arXiv subjects

Ming Hu

Publications and source records attributed to Ming Hu.

At least 37 records · Page 2Linked to original sources

arXiv2026

Geometry-Aware Motion Latents for Learning Robust Manipulation Policies

Learning motion latents for robotic manipulation heavily relies on extracting motion patterns from visual sequences, yet effective action abstractions require understanding three-dimensional geometric transformations. Here, we introduce GeoMoLa (Geometry-Aware Motion Latents), which learns discrete motion latent codes by predicting how point clouds evolve during manipulation rather than reconstructing visual observations. This four-dimensional objective -- spatial geometry changing through time -- forces latent representations to encode actual physical motion rather than appearance patterns. GeoMoLa achieves state-of-the-art performance using only single-view RGB-D input, while existing methods require multi-view reconstruction, succeeding across diverse manipulation benchmarks. Our ablations reveal that geometric prediction is the key to driving performance, quantitatively validating that manipulation depends on spatial understanding. Furthermore, the learned codes exhibit effective motion abstraction: applying them to novel scenes produces physically consistent transformations regardless of visual context. Our real-world experiments also confirm this robustness capability, achieving robust manipulation with minimal demonstrations in cluttered environments where geometric reasoning determines success. Thus, we demonstrate that effective motion latents for robot control can better emerge from understanding motion through its three-dimensional effects rather than pixel-level patterns.

cs.RO↗

arXiv2026

HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding

Document parsing is a fundamental task in multimodal understanding, supporting a wide range of downstream applications such as information extraction and intelligent document analysis. Benefiting from strong semantic modeling and robust generalization, VLM-based end-to-end approaches have emerged as the mainstream paradigm in recent years. However, these models often suffer from substantial inference latency, as they must autoregressively generate long, full-page sequences when processing long-form documents. While recent hybrid methods mitigate this issue via region-level parallel decoding with VLMs, independent region decoding loses full-page context and might weaken global coherence. To address this issue, we propose Hierarchical Speculative Decoding (HSD), a two-stage local-to-global framework for document parsing. HSD first employs a lightweight pipeline drafter to predict region partitions and generate coarse drafts for each region. The first stage verifies the generated region-level drafts in parallel for efficiency, while the second stage further performs page-level verification on these refined outputs to preserve full-page coherence. Experimental results show that HSD achieves a near-lossless 2.7x speedup with HunyuanOCR on OmniDocBench v1.5 and up to 7.04x speedup on long-document parsing tasks, demonstrating the effectiveness of the proposed method. The code is available at https://github.com/whlscut/HSD.

cs.CV↗

arXiv2026

A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions

Policy gradient algorithms for language models optimize the same objective $J(θ) = \mathbb{E}*{τ\sim p*θ(τ)}[R(τ)]$, which has exactly two factors: the trajectory probability $p_θ(τ)$ and the reward $R(τ)$. Every method from REINFORCE to PPO to GRPO and their descendants modifies one or both factors to address a specific failure in the preceding formulation. Existing surveys organize these methods by domain or chronology, which obscures the rationale behind each design choice and the precise location of its intervention within the gradient estimator. This survey revisits the landscape of LLM policy optimization from $J(θ)$ on first principles and uses the trajectory side, induced by $p_θ(τ)$, and the reward side, induced by $R(τ)$, as the two axes along which methods are located. It covers the path from REINFORCE and PPO to GRPO, as well as post-GRPO variants, Agentic RL, and GRPO-OPD. The resulting framework is unified, diagnostic, and extensible: it analyzes methods from a shared objective, identifies which side each method modifies and why, and applies the same trajectory and reward axes across these settings. Across these settings, the framework also exposes compound failures that no single-side fix resolves and that therefore require joint design of the trajectory side and the reward side. The boundary cases and coupled failures identified by this map mark where existing solutions run out and provide a principled starting point for designing the next generation of LLM policy optimization algorithms.

