arXiv subjects

Zhenyu Huang

Publications and source records attributed to Zhenyu Huang.

At least 19 recordsLinked to original sources

arXiv2026

HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness

Embodied navigation requires agents to ground instructions or object goals in spatial observations and translate plans into successful execution. As multimodal large language models (MLLMs) become increasingly capable, they offer stronger support for navigation without task-specific training; however, improved semantic reasoning alone does not ensure that proposed actions remain consistent with spatial evidence, task progress, and execution outcomes. We introduce HarnessVLN, a zero-shot, training-free framework that unifies instruction-following and object-goal navigation through a shared Agent Harness. The Harness coordinates perception, memory, and execution tools through a unified interface, validating planner proposals for evidential support, geometric feasibility, and subgoal consistency before dispatch. It jointly manages hierarchical event memory and a persistent Spatiotemporal Graph to track task progress, preserve spatial evidence, and contextualize failures. Structured execution feedback updates this shared state, guiding subsequent planning, recovery, and termination. Across R2R, RxR, HM3D-v2, and HM3D-OVON, HarnessVLN achieves success rates of 60.8%, 53.9%, 76.0%, and 59.3%, respectively, outperforming prior training-free state-of-the-art methods. Humanoid robot deployment further demonstrates its applicability to both navigation tasks in real-world environments. The project page is available at https://agibot-harnessvln.netlify.app/.

cs.RO↗

arXiv2026

STEGNav: Spatio-Temporal Event Graph Reasoning for Multimodal Lifelong Object Navigation

Multimodal lifelong navigation requires an agent to autonomously explore unseen environments while sequentially completing navigation tasks specified by object categories, language descriptions, or reference images. Existing methods primarily accomplish these tasks by constructing state-centric semantic scene graphs. By treating scene graphs as persistent repositories of semantic observations, these methods struggle to distinguish similar instances, jointly represent semantic targets and exploration frontiers, and effectively exploit navigation memory and trajectory experience. To address these limitations, we propose Spatio-Temporal Event Graph Navigation (STEGNav), a training-free framework that extends conventional scene graphs into spatio-temporal event graphs along complementary spatial and temporal axes. The spatial axis performs query-conditioned instance grounding and jointly represents semantic targets and occupancy-aware exploration frontiers characterized by reachability, path cost, and exploration utility. The temporal axis employs trajectory-aware dual-window memory to retain recent decision--trajectory events and verified cross-subtask navigation outcomes. A VLM-based navigation agent reasons over the resulting spatio-temporal event graph and selects either a target instance or an exploration frontier as its next navigation goal. STEGNav achieves 66.3% SR and 39.7 SPL on GOAT-Bench, as well as SR scores of 64.0% and 69.4% on HM3Dv1 and HM3Dv2, respectively. Ablation studies and error analyses validate the complementary effects of the two axes, demonstrating that event-driven spatio-temporal representations improve navigation reliability and cross-subtask experience reuse.

cs.RO↗

arXiv2026

Robust Code RL via Faulty-Code-Driven Test case Synthesis and Dense Reward Shaping

Reinforcement Learning from Verifiable Rewards (RLVR) is pivotal for enhancing LLM code generation, yet its efficacy is often hindered by insufficient test case coverage, leading to reward hacking and policy degradation. To address this, we propose RobustTests, a framework featuring a faulty-code-driven test case synthesis strategy. By leveraging "near-correct" faulty codes, RobustTests captures latent logical discrepancies and employs validator agents with behavioral feature clustering to filter invalid or redundant test cases. Additionally, a stepwise dense reward function based on pass rates is introduced to mitigate false negatives and enhance training robustness. Using this pipeline, we construct an augmented version of the CodeContests+ dataset with superior diagnostic utility. Experimental results show that RL fine-tuning of Qwen3-32B via RobustTests achieves a 3% absolute gain on LiveCodeBench, demonstrating its effectiveness in advancing LLM code generation proficiency. Codes and data are available at https://huggingface.co/datasets/sid6/RobustTests.

