arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 271 records · Page 15Linked to original sources

arXiv2026

ImProNCDE: Impulse-Corrected Neural Controlled Differential Equations with Prototype Learning for Longitudinal Prognosis Prediction

Longitudinal ophthalmic imaging analysis is an essential step for prognosis prediction in ophthalmic diseases. However, AI-assisted prognosis models are challenged by follow-up sequences, which tend to be sparse, irregularly sampled, and incomplete. Although advanced prognosis modeling methods, especially for the methods based on neural controlled differential equations (NCDEs), provide a principled continuous-time framework for sparse and irregular longitudinal data. Unfortunately, two major concerns remain unsolved in clinical follow-up modeling. First, the smooth latent dynamics of standard NCDEs is poorly matched to abrupt pathological changes induced by therapeutic intervention, lesion recurrence, or long follow-up gaps. Second, numerical integration over long horizons can accumulate errors, which will produce unstable latent trajectories and weakened class discrimination. To address these challenges, we propose ImProNCDE, an impulse-corrected NCDE framework with prototype learning for longitudinal ophthalmic prognosis prediction. To capture abrupt pathological changes beyond smooth latent dynamics, ImProNCDE introduces Residual Impulse Calibration (RIC), which injects residual-based impulse corrections at visit times and then recalibrates the latent state when observations deviate from continuous predictions. To further mitigate error accumulation over long horizons, we introduce a Prototype-guided Trajectory Stabilizer (PTS), which aims to attract latent trajectories toward learnable prognosis prototypes to reduce class overlap and which ultimately improves long-horizon stability. Experiments on multiple private and public longitudinal ophthalmic datasets (totalling over 1206 samples) show that ImProNCDE outperforms existing SOTA methods focusing on sequence modeling.

cs.CE↗

arXiv2026

Uncertainty-Aware Reward Modeling for Stable RLHF

Reinforcement learning from human feedback (RLHF) aligns large language models by training reward models on preference data and optimizing policies to maximize predicted rewards. However, this pipeline faces two fundamental challenges: (1) reward models cannot signal when their predictions are unreliable, since they usually act as deterministic point estimators; and (2) modern group-based policy optimization can amplify unreliable reward signals, as exemplified by GRPO's uniform treatment of rewards during advantage computation. As policies explore increasingly diverse responses, these two limitations create a critical vulnerability: unreliable reward estimates may be granted disproportionate influence, triggering severe reward hacking. We propose Uncertainty-Aware Reward Modeling (UARM), which equips reward models with calibrated uncertainty via quantile-based conformal prediction and reweights GRPO advantages through heteroscedastic variance decomposition. Experiments across HelpSteer, UltraFeedback, and PKU-SafeRLHF demonstrate that UARM significantly improves reward model calibration, reduces reward hacking, and enhances downstream alignment quality compared to standard GRPO and uncertainty-agnostic baselines.

cs.LG↗

arXiv2026

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation

Block-diffusion language models offer a promising path toward faster-than-autoregressive generation by combining block-wise autoregressive decoding with within-block parallel denoising. However, in the few-step regime needed for practical acceleration, standard confidence-thresholded decoding is often brittle: aggressive thresholds hurt quality, while conservative thresholds require unnecessary denoising steps. Existing approaches that address this issue either require additional training or incur extra test-time compute. We present S2D2, a training-free self-speculative decoding framework for block-diffusion language models. Our key observation is that a block-diffusion model becomes autoregressive when the block size is reduced to one, allowing the same pretrained model to act as both drafter and verifier. S2D2 inserts a speculative verification step into standard block-diffusion decoding and uses lightweight routing policies to decide when verification is worth its cost. This yields a hybrid decoding trajectory in which diffusion proposes tokens in parallel, while the autoregressive mode acts as a local sequence-level critic. Across three mainstream block-diffusion families, S2D2 consistently improves the accuracy-speed tradeoff over strong confidence-thresholding baselines. On SDAR, we observe up to $4.7\times$ speedup over autoregressive decoding, and up to $1.57\times$ over a tuned dynamic decoding baseline while improving accuracy by up to $4.5$ points. On LLaDA2.1-Mini, S2D2 remains complementary to built-in self-correction, including a conservative setting where it is $4.4\times$ faster than the static baseline with slightly higher accuracy.