cs.AI↗

arXiv2026

Supracompetitive Pricing Under AI Monoculture

When competing sellers delegate pricing to a shared AI model, such as a large language model, correlated recommendations combined with performance-driven updates aggregating seller feedback raise a key question: can standard AI deployment practices inadvertently produce supracompetitive pricing? We develop a stylized duopoly model in which two sellers receive pricing recommendations from a shared AI characterized by two parameters: a propensity parameter capturing the model's tendency to set high prices and an output-fidelity parameter measuring alignment between this tendency and actual outputs, with propensity updated via periodic retraining on observed outcomes. We find that configuring AI models for robustness and reproducibility can lead to supracompetitive pricing via a phase transition. Below a critical output-fidelity threshold, competitive pricing is the unique stable outcome. Above it, the model exhibits bistability: both competitive and supracompetitive pricing are locally stable, with the realized outcome determined by the model's initial propensity. Supracompetitive pricing raises average prices, but occasional low-price recommendations complicate detection. With perfect output fidelity, full price coordination emerges from any interior initial propensity. For finite training batches of size $b$, when the initial propensity lies in the supracompetitive basin, the probability of supracompetitive pricing approaches 1 as $b$ increases, with the region of indeterminate outcomes shrinking at rate $O(1/\sqrt{b})$. Any factor reducing alignment between the model's propensity and sellers' actual pricing, whether through diversifying AI providers, introducing recommendation noise, or reducing seller adherence, pushes the market toward competitive outcomes.

econ.TH↗

arXiv2026

UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis

Medical workflows routinely combine reading images with producing visual and textual outputs, making both image understanding and generation central to medical AI. Most existing systems, however, address these abilities in isolated models, losing the shared knowledge that a unified architecture could exploit. To bridge this gap, we present UniMedVL, the first unified medical model that seamlessly integrates multimodal understanding and generation capabilities within a single model without switching weights. We achieve this via a tailored progressive training pipeline where understanding and generation mutually reinforce each other. To effectively train UniMedVL, we curate UniMedVL-5M, the first large-scale medical dataset comprising over 5.6M instances across 8 medical imaging modalities, tailored for multimodal input-output tasks in unified medical understanding and generation. Experimental results demonstrate that UniMedVL achieves competitive performance on five medical understanding benchmarks. Crucially, UniMedVL natively supports diverse interleaved generation tasks, e.g., virtual staining, super-resolution, cross-modal synthesis, essential for complex medical workflows. Our code and dataset are publicly available.

cs.CV↗

arXiv2026

MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation

The LLM-as-a-Judge paradigm shows promise for evaluating generative content but lacks reliability in reasoning-intensive scenarios, such as programming. Inspired by recent advances in reasoning models and shifts in scaling laws, we pioneer bringing test-time computation into LLM-as-a-Judge, proposing MCTS-Judge, a resource-efficient, System-2 thinking framework for code correctness evaluation. MCTS-Judge leverages Monte Carlo Tree Search (MCTS) to decompose problems into simpler, multi-perspective evaluations. Through a node-selection strategy that combines self-assessment based on historical actions in the current trajectory and the Upper Confidence Bound for Trees based on prior rollouts, MCTS-Judge balances global optimization and refinement of the current trajectory. We further designed a high-precision, unit-test-level reward mechanism to encourage the Large Language Model (LLM) to perform line-by-line analysis. Extensive experiments on three benchmarks and five LLMs demonstrate the effectiveness of MCTS-Judge, which improves the base model's accuracy from 41% to 80%, surpassing the o1-series models with 3x fewer tokens. Further evaluations validate the superiority of its reasoning trajectory in logic, analytics, thoroughness, and overall quality, while revealing the test-time scaling law of the LLM-as-a-Judge paradigm.

