlocking pieces where geometric constraints provide strong local compatibility requirements that, combined with visual content, yield unambiguous ground truth. Across 95K instances at four grid densities (4$\times$4 to 16$\times$16), we find that \textbf{zero-shot VLMs largely lack geometric reasoning}: only one of five frontier models (GPT-5.5) exceeds random baseline on 4$\times$4 puzzles, while all others perform at chance level. While supervised fine-tuning achieves $>$97\% on 4$\times$4, \textbf{all models collapse on larger grids}: GPT-5.5 drops from 70\% to near-random on 8$\times$8, and even fine-tuned models fall below 5\% on 12$\times$12. This ``scaling cliff'' suggests current architectures cannot maintain consistent constraint satisfaction as the number of pieces increases. \ours{} establishes scalable geometric reasoning as an open challenge for vision-language models.

cs.CV↗

arXiv2026

Fast Matrix Multiplication in fp8: Certified Coefficient Optimization and Measured Error

A Strassen-type algorithm has many realizations with the same exact product and multiplication count yet different fp8 error because basis changes reshape coefficient geometry, posing the question of which to run. No current account settles this: classical stability controls worst-case $\ell_1$ growth, not the expected-error magnitude, and the Dumas--Pernet--Sedoglavic optimizer could only be called probably optimal, its global optimality unproved. To settle this, we attach to each realization a coefficient functional $Φ$, a scalar summary of its coefficient geometry, which we minimize over the change-of-basis orbit. This Kempf--Ness problem on a Hadamard manifold lets us certify the global $Φ$ optimum rather than merely search for it: an exact moment-map zero fixes $Φ_{\min} = 200/9$, and de Groote's classification extends that optimality to every exact real rank-7 $2\times2$ decomposition. Every exact real rank-7 realization therefore has a $Φ$-predicted RMS constant at least $5/3$ times that of the cubic algorithm, at fixed noise coefficient. We then introduce an explicit block-scaled e4m3 model in which $Φ$ is the leading-order coefficient of relative expected mean-squared error, and we test the resulting $Φ$-predicted ordering against realized fp8 error. Ordering and re-basing experiments support that prediction within tested fused block-scaled regimes, and on real matmul tiles from four architecture families the $Φ$-optimal realization falls in the fp8 low-error region. Across two $\sim$70B models on real deep_gemm kernels, the same realization removes 10 to 55% of classic Strassen's excess NLL over the clean model. Algorithm realization thus becomes a mathematically certified design problem rather than a tuning choice: an independent low-precision axis with a global $Φ$ optimum and measured fp8 relevance.

cs.LG↗

arXiv2026

WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics

Web applications (web apps) have become a key arena for large language models (LLMs) to demonstrate their code generation capabilities and commercial potential. However, building a benchmark for LLM-generated web apps remains challenging due to the need for real-world user requirements, generalizable evaluation metrics without relying on ground-truth implementations or test cases, and interpretable evaluation results. To address these challenges, we introduce WebCoderBench, the first real-world-collected, generalizable, and interpretable benchmark for web app generation. WebCoderBench comprises 1,572 real user requirements, covering diverse modalities and expression styles that reflect realistic user intentions. WebCoderBench provides 24 fine-grained evaluation metrics across 9 perspectives, combining rule-based and LLM-as-a-judge paradigm for fully automated, objective, and general evaluation. Moreover, WebCoderBench adopts human-preference-aligned weights over metrics to yield interpretable overall scores. Experiments across 12 representative LLMs and 2 LLM-based agents show that there exists no dominant model across all evaluation metrics, offering an opportunity for LLM developers to optimize their models in a targeted manner for a more powerful version.

cs.SE↗

arXiv2026

Characterizing Real-World Bugs in Tile Programs for Automated Bug Detection

Tile-based programming frameworks are increasingly adopted to write high-performance GPU kernels in domains such as deep learning and scientific computing. While these frameworks enhance productivity and hardware utilization, their multi-stage compilation pipelines introduce distinct code generation bugs that are tightly coupled to input shapes, data types, and backend targets. These bugs often manifest as silent wrong results or performance issues, making them difficult to detect using existing compiler testing tools. Additionally, the unique programming conventions of tile domain-specific languages complicate root cause identification, while fixing such bugs demands specialized knowledge of tile abstractions and compilation pipelines. Despite the growing adoption of tile-based systems, their code generation bugs remain largely unexplored. This paper presents the first systematic study of tile-program code generation bugs. We curate 401 bug reports from GitHub and identify 301 tile-program codegen bugs for analysis, characterizing their root causes and symptoms, the input patterns that trigger them, the test oracles that detect them, and the strategies for fixing these bugs. Our study provides foundational insights for building debugging, testing, and repair tools tailored to tile-based compiler infrastructures.