cs.CL↗

arXiv2026

Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Serving

LLM-powered agents execute tasks through a sequential loop of model generation and tool execution. Today's serving systems serialize this loop, leaving tool latency exposed on the task critical path. This paper presents PASTE, a tool-aware agent-serving system that predicts concrete future tool invocations from recurring agent patterns and executes them speculatively while the LLM is still generating. PASTE isolates speculative results until confirmed by the LLM and jointly schedules tool execution and returning LLM sessions to avoid shifting bottlenecks to the GPU. Across deep research, coding, and scientific-agent workloads, PASTE reduces average task completion time by 43.5% and lowers observed tool latency by 1.8x.

cs.DC↗

arXiv2026

EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation

Zero-Shot Object-Goal Navigation (ZS-OGN) requires embodied agents to explore and locate target objects without any prior training. To this end, recent methods leverage foundation models. But they typically rely on static priors and lack adaptation, which leads to repeated errors and costly trial and error. In this paper, we propose a self-evolving ZS-OGN framework that enables continuous test-time improvement. Specifically, we build an agentic rule memory by extracting actionable knowledge from past trajectories. Then, we propose a retrieval strategy based on upper confidence bound, selecting effective rules by balancing semantic relevance and historical success. In addition, we introduce a memory-guided preflection module that forecasts potential outcomes before action, reducing inefficient exploration. Extensive experiments show that our method outperforms existing zero-shot baselines, achieving a 10.1\% improvement in success rate with fewer unnecessary steps.

cs.AI↗

arXiv2026

Spatio-Temporal Wildfire Spread Prediction in Canada using a Video Swin-Hybrid-U-Net and Satellite Imagery

Background: Wildfires in Canada present increasing threats to ecosystems, communities, and infrastructure, demanding accurate forecasting tools to aid mitigation efforts. Existing models often lack scalability or fail to capture temporal dynamics effectively. Aims: This study aims to develop a deep learning framework tailored to Canadian wildfire spread prediction that captures spatio-temporal patterns in environmental data. Methods: We propose a U-Net architecture integrating a Video Swin Transformer encoder with a convolutional decoder to model three-day sequences of meteorological and environmental variables. Data are exclusively sourced from public repositories via Google Earth Engine, ensuring transparency and scalability. The model is trained and tested on a curated dataset of major Canadian wildfire events from 2014 to 2023. Key results: Our approach achieves strong predictive performance by effectively leveraging spatio-temporal attention to forecast next-day fire incidence maps. Conclusions: The model successfully captures complex wildfire dynamics unique to Canada's landscape and temporal variability. Implications: This framework paves the way for advanced spatio-temporal wildfire forecasting research and operational applications using publicly accessible datasets.

cs.CV↗

arXiv2026

DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning

Post-training LLMs with Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), has emerged as a paradigm for enhancing mathematical reasoning. However, standard GRPO relies on scalar correctness rewards that are often non-injective with respect to semantic content: distinct reasoning paths receive identical rewards. This leads to a Diversity-Quality Inconsistency, where the policy collapses into a narrow set of dominant modes while ignoring equally valid but structurally novel strategies. To bridge this gap, we propose Diversity-aware Reward Adjustment (DRA), a theoretically grounded framework that calibrates the reward signal using the semantic density of sampled groups. By leveraging Submodular Mutual Information (SMI), DRA implements an Inverse Propensity Scoring (IPS) mechanism that effectively de-biases the gradient estimation. This creates a repulsive force against redundancy, driving the policy to achieve better coverage of the high-reward landscape. Our method is plug-and-play and integrates seamlessly with GRPO variants. Empirical evaluations on five math benchmarks demonstrate that DRA-GRPO consistently outperforms strong baselines, achieving an average accuracy of 58.2% on DeepSeek-R1-Distill-Qwen-1.5B with only 7,000 training samples and $55 cost, highlighting the critical role of diversity calibration in data-efficient alignment. The code is available at https://github.com/xiwenc1/DRA-GRPO.

cs.CL↗

arXiv2026

Reward Modeling for Multi-Agent Orchestration

Multi-Agent Systems (MAS) built on Large Language Models (LLMs) require effective orchestration to coordinate specialized agents, yet training such orchestrators is hindered by limited supervision and high computational cost. We propose Orchestration Reward Modeling (OrchRM), a self-supervised framework for evaluating orchestration quality without human annotations. OrchRM leverages intermediate artifacts from multi-agent executions to construct win-lose pairs for Bradley-Terry reward model training. Unlike existing MAS test-time scaling and orchestrator training frameworks that rely on costly sub-agent rollouts, OrchRM operates directly at the orchestration level, enabling efficient and high-performing reward-guided orchestrator training and MAS test-time scaling. OrchRM improves training efficiency by up to 10x in token usage while improving MAS test-time scaling performance by up to 8% in accuracy. These gains consistently transfer across multiple domains, including mathematical reasoning, web-based question answering, and multi-hop reasoning, demonstrating orchestration-level reward modeling as a scalable direction for robust multi-agent orchestration. Code will be available at https://github.com/Wang-ML-Lab/OrchRM.