cs.LG↗

arXiv2026

Towards Interpretable Federated Learning

Federated learning (FL) enables multiple data owners to build machine learning models collaboratively without exposing their private local data. In order for FL to achieve widespread adoption, it is important to balance the need for performance, privacy-preservation and interpretability, especially in mission critical applications such as finance and healthcare. Thus, interpretable federated learning (IFL) has become an emerging topic of research attracting significant interest from the academia and the industry alike. Its interdisciplinary nature can be challenging for new researchers to pick up. In this paper, we bridge this gap by providing (to the best of our knowledge) the first survey on IFL. We propose a unique IFL taxonomy which covers relevant works enabling FL models to explain the prediction results, support model debugging, and provide insights into the contributions made by individual data owners or data samples, which in turn, is crucial for allocating rewards fairly to motivate active and reliable participation in FL. We conduct comprehensive analysis of the representative IFL approaches, the commonly adopted performance evaluation metrics, and promising directions towards building versatile IFL techniques.

cs.LG↗

arXiv2026

LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence

We introduce LLaVA-OneVision-2 (LLaVA-OV-2), the most capable vision-language model in the LLaVA-OneVision series to date, achieving superior performance across a broad range of multimodal benchmarks. The model builds on a native OneVision-Encoder and incorporates Windowed Attention for efficient local computation while maintaining native resolution. Its key advance is codec-stream tokenization: it treats compressed video as a continuous bit-cost stream, where bit-cost dynamics determine adaptive temporal groups, and motion-residual cues select salient spatial evidence into compact visual canvases. This allocation concentrates a limited token budget on event-bearing content, enabling more stable long-video token compression than fixed groups of pictures. A shared 3D RoPE further places codec canvases, sampled frames, and images in a unified spatiotemporal coordinate system. Furthermore, we build the LLaVA-OV-2 data and training stack around large-scale open supervision: approximately 8M re-captioned video samples for pretraining, a 4M-sample spatial corpus for fine-tuning. We also introduce JumpScore, a temporal-localization benchmark targeting fine-grained grounding in high-frequency, densely repeated motion, a regime underrepresented by existing video evaluations. A standout capability of LLaVA-OV-2 is its unified perception across video understanding, temporal grounding, spatial grounding, and manipulation-trace reasoning. On JumpScore, LLaVA-OneVision-2-8B reaches 74.9 JumpScore mAP, surpassing Qwen3-VL-8B (30.1) by +44.8 points; under matched visual-token budgets on the same benchmark, codec-stream inputs improve temporal grounding over frame sampling by +9.7 points. Across standard benchmarks, LLaVA-OneVision-2-8B further outperforms Qwen3-VL-8B by +4.3 average points on video tasks, +5.3 on spatial tasks, and +15.6 average J&F on tracking tasks.

cs.CV↗

arXiv2026

DermAgent: A Self-Reflective Agentic System for Dermatological Image Analysis with Multi-Tool Reasoning and Traceable Decision-Making

Dermatological diagnosis requires integrating fine-grained visual perception with expert clinical knowledge. Although Multimodal Large Language Models (MLLMs) facilitate interactive medical image analysis, their application in dermatology is hindered by insufficient domain-specific grounding and hallucinations. To address these issues, we propose DermAgent, a collaborative multi-tool agent that orchestrates seven specialized vision and language modules within a Plan-Execute-Reflect framework. DermAgent delivers stepwise, traceable diagnostic reasoning through three core components. First, it employs complementary visual perception tools for comprehensive morphological description, dermoscopic concept annotation, and disease diagnosis. Second, to overcome the lack of domain prior, a dual-modality retrieval module anchors every prediction in external evidence by cross-referencing 413,210 diagnosed image cases and 3,199 clinical guideline chunks. To further mitigate hallucinations, a deterministic critic module conducts strict post-hoc auditing via confidence, coverage, and conflict gates, automatically detecting inter-source disagreements to trigger targeted self-correction. Extensive experiments on five dermatology benchmarks demonstrate that DermAgent consistently outperforms state-of-the-art MLLMs and medical agent baselines across zero-shot fine-grained disease diagnosis, concept annotation, and clinical captioning tasks, exceeding GPT-4o by 17.6% in skin disease diagnostic accuracy and 3.15% in captioning ROUGE-L. Our code is available at https://github.com/YizeezLiu/DermAgent.

cs.CV↗

arXiv2026

VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?

