arXiv subjects

Hongwei Wang

Publications and source records attributed to Hongwei Wang.

At least 37 records · Page 2Linked to original sources

arXiv2026

GAM: Hierarchical Graph-based Agentic Memory for LLM Agents

To sustain coherent long-term interactions, Large Language Model (LLM) agents must navigate the tension between acquiring new information and retaining prior knowledge. Current unified stream-based memory systems facilitate context updates but remain vulnerable to interference from transient noise. Conversely, discrete structured memory architectures provide robust knowledge retention but often struggle to adapt to evolving narratives. To address this, we propose GAM, a hierarchical Graph-based Agentic Memory framework that explicitly decouples memory encoding from consolidation to effectively resolve the conflict between rapid context perception and stable knowledge retention. By isolating ongoing dialogue in an event progression graph and integrating it into a topic associative network only upon semantic shifts, our approach minimizes interference while preserving long-term consistency. Additionally, we introduce a graph-guided, multi-factor retrieval strategy to enhance context precision. Experiments on LoCoMo and LongDialQA indicate that our method consistently outperforms state-of-the-art baselines in both reasoning accuracy and efficiency.

cs.AI↗

arXiv2026

SENSE: Semantic Embedding Navigation with Soft-gated Evaluation for Retrieval-based Speculative Decoding

Speculative Decoding (SD) accelerates Large Language Model (LLM) inference by employing a lightweight draft model to propose candidate tokens, which are verified in parallel by the target model, without compromising generation quality. While Retrieval-based Speculative Decoding (RSD) is favored for its plug-and-play versatility, its potential is impeded by rigid lexical dependencies, rendering both retrieval and verification brittle to surface-level variations. To address this, we propose SENSE (Semantic Embedding Navigation with Soft-gated Evaluation). By anchoring retrieval on the hidden states of the target model, SENSE establishes robust semantic alignment, which empowers the Soft-gated Evaluation module to validate semantic equivalence rather than surface forms. To ensure rigorous benchmarking, we deconstruct existing methods into atomic primitives within a unified framework, facilitating granular, component-level comparison. Extensive experiments across diverse domains demonstrate that SENSE outperforms multiple baselines on the LLaMA and Qwen families, attaining up to 4.09 mean acceptance length and 3.26x speedup, while preserving generation quality. Our code will be released upon publication.

cs.CL↗

arXiv2026

NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3)

In this paper, we present a comprehensive overview of the NTIRE 2026 3rd Restore Any Image Model (RAIM) challenge, with a specific focus on Track 3: AI Flash Portrait. Despite significant advancements in deep learning for image restoration, existing models still encounter substantial challenges in real-world low-light portrait scenarios. Specifically, they struggle to achieve an optimal balance among noise suppression, detail preservation, and faithful illumination and color reproduction. To bridge this gap, this challenge aims to establish a novel benchmark for real-world low-light portrait restoration. We comprehensively evaluate the proposed algorithms utilizing a hybrid evaluation system that integrates objective quantitative metrics with rigorous subjective assessment protocols. For this competition, we provide a dataset containing 800 groups of real-captured low-light portrait data. Each group consists of a 1K-resolution low-light input image, a 1K ground truth (GT), and a 1K person mask. This challenge has garnered widespread attention from both academia and industry, attracting over 100 participating teams and receiving more than 3,000 valid submissions. This report details the motivation behind the challenge, the dataset construction process, the evaluation metrics, and the various phases of the competition. The released dataset and baseline code for this track are publicly available from the same \href{https://github.com/zsn1434/AI_Flash-BaseLine/tree/main}{GitHub repository}, and the official challenge webpage is hosted on \href{https://www.codabench.org/competitions/12885/}{CodaBench}.

cs.CV↗

arXiv2026

Near-Field Wideband Channel Estimation for Extremely Large-Scale RIS-Aided Communication Systems