cs.AI↗

arXiv2026

Distortion-Resilient Robotic Imitation Learning for Autonomous Cable Routing

The rapid development of intelligent control methodologies has endowed robots with powerful autonomous intelligence. Cable routing, a ubiquitous foundational task in industry, provides a rigorous benchmark for robotic dexterity and sequential decision-making. In these practical scenarios, image observation distortion frequently occurs. Samples characterized by low-quality image observations often hinder accurate model training, posing challenges to the reliability and accuracy of intelligent control systems. Nevertheless, no dedicated intelligent control solution has been proposed for scenarios of image signal distortion. Meanwhile, image quality information has not been sufficiently exploited to further enhance the performance of intelligent control methodologies. To this end, we propose a novel robotic imitation learning framework that comprises an image quality assessment module, a confidence-based learning mechanism, and a decision-making module, which is designed to maintain high performance even under distorted image observations. In the proposed framework, the image quality assessment module synergizes with the confidence-based learning mechanism to enhance the efficacy of the decision-making module. Specifically, the image quality assessment module is incorporated to extract image quality information from image observations, while the confidence-based learning mechanism adaptively prioritizes challenging samples to improve learning effectiveness. The decision-making module determines appropriate discrete skills or continuous actions. Experimental results demonstrate that our formulated framework enhances the overall performance of the decision-making module.

cs.RO↗

arXiv2026

Rethinking the Flow-Based Gradual Domain Adaptation: A Semi-Dual Optimal Transport Perspective

Gradual domain adaptation (GDA) aims to mitigate domain shift by progressively adapting models from the source domain to the target domain via intermediate domains. However, real intermediate domains are often unavailable or ineffective, necessitating the synthesis of intermediate samples. Flow-based models have recently been used for this purpose by interpolating between source and target distributions. Notably, their training typically relies on sample-based log-likelihood estimation, which can discard useful information and thus degrade GDA performance. The key to addressing this limitation is constructing the intermediate domains via samples directly. To this end, we propose an Entropy-regularized Semi-dual Unbalanced Optimal Transport (E-SUOT) framework to construct intermediate domains. Specifically, we reformulate flow-based GDA as a Lagrangian dual problem and derive an equivalent semi-dual objective that circumvents the need for likelihood estimation. However, the dual problem leads to an unstable min-max training procedure. To alleviate this issue, we further introduce the entropy regularization to convert it into a more stable sequential optimization procedure. Based on this, we propose a novel GDA training framework and provide theoretical analysis in terms of stability and generalization. Finally, extensive experiments are conducted to demonstrate the efficacy of the E-SUOT framework.

cs.LG↗

arXiv2026

The Birational Invariance Of Fundamental Group Schemes

Let $k$ be a field, $f \colon X \to Y$ a birational morphism of integral connected schemes proper over $k$ with $Y$ normal, $x \in X(k)$ lying over $y \in Y(k)$. For Tannakian categories $\mathcal{C}_X \subset \mathfrak{Vect}(X)$ and $\mathcal{C}_Y \subset \mathfrak{Vect}(Y)$, denote by $π(\mathcal{C}_X,x)$ and $π(\mathcal{C}_Y,y)$ the corresponding Tannaka group schemes. We establish a unified Tannakian criteria for the natural homomorphism $π(\mathcal{C}_X,x)\to π(\mathcal{C}_Y,y)$ to be an isomorphism. As applications, for a birational map $X \dashrightarrow Y$ between smooth projective varieties over a perfect field $k$, we prove that there exists a natural isomorphism $π^{*}(X,x)\cong π^{*}(Y,y)$ for any $* \in \{S,N,EN,F,EF,Loc,ELoc,\acute{e}t, E\acute{e}t,uni\}$. In particular, we prove that the induced homomorphism $π^{str}(X,x)\to π^{str}(Y,y)$ is an isomorphism for any birational morphism $ X \rightarrow Y$.