cs.AI↗

arXiv2026

DocPO: Advancing Document Policy Optimization via Tailored Step-Aware Rewards

Reinforcement learning (RL) for document parsing often relies on reference-based rewards rooted in edit distance (e.g., tree edit distance), yet it remains hard to optimize in the high-accuracy regime because such rewards become weakly discriminative: near-correct outputs receive very similar scores, providing limited learning signal for hard cases. We propose Step-Aware Annealing (SAA), a plug-and-play reward sharpening mechanism that progressively increases reward curvature during training, amplifying subtle quality differences among high-scoring samples while preserving stability in early learning. Built on SAA, we introduce DocPO, a document policy optimization framework with element-specific, reference-based rewards anchored by edit-distance signals: normalized string edit distance (NED) for text, tree edit distance similarity (TEDS) for tables, and a hybrid Rubric+edit reward for formulas. Experiments on OmniDocBench and DocElemHard show that SAA consistently improves GRPO-style RL across document elements over non-annealed rewards, without requiring additional human supervision for reward construction.

cs.CV↗

arXiv2026

Mean field error estimate of the random batch method for vortex blob dynamics for the 2D Navier--Stokes Equation

We propose and analyze the random batch vortex blob method for the 2D Navier--Stokes equation in vorticity form on the whole plane. The vortex blob method is based on an interacting particle system of $N$ particles with computational complexity of $O(N^2)$, which is reduced to $O(N)$ by the random batch method \cite{JinLiLiu2020}. Our main result is a quantitative law level mean field error estimate whose dependence on the blob radius remains algebraic. We treat the two main error mechanisms separately. The random batch error is controlled through a locally coupled auxiliary partition, a symmetric law comparison, and Fisher-information dissipation. The mean field fluctuation is estimated by exploiting the oddness and divergence-free structure of the Biot--Savart kernel. For smooth, strictly positive initial vorticity, we prove on every finite time interval a normalized relative-entropy bound of order $ O\!\left(\varepsilon^{-4}τ^2+N^{-1} \right), $ with constants independent of $N$, $τ$, and $varepsilon$. Here $τ$ is the batch refreshing interval and $\varepsilon$ is the blob radius. As a consequence, the fixed-particle marginals converge strongly in $L^1$ to tensor products of the regularized vorticity solution when $N\to\infty$ and $\varepsilon^{-2}τ\to 0$.

math.NA↗

arXiv2026

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports

Coding agents powered by large language models (LLMs) are increasingly adopted in software engineering (SWE) scenarios, capable of fixing a specific bug in large-scale codebase. However, existing SWE benchmarks typically assume that high-quality issue reports with detailed information are always available, which is easily violated in practice due to the complexity of report acquisition and curation. To address this, we introduce Active-SWE, a benchmark for evaluating coding agents on proactively discovering and fixing multiple bugs without report guidance, covering 1,663 tasks across six bug categories and eight languages. Beyond shifting the focus from existing reactive bug fixing to proactive bug fixing, Active-SWE enables a more in-depth evaluation by expanding the scope from fixing a specific recorded bug to multiple-bug fixing and potential bug discovery scenarios. To construct Active-SWE, we propose a novel difficulty-aware task formulation pipeline with a dual-track evaluation framework, facilitating comprehensive evaluation of proactive bug-fixing capability. Extensive experiments reveal that most state-of-the-art coding agents struggle with proactive bug-fixing tasks, demonstrating limited performance in locating and resolving recorded bugs, handling multiple bug fixing scenarios, and discovering valid potential bugs.

cs.SE↗

arXiv2026

MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs

Systematically evaluating Multimodal Large Language Models (MLLMs) is essential for advancing Artificial General Intelligence (AGI). Yet existing benchmarks remain inadequate for rigorously measuring their reasoning capabilities under multi-criteria constraints. To address this gap, we introduce MapTab, a multimodal benchmark designed to assess holistic multi-criteria reasoning in MLLMs through route-planning tasks. MapTab requires models to perceive and ground visual information from map images while integrating route attributes, such as Time and Price, from structured tables. It covers two scenarios: Metromap, spanning metro networks in 160 cities across 52 countries, and Travelmap, featuring 168 representative tourist attractions from 19 countries. Overall, MapTab includes 328 images, 196,800 route-planning queries, and 3,936 QA queries, incorporating four key criteria: Time, Price, Comfort, and Reliability. Extensive evaluations of 21 representative MLLMs show that current models still struggle with multicriteria multimodal reasoning. Notably, when visual perception is unreliable, multimodal reasoning can even underperform unimodal approaches. MapTab therefore offers a challenging and realistic testbed for systematically evaluating and advancing MLLMs across core perception, integration, numerical comparison, and route planning capabilities.