With AI-generated videos increasingly indistinguishable from reality, current benchmarks primarily focus on broad semantic alignment and basic physical consistency, offering limited discriminative power for evaluating them. To address this, we introduce VideoASMR-Bench, a benchmark based on Autonomous Sensory Meridian Response (ASMR) videos that emphasizes fine-grained audio-visual perception and sensory immersion. This benchmark aims to answer two key questions: (i) Are today's video understanding models (VLMs) sensitive enough to detect AI-generated ASMR videos by recognizing minor visual, physical, or auditory artifacts? (ii) Can today's video generation models (VGMs) produce convincing ASMR videos with immersive experiences? This benchmark comprises a diverse set of 1,500 high-quality real ASMR videos curated from social media, alongside 2,235 synthetic counterparts generated by nine VGMs. Additionally, we open-source an extensible suite of prompts and reference images, enabling the benchmark to scale dynamically with future video models. Moreover, we design an automatic understanding-generation evaluation framework between VGMs and VLMs, where VGMs aim to produce realistic fake videos to fool the VLMs, while the VLMs seek to detect them, forming an adversarial game between the two parties. Our evaluation on VideoASMR-Bench reveals that even state-of-the-art VLMs, such as Gemini-3-Pro, fail to reliably detect AI-generated ASMR videos. Meanwhile, current frontier video generation models can produce ASMR videos that are difficult for VLMs to distinguish from real ones, while humans can still identify them relatively easily.

cs.CV↗

arXiv2026

StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding

Real-time streaming video understanding in domains such as autonomous driving and intelligent surveillance poses challenges beyond conventional offline video processing, requiring continuous perception, proactive decision making, and responsive interaction based on dynamically evolving visual content. However, existing methods rely on alternating perception-reaction or asynchronous triggers, lacking task-driven planning and future anticipation, which limits their real-time responsiveness and proactive decision making in evolving video streams. To this end, we propose a StreamAgent that anticipates the temporal intervals and spatial regions expected to contain future task-relevant information to enable proactive and goal-driven responses. Specifically, we integrate question semantics and historical observations through prompting the anticipatory agent to anticipate the temporal progression of key events, align current observations with the expected future evidence, and subsequently adjust the perception action (e.g., attending to task-relevant regions or continuously tracking in subsequent frames). To enable efficient inference, we design a streaming KV-cache memory mechanism that constructs a hierarchical memory structure for selective recall of relevant tokens, enabling efficient semantic retrieval while reducing the overhead of storing all tokens in the traditional KV-cache. Extensive experiments on streaming and long video understanding tasks demonstrate that our method outperforms existing methods in response accuracy and real-time efficiency, highlighting its practical value for real-world streaming scenarios.

cs.CV↗

arXiv2026

Leveraging Multimodal LLMs for Built Environment and Housing Attribute Assessment from Street-View Imagery

We present a novel framework for automatically evaluating building conditions nationwide in the United States by leveraging large language models (LLMs) and Google Street View (GSV) imagery. By fine-tuning Gemma 3 27B on a modest human-labeled dataset, our approach achieves strong alignment with human mean opinion scores (MOS), outperforming even individual raters on SRCC and PLCC relative to the MOS benchmark. To enhance efficiency, we apply knowledge distillation, transferring the capabilities of Gemma 3 27B to a smaller Gemma 3 4B model that achieves comparable performance with a 3x speedup. Further, we distill the knowledge into a CNN-based model (EfficientNetV2-M) and a transformer (SwinV2-B), delivering close performance while achieving a 30x speed gain. Furthermore, we investigate LLMs' capabilities for assessing an extensive list of built environment and housing attributes through a human-AI alignment study and develop a visualization dashboard that integrates LLM assessment outcomes for downstream analysis by homeowners. Our framework offers a flexible and efficient solution for large-scale building condition assessment, enabling high accuracy with minimal human labeling effort.

cs.CV↗

arXiv2026

MedProbeBench: Systematic Benchmarking at Deep Evidence Integration for Expert-level Medical Guideline