math.AG↗

arXiv2026

Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Tasks

RS-MLLMs enable natural-language understanding and spatial reasoning over earth observation imagery. However, existing models support only a narrow range of sensor types and tasks, yielding a fragmented view of the earth and leaving cross-modal geoscientific knowledge largely unexploited. This work presents Earth-OneVision, a 2B RS-MLLM that unifies six sensor modalities (i.e., optical, SAR, infrared, multispectral, temporal, and video) and cross-sensor fusion across 9 task categories within a single autoregressive framework. Three dedicated mechanisms address three bottlenecks. Full-Granularity Vision-Language Alignment (FGVLA) aligns multi-level visual features with the multi-dimensional language space. Spatial-Linguistic Isomorphic Serialization (SLIS) unifies heterogeneous spatial outputs as autoregressive tokens. Progressive Cross-Modality Adaptation (PCMA) decomposes the compound domain gap into sequential stages, tackling the viewpoint and imaging physics gaps in turn. To support joint training, MMRS-OneVision is constructed with ~34M QA pairs spanning all six sensor modalities and cross-sensor fusion across 9 task categories, substantially exceeding existing RS multimodal instruction datasets. With only 2B parameters, Earth-OneVision achieves competitive or state-of-the-art results across extensive benchmarks, consistently matching or outperforming 4B-72B RS-MLLMs. It achieves 87.52% P@0.5 on the OPT-RSVG testset for optical visual grounding and 80.68% on the SAR VQA benchmark SARLANG-Bench, exceeding 7B models by over 7%. It further achieves 75.74% recall on the BigEarthNet-MS testset for multispectral classification, and 81.94% MCQ accuracy on EarthMind-Bench for cross-modality reasoning.

cs.CV↗

arXiv2026

CRANE: Knowledge Editing for Reasoning MLLMs

The emergence of reasoning multimodal large language models (MLLMs), which generate explicit chain-of-thought (CoT) reasoning before producing answers, has introduced a new challenge for knowledge editing: methods that appear successful under traditional metrics (teacher-forcing accuracy up to 100%) can fail severely when the model's reasoning process is examined (Grounded Success as low as 0%). We identify three failure modes: (1) Structural Collapse, where weight-modifying methods destroy the CoT format; (2) Cognitive Dissonance, where the model's reasoning chain actively rejects the injected edit fact based on visual evidence; and (3) Shallow Internalization, where methods succeed on exact queries but fail on rephrase or multi-hop variants. On reasoning MLLMs, these modes interact: methods that generalize (FT, LoRA) trigger format collapse, while methods without deep modification cannot generalize. To expose these failures, we propose a CoT-aware evaluation protocol and construct ReasonEdit-Bench, with conflict stratification, multi-level probes, and multi-hop portability tests. We propose CRANE, a retrieval-augmented framework that requires no per-edit parameter modification. CRANE combines a modality-aware dual-library retrieval system with a two-phase training strategy: Supervised Fine-Tuning (SFT) for structural initialization, followed by GRPO with a Cognitive Routing Reward that trains the model to arbitrate between visual priors and injected edit facts. On ReasonEdit-Bench, CRANE achieves 96.9% Grounded Success on conflict scenarios and 96.9% intermediate entity usage in multi-hop chains, with 97.6% text-locality and 68.1% image-locality Edit Independence. On the out-of-distribution MMEVOKE benchmark, CRANE reaches 87.0% under gold retrieval.

cs.CV↗

arXiv2026

GraspFoM: Towards Reconstruction-Driven Robotic Grasping with 3D Foundation Priors

Robotic grasping is a fundamental capability in robotic manipulation. Yet grasping remains challenging under partial observations. Reliable grasping depends on both local contact cues and object-level 3D structure. Existing geometry-aware grasping methods recognize the value of reconstruction, but they typically treat geometry as an intermediate prediction rather than a reusable object prior for grasping. In this paper, we present GraspFoM, a unified framework that leverages 3D foundation priors (SAM3D) to build a shared 3D object latent for both reconstruction and grasp pose prediction. Built on this shared object latent, we introduce an anchor-initialized truncated pose-reasoning diffuser that predicts continuous and multimodal grasp poses without directly relying on discrete grasp candidates. We further investigate the interaction between reconstruction and grasping through a reconstruction-aware scorer and a residual latent updater. Reconstruction provides grounded geometric cues, while grasp supervision refines the shared object latent toward grasp-relevant affordances. GraspFoM jointly predicts grasp poses and reconstructs high-fidelity 3D assets in mesh and 3DGS forms. Comprehensive experiments demonstrate that GraspFoM achieves state-of-the-art results on both reconstruction and grasping. Notably, these improvements require only a small number of additional trainable parameters. Component-wise ablation studies also demonstrate the contribution of each component.