cs.LG↗

arXiv2026

MORE: A Multilingual Document Parsing Benchmark and Evaluation

Multilingual documents encapsulate rich regional cultures, scientific discoveries, and historical records. Parsing this content into structured, machine-readable formats is critical for unlocking global knowledge. However, existing benchmarks predominantly focus on high-resource languages like English and Chinese, creating an evaluation blind spot concerning model performance on other languages. While recent Vision-Language Models (VLMs) claim support for hundreds of languages, the lack of ground truth makes it impossible to empirically verify these capabilities. To bridge this gap, we introduce MORE, a large-scale benchmark designed for multilingual document parsing evaluation. MORE distinguishes itself through three key dimensions: (1) Unprecedented Scale: It covers 149 languages, making it the most linguistically diverse benchmark to date; (2) Structural Complexity: Unlike previous works, it extends evaluation beyond plain text to include structural elements such as code blocks, tables, and catalogs; and (3) Data Authenticity: All samples are curated from real-world documents via a model-assisted, human-refined annotation pipeline. We evaluate state-of-the-art models using MORE, establishing new performance baselines for long-tail languages and validating the benchmark's effectiveness in diagnosing model capabilities in realistic, diverse scenarios. The MORE dataset will be available at https://github.com/zimoqingfeng/MORE.

cs.CV↗

arXiv2026

An Algebraic Method for Full-Rank Characterization in Binary Linear Coding

In this paper, we develop a characteristic set (CS)-based method for deriving full-rank equivalence conditions of symbolic matrices over the binary field. Such full-rank conditions are of fundamental importance for many linear coding problems in communication and information theory. Building on the developed CS-based method, we present an algorithm called Binary Characteristic Set for Full Rank (BCSFR), which efficiently derives the full-rank equivalence conditions as the zeros of a series of characteristic sets. In other words, the BCSFR algorithm can characterize all feasible linear coding schemes for certain linear coding problems (e.g., linear network coding and distributed storage coding), where full-rank constraints are imposed on several symbolic matrices to guarantee decodability or other properties of the codes. The derived equivalence conditions can be used to simplify the optimization of coding schemes, since the intractable full-rank constraints in the optimization problem are explicitly characterized by simple triangular-form equality constraints.

cs.IT↗

arXiv2025

Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model

We present Ring-1T, the first open-source, state-of-the-art thinking model with a trillion-scale parameter. It features 1 trillion total parameters and activates approximately 50 billion per token. Training such models at a trillion-parameter scale introduces unprecedented challenges, including train-inference misalignment, inefficiencies in rollout processing, and bottlenecks in the RL system. To address these, we pioneer three interconnected innovations: (1) IcePop stabilizes RL training via token-level discrepancy masking and clipping, resolving instability from training-inference mismatches; (2) C3PO++ improves resource utilization for long rollouts under a token budget by dynamically partitioning them, thereby obtaining high time efficiency; and (3) ASystem, a high-performance RL framework designed to overcome the systemic bottlenecks that impede trillion-parameter model training. Ring-1T delivers breakthrough results across critical benchmarks: 93.4 on AIME-2025, 86.72 on HMMT-2025, 2088 on CodeForces, and 55.94 on ARC-AGI-1. Notably, it attains a silver medal-level result on the IMO-2025, underscoring its exceptional reasoning capabilities. By releasing the complete 1T parameter MoE model to the community, we provide the research community with direct access to cutting-edge reasoning capabilities. This contribution marks a significant milestone in democratizing large-scale reasoning intelligence and establishes a new baseline for open-source model performance.