cs.SE↗

arXiv2026

LaRec: Unleashing LLM-based Latent Reasoning for Generative Recommendation

Large Language Models (LLMs) have shown great promise in recommendation due to superior reasoning abilities. However, existing methods mainly rely on explicit Chain-of-Thought (CoT), resulting in verbose reasoning texts and inefficient response times. latent reasoning aims to balance efficiency by thinking within a continuous latent space, yet it faces two major challenges: (1) Lack of Fine-grained Supervision: Latent reasoning relies solely on feedback from the final labels, providing sparse supervisory signals that struggle to effectively guide the optimization of multiple hidden reasoning steps. (2) Single Reasoning Path: The deterministic nature of latent reasoning impedes the exploration of users' diverse interests and preferences, thereby limiting the recommendation capabilities of LLMs. To address these issues, we propose \textbf{$LaRec$}, an efficient generative recommendation framework designed to unleash the potential of latent reasoning in LLMs. $LaRec$ consists of two core stages: First, we design Latent Pre-training that empowers LLMs with latent reasoning capabilities by providing rich supervisory signals to the latent space reasoning via step-level alignment and process direction alignment. Second, we introduce Personalized RL-tuning. Specifically, we construct a personalized Gaussian Mixture Distribution for each user based on their historical interests. By randomly sampling distinct reasoning starting points from this distribution during training, we guide the LLMs to traverse diverse reasoning paths within the latent space, enabling efficient exploration of user's multi-faceted interests. Experiments on multiple datasets show that $LaRec$ significantly outperforms existing baselines with comparable efficiency.

cs.IR↗

arXiv2026

A Scale-adaptive Vision Model Links C. elegans Neuronal Morphology to Behavior for Neurotoxicity Assessment

Neurological disorders are a leading cause of global disability and are increasingly linked to environmental chemical exposures. Yet neurotoxicity assessment still relies on hand-scored morphological readouts that are subjective and poorly predictive of behavioral outcomes. Caenorhabditis elegans provides a genetically tractable, 3R-compliant alternative, but quantifying neuronal phenotypes from confocal microscopy at scale remains computationally challenging: existing vision foundation models, trained on natural or radiological images, cannot resolve the sparse signals and multi-scale lesions of neuronal imaging. Here, we introduce a dedicated self-supervised vision model for C. elegans dopaminergic neurons, together with CeNeuMorph, a multi-grained confocal benchmark of 27,117 annotated images. Specifically, moving beyond standard Masked Autoencoders, we propose a scale-adaptive masked image modeling strategy that jointly learns representations across resolutions and patch sizes under a fixed token budget. By decoupling structural semantic learning from rigid grid constraints, the model effectively resolves the full spectrum of neurodegenerative lesions - ranging from fine dendritic beading to gross soma shrinkage - within a tractable computational framework. Finally, our model surpasses both generalist and biomedical foundation models across classification, segmentation and detection tasks. Fusing visual features with morphological descriptors enables prediction of dopamine-dependent behavioral deficits ($R^2=0.498$). Screening 180 agrochemicals, we identify the benzimidazole moiety as a previously unrecognized determinant of dopaminergic neurotoxicity. Together, the work demonstrates how scale-adaptive self-supervised learning can connect morphology to function for a scalable alternative to mammalian in vivo models for neurotoxicity assessment and drug discovery.

cs.CE↗

arXiv2026

LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow

Flow matching over carefully designed latent representations has recently emerged as a powerful paradigm for topology-aware mesh generation. Existing approaches, however, model vertices and connectivity jointly in a joint latent space, entangling continuous vertex geometry with discrete combinatorial structure; this complicates flow learning and manifests as drifting vertices and broken surfaces. We present LATO.2, a factorized flow matching framework that decomposes mesh generation into a vertex flow followed by a connectivity flow conditioned on the realized vertices, with both stages anchored to a shared coarse voxel scaffold. Dedicated VAEs underpin the two stages, recovering vertices at sub-voxel precision and embedding discrete connectivity into a continuous latent space. We demonstrate two advantages unique to this factorization: (i) part-wise generation, in which the scaffold is partitioned and each part synthesized at full latent capacity, yielding substantially higher-resolution meshes than a monolithic latent permits; and (ii) topology-adaptive editing, in which manipulating first-stage vertices induces the corresponding connectivity without re-optimization. Experiments show that LATO.2 surpasses state-of-the-art topology-aware mesh generators in geometric fidelity and connectivity quality.

cs.GR↗

arXiv2026

SubdivAR: Autoregressive Next-Scale Prediction for Neural Mesh Subdivision

Mesh subdivision is a fundamental operation for converting coarse, editable meshes into high-resolution surfaces, with broad applications in digital asset creation. Classical rule-based schemes rely on fixed local refinement rules and often produce over-smoothed surfaces. Recent neural subdivision methods improve detail synthesis, but remain constrained by local modeling and exhibit limited generalizability. We present SubdivAR, a neural mesh subdivision framework based on our proposed Mesh Autoregressive Representation (MAR). MAR arranges meshes at different subdivision levels into an ordered scale sequence, reformulating subdivision as autoregressive next-scale prediction. To support this formulation, we introduce a Hybrid Topology-Aware Transformer that combines global semantic attention with topology-constrained local feature aggregation. SubdivAR adopts a next-scale coordinate prediction paradigm, regressing vertex offsets at each refinement stage to preserve subdivision topology while recovering fine-grained geometric details. To enable reliable learning, we construct FII-40K, a curated dataset of nearly 40,000 high-quality meshes with multi-level subdivision supervision. Experiments show that SubdivAR outperforms state-of-the-art baselines, reducing Hausdorff Distance and Chamfer Distance by 18.8% and 14.2%, respectively, and demonstrates strong robustness on complex open-surface geometries.

cs.CV↗