Recent advances in deep research systems enable large language models to retrieve, synthesize, and reason over large-scale external knowledge. In medicine, developing clinical guidelines critically depends on such deep evidence integration. However, existing benchmarks fail to evaluate this capability in realistic workflows requiring multi-step evidence integration and expert-level judgment. To address this gap, we introduce MedProbeBench, the first benchmark leveraging high-quality clinical guidelines as expert-level references. Medical guidelines, with their rigorous standards in neutrality and verifiability, represent the pinnacle of medical expertise and pose substantial challenges for deep research agents. For evaluation, we propose MedProbe-Eval, a comprehensive evaluation framework featuring: (1) Holistic Rubrics with 1,200+ task-adaptive rubric criteria for comprehensive quality assessment, and (2) Fine-grained Evidence Verification for rigorous validation of evidence precision, grounded in 5,130+ atomic claims. Evaluation of 17 LLMs and deep research agents reveals critical gaps in evidence integration and guideline generation, underscoring the substantial distance between current capabilities and expert-level clinical guideline development. Project: https://github.com/uni-medical/MedProbeBench

cs.CV↗

arXiv2026

Radiology Report Generation for Low-Quality X-Ray Images

Vision-Language Models (VLMs) have significantly advanced automated Radiology Report Generation (RRG). However, existing methods implicitly assume high-quality inputs, overlooking the noise and artifacts prevalent in real-world clinical environments. Consequently, current models exhibit severe performance degradation when processing suboptimal images. To bridge this gap, we propose a robust report generation framework explicitly designed for image quality variations. We first introduce an Automated Quality Assessment Agent (AQAA) to identify low-quality samples within the MIMIC-CXR dataset and establish the Low-quality Radiology Report Generation (LRRG) benchmark. To tackle degradation-induced shifts, we propose a novel Dual-loop Training Strategy leveraging bi-level optimization and gradient consistency. This approach ensures the model learns quality-agnostic diagnostic features by aligning gradient directions across varying quality regimes. Extensive experiments demonstrate that our approach effectively mitigates model performance degradation caused by image quality deterioration. The code and data will be released upon acceptance.

cs.CV↗

arXiv2026

OralAgent: Integrating Reasoning, Tools, and Knowledge for Interactive Dental Image Analysis

Dental image analysis plays a pivotal role in supporting accurate diagnosis and treatment planning in oral healthcare. Although recent advances have produced dental AI models for specific tasks and individual imaging modalities, their isolated designs limit practical use in real-world clinical workflows. In this paper, we present OralAgent, the first dental-specialized AI agent that unifies multimodal reasoning, tool-based decision-making, and knowledge-grounded retrieval within an end-to-end automated framework. It integrates 22 visual analysis tools and 368 widely-used classical dental textbooks, enabling autonomous reasoning, planning, tool use, knowledge retrieval, and multi-step workflow execution. Furthermore, we introduce OralCorpus, a large-scale, high-quality bilingual textual resource containing 134.8M tokens curated for dental retrieval-augmented generation (RAG). To evaluate models' multidisciplinary dental knowledge, we construct OralQA-ZH, a Chinese multiple-choice question benchmark consisting of 798 items across eleven oral subspecialties. Extensive experiments demonstrate that OralAgent achieves state-of-the-art performance on the MMOral-Uni, MMOral-OPG, and OralQA-ZH benchmarks, highlighting its effectiveness, interpretability, and adaptability in real-world clinical settings. The code and models are publicly available at https://github.com/isjinghao/OralAgent.