cs.CL↗

arXiv2025

Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs

We present Ring-lite, a Mixture-of-Experts (MoE)-based large language model optimized via reinforcement learning (RL) to achieve efficient and robust reasoning capabilities. Built upon the publicly available Ling-lite model, a 16.8 billion parameter model with 2.75 billion activated parameters, our approach matches the performance of state-of-the-art (SOTA) small-scale reasoning models on challenging benchmarks (e.g., AIME, LiveCodeBench, GPQA-Diamond) while activating only one-third of the parameters required by comparable models. To accomplish this, we introduce a joint training pipeline integrating distillation with RL, revealing undocumented challenges in MoE RL training. First, we identify optimization instability during RL training, and we propose Constrained Contextual Computation Policy Optimization(C3PO), a novel approach that enhances training stability and improves computational throughput via algorithm-system co-design methodology. Second, we empirically demonstrate that selecting distillation checkpoints based on entropy loss for RL training, rather than validation metrics, yields superior performance-efficiency trade-offs in subsequent RL training. Finally, we develop a two-stage training paradigm to harmonize multi-domain data integration, addressing domain conflicts that arise in training with mixed dataset. We will release the model, dataset, and code.

cs.CL↗

arXiv2025

Holistic Capability Preservation: Towards Compact Yet Comprehensive Reasoning Models

This technical report presents Ring-Lite-Distill, a lightweight reasoning model derived from our open-source Mixture-of-Experts (MoE) Large Language Models (LLMs) Ling-Lite. This study demonstrates that through meticulous high-quality data curation and ingenious training paradigms, the compact MoE model Ling-Lite can be further trained to achieve exceptional reasoning capabilities, while maintaining its parameter-efficient architecture with only 2.75 billion activated parameters, establishing an efficient lightweight reasoning architecture. In particular, in constructing this model, we have not merely focused on enhancing advanced reasoning capabilities, exemplified by high-difficulty mathematical problem solving, but rather aimed to develop a reasoning model with more comprehensive competency coverage. Our approach ensures coverage across reasoning tasks of varying difficulty levels while preserving generic capabilities, such as instruction following, tool use, and knowledge retention. We show that, Ring-Lite-Distill's reasoning ability reaches a level comparable to DeepSeek-R1-Distill-Qwen-7B, while its general capabilities significantly surpass those of DeepSeek-R1-Distill-Qwen-7B. The models are accessible at https://huggingface.co/inclusionAI

cs.LG↗

arXiv2024

TemporalPaD: a reinforcement-learning framework for temporal feature representation and dimension reduction

Recent advancements in feature representation and dimension reduction have highlighted their crucial role in enhancing the efficacy of predictive modeling. This work introduces TemporalPaD, a novel end-to-end deep learning framework designed for temporal pattern datasets. TemporalPaD integrates reinforcement learning (RL) with neural networks to achieve concurrent feature representation and feature reduction. The framework consists of three cooperative modules: a Policy Module, a Representation Module, and a Classification Module, structured based on the Actor-Critic (AC) framework. The Policy Module, responsible for dimensionality reduction through RL, functions as the actor, while the Representation Module for feature extraction and the Classification Module collectively serve as the critic. We comprehensively evaluate TemporalPaD using 29 UCI datasets, a well-known benchmark for validating feature reduction algorithms, through 10 independent tests and 10-fold cross-validation. Additionally, given that TemporalPaD is specifically designed for time series data, we apply it to a real-world DNA classification problem involving enhancer category and enhancer strength. The results demonstrate that TemporalPaD is an efficient and effective framework for achieving feature reduction, applicable to both structured data and sequence datasets. The source code of the proposed TemporalPaD is freely available as supplementary material to this article and at http://www.healthinformaticslab.org/supp/.

cs.LG↗

arXiv2024

Mean field error estimate of the random batch method for large interacting particle system

The random batch method (RBM) proposed in [Jin et al., J. Comput. Phys., 400(2020), 108877] for large interacting particle systems is an efficient with linear complexity in particle numbers and highly scalable algorithm for $N$-particle interacting systems and their mean-field limits when $N$ is large. We consider in this work the quantitative error estimate of RBM toward its mean-field limit, the Fokker-Planck equation. Under mild assumptions, we obtain a uniform-in-time $O(τ^2 + 1/N)$ bound on the scaled relative entropy between the joint law of the random batch particles and the tensorized law at the mean-field limit, where $τ$ is the time step size and $N$ is the number of particles. Therefore, we improve the existing rate in discretization step size from $O(\sqrtτ)$ to $O(τ)$ in terms of the Wasserstein distance.