This paper studies wideband channel estimation for OFDM systems assisted by extremely large RIS (XL-RIS). Due to the large aperture of XL-RISs, the user equipment may operate in the near-field region, while the base station-XL-RIS link remains in the far field, leading to a cascaded channel with hybrid near-field and far-field characteristics. Moreover, wideband effects further complicate channel estimation in mmWave/THz systems. To address these challenges, we propose a frequency-independent orthogonal dictionary by augmenting the discrete Fourier transform (DFT) matrix with additional parameters, which enables an efficient representation of the wideband cascaded channel using a two-dimensional block-sparse structure. Based on this property, the considered channel estimation problem is effectively solved within a tailored compressed sensing framework. Simulation results demonstrate that the proposed method significantly outperforms conventional polar-domain channel estimation approaches in terms of estimation accuracy.

eess.SP↗

arXiv2026

Near-Field Channel Estimation for mmWave/THz Communications with Extremely Large-Scale UPAs

Extremely large antenna arrays (ELAAs) are widely adopted in mmWave/THz communications to compensate for the severe path loss, wherein the channel estimation remains a significant challenge since the Rayleigh distance of ELAAs stretches to tens or even hundreds of meters and the near-field channel model should be considered. Existing polar-domain based methods and block-sparse based methods are originally devised for Uniform Linear Arrays (ULAs) near-field channel estimation. The polar-domain based method can be applied to Uniform Planar Arrays (UPAs), but it behaves plain since it ignores the specific sparsity structure of the UPA near-field channels. Meanwhile, the block-sparse based method cannot be extended to the UPA scenarios directly. To address these issues, we first reformulate the original UPA near-field channel as an outer product of two ULA near-field channels and we construct a modified two-dimensional DFT (2D-DFT) dictionary for it. With the proposed dictionary, we further prove that the UPA near-field channel admits a 2D block-sparse structure. Leveraging this specific sparse structure, we solve the channel estimation problem with the 2D Pattern-Coupled Sparse Bayesian Learning (2D-PCSBL) algorithm. Simulation results show that the proposed approach outperforms conventional existing methods while maintaining a comparable computational complexity.

eess.SP↗

arXiv2026

Experimental Study of Bremsstrahlung Gamma Ray Emission and Short-Range Correlations in $^{124}$Sn+$^{124}$Sn Collisions at 25 MeV/u

Short-range correlation (SRC) in nuclei refers to nucleons forming temporally correlated pairs in close proximity, giving rise to the high momentum of the nucleons beyond the Fermi surface. It has been reported that bremsstrahlung $γ$ production from neutron-proton process in heavy-ion reactions provides a potential probe to the SRC abundance in nuclei. In this paper, we present in detail the precision measurement of bremsstrahlung $γ$-rays in $\rm ^{124}Sn$+$\rm ^{124}Sn$ reactions at 25 MeV/u using the Compact Spectrometer for Heavy IoN Experiment (CSHINE). A comprehensive experimental and analysis framework is established to ensure the reliability and robustness of the extracted results. Background contributions are evaluated and subtracted using independent methods, and the consistency of the analysis is systematically validated. By comparing the experimental $γ$ spectrum with the Isospin-dependent Boltzmann-Uehling-Uhlenbeck simulations, the high momentum tail (HMT) fraction of $R_{\rm HMT}=(20 \pm 3)\%$ is derived in $^{124}$Sn nuclei. This work provides a detailed and validated experimental framework for extracting SRC information from bremsstrahlung $γ$-ray emission and demonstrates the feasibility of studying nucleon SRCs with high precision in low-energy heavy-ion collisions.

nucl-ex↗

arXiv2026

Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems

While Multi-Agent Systems (MAS) excel at complex tasks, their growing autonomy with operational complexity often leads to critical inefficiencies, such as excessive token consumption and failures arising from misinformation. Existing methods primarily focus on post-hoc failure attribution, lacking proactive, real-time interventions to enhance robustness and efficiency. To this end, we introduce SupervisorAgent, a lightweight and modular framework for runtime, adaptive supervision that operates without altering the base agent's architecture. Triggered by an LLM-free adaptive filter, SupervisorAgent intervenes at critical junctures to proactively correct errors, guide inefficient behaviors, and purify observations. On the challenging GAIA benchmark, SupervisorAgent reduces the token consumption of the Smolagent framework by an average of 29.68% without compromising its success rate. Extensive experiments across five additional benchmarks (math reasoning, code generation, and question answering) and various SoTA foundation models validate the broad applicability and robustness of our approach.