cs.RO↗

arXiv2026

AMix-1: A Pathway to Test-Time Scalable Protein Foundation Model

We introduce AMix-1, a powerful protein foundation model built on Bayesian Flow Networks and empowered by a systematic training methodology, encompassing pretraining scaling laws, emergent capability analysis, in-context learning mechanism, and test-time scaling algorithm. To guarantee robust scalability, we establish a predictive scaling law and reveal the progressive emergence of structural understanding via loss perspective, culminating in a strong 1.7-billion model. Building on this foundation, we devise a multiple sequence alignment (MSA)-based in-context learning strategy to unify protein design into a general framework, where AMix-1 recognizes deep evolutionary signals among MSAs and consistently generates structurally and functionally coherent proteins. This framework enables the successful design of a dramatically improved AmeR variant with an up to $50\times$ activity increase over its wild type. Pushing the boundaries of protein engineering, we further empower AMix-1 with an evolutionary test-time scaling algorithm for in silico directed evolution that delivers substantial, scalable performance gains as verification budgets are intensified, laying the groundwork for next-generation lab-in-the-loop protein design.

q-bio.BM↗

arXiv2026

Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions

While Proximal Policy Optimization (PPO) demonstrates strong performance in stationary settings, we show that its standard optimization paradigm struggles in continual and non-stationary environments. The failure does not stem from insufficient model capacity or overly restrictive clipping. Instead, PPO performs persistent, directionally inefficient local updates, which indicates a lack of geometry-aware guidance for accumulating meaningful behavioral change and ultimately hindering transitions toward new behavior patterns. Although divergence-based regularization introduces partial geometric awareness, its monotonically increasing penalties implicitly discourage large policy deviations, even when such shifts are necessary for effective adaptation. To address this limitation, we propose Gaussian Trust Region Policy Optimization (GTR), which reshapes the trust region using a Gaussian kernel. The resulting constraint is bounded and non-monotonic, providing strong local stability while progressively relaxing under sustained high-advantage updates. To further improve robustness, we introduce a Mixture Gaussian Anchor that adapts to recent policy trajectories, reducing variance induced by stale references. GTR is architecture-agnostic and achieves strong performance across games, simulated robotic control, open-world exploration, and language model post-training. These results demonstrate that geometry-aware trust-region design can be a promising direction for robust reinforcement learning in complex non-stationary environments. Our code is available at https://anonymous.4open.science/r/GTR_demo/README.md.

cs.LG↗

arXiv2026

SafeSearch: Automated Red-Teaming of LLM-Based Search Agents

Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new threat surface: unreliable search results can mislead agents into producing unsafe outputs. Real-world incidents and our two in-the-wild observations show that such failures can occur in practice. To study this threat systematically, we propose SafeSearch, an automated red-teaming framework that is scalable, cost-efficient, and lightweight, enabling sandboxed safety evaluation of search agents. Using this, we generate 300 test cases spanning five risk categories (e.g., misinformation and prompt injection) and evaluate three search agent scaffolds across 17 representative LLMs. Our results reveal substantial vulnerabilities in LLM-based search agents, with the highest ASR reaching 90.5% for GPT-4.1-mini in a search-workflow setting. Moreover, we find that common defenses, such as reminder prompting, offer limited protection. Overall, SafeSearch provides a practical way to measure and improve the safety of LLM-based search agents.

cs.AI↗

arXiv2026

Robust Multi-view Clustering against Imperfect Information

Real-world multi-view data always suffer from imperfect information problem, where the view-specific observations are absent (i.e., Incomplete Views, IV) and cross-view correspondences are mismatched (i.e., Noisy Correspondences, NC) for certain instances. As a remedy, numerous IV- and NC-oriented multi-view clustering (MvC) methods have been proposed, which however require either reliable correspondences or sufficiently complete instances, thus stopping short of addressing the imperfect information problem. In contrast, we observe that both IV and NC challenges originate from the same issue of imperfect cross-view counterpart information, where the counterpart of an anchor instance in another view might be either unavailable or unreliable. Based on the observation, we propose a novel robust MvC framework, termed Posterior-guided Latent Counterpart Inference (PLCI), which could handle both IV and NC in a unified manner. Specifically, PLCI formulates the desired cross-view counterpart of each anchor instance as a latent variable, and integrates both instance-level reliability and prototype-level semantic transport to infer the posterior distribution of the latent counterpart. Extensive experiments on six widely-used multi-view datasets against 10 state-of-the-art MvC methods demonstrate the effectiveness of PLCI for tackling the imperfect information problem. The code will be released upon acceptance.

cs.CV↗