math.NA↗

arXiv2024

Multi-granularity Correspondence Learning from Long-term Noisy Videos

Existing video-language studies mainly focus on learning short video clips, leaving long-term temporal dependencies rarely explored due to over-high computational cost of modeling long videos. To address this issue, one feasible solution is learning the correspondence between video clips and captions, which however inevitably encounters the multi-granularity noisy correspondence (MNC) problem. To be specific, MNC refers to the clip-caption misalignment (coarse-grained) and frame-word misalignment (fine-grained), hindering temporal learning and video understanding. In this paper, we propose NOise Robust Temporal Optimal traNsport (Norton) that addresses MNC in a unified optimal transport (OT) framework. In brief, Norton employs video-paragraph and clip-caption contrastive losses to capture long-term dependencies based on OT. To address coarse-grained misalignment in video-paragraph contrast, Norton filters out the irrelevant clips and captions through an alignable prompt bucket and realigns asynchronous clip-caption pairs based on transport distance. To address the fine-grained misalignment, Norton incorporates a soft-maximum operator to identify crucial words and key frames. Additionally, Norton exploits the potential faulty negative samples in clip-caption contrast by rectifying the alignment target with OT assignment to ensure precise temporal modeling. Extensive experiments on video retrieval, videoQA, and action segmentation verify the effectiveness of our method. Code is available at https://lin-yijie.github.io/projects/Norton.

cs.CV↗

arXiv2022

Robust Domain Adaptation for Machine Reading Comprehension

Most domain adaptation methods for machine reading comprehension (MRC) use a pre-trained question-answer (QA) construction model to generate pseudo QA pairs for MRC transfer. Such a process will inevitably introduce mismatched pairs (i.e., noisy correspondence) due to i) the unavailable QA pairs in target documents, and ii) the domain shift during applying the QA construction model to the target domain. Undoubtedly, the noisy correspondence will degenerate the performance of MRC, which however is neglected by existing works. To solve such an untouched problem, we propose to construct QA pairs by additionally using the dialogue related to the documents, as well as a new domain adaptation method for MRC. Specifically, we propose Robust Domain Adaptation for Machine Reading Comprehension (RMRC) method which consists of an answer extractor (AE), a question selector (QS), and an MRC model. Specifically, RMRC filters out the irrelevant answers by estimating the correlation to the document via the AE, and extracts the questions by fusing the candidate questions in multiple rounds of dialogue chats via the QS. With the extracted QA pairs, MRC is fine-tuned and provides the feedback to optimize the QS through a novel reinforced self-training method. Thanks to the optimization of the QS, our method will greatly alleviate the noisy correspondence problem caused by the domain shift. To the best of our knowledge, this could be the first study to reveal the influence of noisy correspondence in domain adaptation MRC models and show a feasible way to achieve robustness to mismatched pairs. Extensive experiments on three datasets demonstrate the effectiveness of our method.

cs.LG↗

arXiv2021

Quantifying Bounds of Model Gap for Synchronous Generators

In practice, uncertainties in parameters and model structures always cause a gap between a model and the corresponding physical entity. Hence, to evaluate the performance of a model, the bounds of this gap must be assessed. In this paper, we propose a trajectory-sensitivity--based approach to quantify the bounds of the gap. The trajectory sensitivity is expressed as a linear time-varying system. We thus first derive several bounds for a general linear time-varying system in different scenarios. The derived bounds are then applied to obtain bounds of the model gap for generator plant models with different types of structural information, e.g., models of different orders. Case studies are carried out to show the efficacy of the bounds through synchronous generator models on different accuracy levels.

math.OC↗

arXiv2020

Dynamic State Estimation for Power System Control and Protection

Dynamic state estimation (DSE) accurately tracks the dynamics of a power system and provides the evolution of the system state in real-time. This paper focuses on the control and protection applications of DSE, comprehensively presenting different facets of control and protection challenges arising in modern power systems. It is demonstrated how these challenges are effectively addressed with DSE-enabled solutions. As precursors to these solutions, reformulation of DSE considering both synchrophasor and sampled value measurements and comprehensive comparisons of DSE and observers have been presented. The usefulness and necessity of DSE based solutions in ensuring system stability, reliable protection and security, and resilience by revamping of control and protection methods are shown through examples, practical applications, and suggestions for further development.

eess.SY↗