cs.CL↗

arXiv2026

LLM Biases

Transformer-based agentic AI is rapidly being deployed on major platforms to help users shop, watch, and navigate content with less effort. While these systems can deliver impressive performance, a key concern is whether they may be less reliable than they appear. We ask a simple but fundamental question: whether the mechanisms that make transformer-based agents effective can also induce systematic biases or distortions? We study this question through a theoretical analysis of transformer-based generative recommenders, in which the next user interaction is generated sequentially from the user history. Focusing on how the model allocates attention across historical evidence, we identify four bias channels: (i) Positional bias: stronger positional encoding shifts influence toward recent history, improving responsiveness but potentially reducing stability and long-term diversity; (ii) Popularity amplification: small frequency differences in data can be magnified into disproportionate exposure, contributing to Matthew effects and echo chambers; (iii) Latent driver bias: when important drivers of user choices are not directly observed, the model can place overly concentrated weight on a small subset of past events, creating overconfident attributions. (iv) Synthetic data bias: when users increasingly follow AI suggestions and platforms retrain on model-shaped synthetic logs, outputs can concentrate over time, and long-tail alternatives can disappear first. Our analysis highlights mechanism-level reliability risks that may not be visible in offline performance metrics. The four bias channels indicate that large-scale deployment may systematically distort exposure and choice. For managers, the immediate implication is to treat these as operational risk factors and to monitor concentration and drift over time, rather than assuming that performance gains alone guarantee reliability.

cs.CY↗

arXiv2026

Foundation-Model Surrogates Enable Data-Efficient Active Learning for Materials Discovery

Active learning (AL) has emerged as a powerful paradigm for accelerating materials discovery by iteratively steering experiments toward promising candidates, reducing the number of costly synthesis-and-characterization cycles needed to identify optimal materials. However, current AL relies predominantly on Gaussian Process (GP) and Random Forest (RF) surrogates, which suffer from complementary limitations: GP underfits complex composition-property landscapes due to rigid kernel assumptions, while RF produces unreliable heuristic uncertainty estimates in small-data regimes. This small-data challenge is pervasive in materials science, making reliable surrogate modeling extremely difficult with models trained from scratch on each new dataset. Here we propose In-Context Active Learning (ICAL), which addresses this bottleneck by replacing conventional surrogates with TabPFN, a transformer-based foundation model (FM) pre-trained on millions of synthetic regression tasks to meta-learn a universal prior over tabular data, upon which TabPFN performs principled Bayesian inference in a single forward pass without dataset-specific retraining, delivering strong small-data regression performance and well-calibrated predictive uncertainty (required for effective AL). We benchmark ICAL against GP and RF across 10 materials datasets and TabPFN wins on 8 out of 10 datasets, achieving a mean saving of 52% in extra evaluations relative to GP and 29.77% relative to RF. Cross-validation analysis confirms that TabPFN's advantage stems from superior uncertainty calibration, achieving the lowest Negative Log-Likelihood and Area Under the Sparsification Error curve among all surrogates. These results demonstrate that pre-trained FMs can serve as effective surrogates for active learning, enabling data-efficient discovery across diverse materials systems and small-data experimental sciences.

cond-mat.mtrl-sci↗

arXiv2026

A Solicit-Then-Suggest Model of Agentic Purchasing

E-commerce is shifting from search-based shopping to agentic purchasing. Rather than relying on keywords, AI shopping agents learn customer preferences through targeted multi-round conversations and then recommend a tailored set of products. We develop a solicit-then-suggest framework to study this setting. In a d-dimensional preference space, an agent conducts m rounds of solicitation to refine its belief about the customer's ideal product, then recommends k products from which the customer chooses. Our analysis identifies the key economic tradeoff. Under a Gaussian prior, we establish an uncertainty decomposition: solicitation depth and assortment breadth are substitutes, with total prior uncertainty split between what solicitation resolves and what assortment breadth hedges. The two instruments improve match quality at very different rates. Expected loss decreases on the order of 1/m with solicitation depth, but only on the order of k^(-2/d) with assortment breadth, reflecting a curse of dimensionality. Thus, a few well-designed questions can achieve what would otherwise require far more recommendations. We also characterize the optimal policy. The optimal assortment forms a Voronoi partition, assigning each product to the posterior region it best serves. With a single recommended product, the optimal solicitation follows a water-filling rule that equalizes posterior uncertainty across dimensions. With multiple products, the optimum may allocate less precision to dimensions that the assortment can hedge. This single-product water-filling rule also yields a general approximation guarantee for larger assortments, and the gap vanishes as dimension grows. Beyond the Gaussian case, the uncertainty decomposition and substitutability between solicitation depth and assortment breadth continue to hold for non-Gaussian priors.

cs.GT↗