cs.MA↗

arXiv2026

See, Act, Adapt: Active Perception for Unsupervised Cross-Domain Visual Adaptation via Personalized VLM-Guided Agent

Pre-trained perception models excel in generic image domains but degrade significantly in novel environments like indoor scenes. The conventional remedy is fine-tuning on downstream data which incurs catastrophic forgetting of prior knowledge and demands costly, scene-specific annotations. We propose a paradigm shift through Sea$^2$ (See, Act, Adapt): rather than adapting the perception modules themselves, we adapt how they are deployed through an intelligent pose-control agent. Sea$^2$ keeps all perception modules frozen, requiring no downstream labels during training, and uses only scalar perceptual feedback to navigate the agent toward informative viewpoints. Specially, we transform a vision-language model (VLM) into a low-level pose controller through a two-stage training pipeline: first fine-tuning it on rule-based exploration trajectories that systematically probe indoor scenes, and then refining the policy via unsupervised reinforcement learning that constructs rewards from the perception module's outputs and confidence. Unlike prior active perception methods that couple exploration with specific models or collect data for retraining them, Sea$^2$ directly leverages off-the-shelf perception models for various tasks without the need for retraining. We conducted experiments on three visual perception tasks, including visual grounding, segmentation and 3D box estimation, with performance improvements of 13.54%, 15.92% and 27.68% respectively on dataset ReplicaCAD.

cs.CV↗

arXiv2026

GLM-5: from Vibe Coding to Agentic Engineering

We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (ARC) capabilities of its predecessor, GLM-5 adopts DSA to significantly reduce training and inference costs while maintaining long-context fidelity. To advance model alignment and autonomy, we implement a new asynchronous reinforcement learning infrastructure that drastically improves post-training efficiency by decoupling generation from training. Furthermore, we propose novel asynchronous agent RL algorithms that further improve RL quality, enabling the model to learn from complex, long-horizon interactions more effectively. Through these innovations, GLM-5 achieves state-of-the-art performance on major open benchmarks. Most critically, GLM-5 demonstrates unprecedented capability in real-world coding tasks, surpassing previous baselines in handling end-to-end software engineering challenges. Code, models, and more information are available at https://github.com/zai-org/GLM-5.

cs.LG↗

arXiv2026

High-Precision Measurement of D($γ$, $n$)$p$ Photodisintegration Reaction and Implications for Big-Bang Nucleosynthesis

We report on a high-precision measurement of the D($γ$,\,$n$)$p$ photodisintegration reaction at the newly commissioned Shanghai Laser Electron Gamma Source (SLEGS), employing a quasi-monochromatic $γ$-ray beam from Laser Compton Scattering. The cross sections were determined over $E_γ$=2.327--7.089 MeV, achieving up to a factor of 2.2 improvement in precision near the neutron separation threshold. Combined with previous data in a global Markov chain Monte Carlo (MCMC) analysis using dibaryon effective field theory, we obtained the unprecedentedly precise $p$($n$,\,$γ$)D cross sections and thermonuclear rate, with a precision up to $\approx$4 times higher than previous evaluations. Implemented in a standard Big-Bang Nucleosynthesis (BBN) framework, this new rate decreases uncertainty of the key cosmological parameter of baryon density $Ω_b h^2$ by up to $\approx$16\% relative to the LUNA result. A residual $\approx$1.2$σ$ tension between $Ω_b h^2$ constrained from primordial D/H observations and CMB measurements persists, highlighting the need for improved $dd$ reaction rates and offering potential hints of new physics beyond the standard model of cosmology.

nucl-ex↗

arXiv2026

MAU-GPT: Enhancing Multi-type Industrial Anomaly Understanding via Anomaly-aware and Generalist Experts Adaptation

As industrial manufacturing scales, automating fine-grained product image analysis has become critical for quality control. However, existing approaches are hindered by limited dataset coverage and poor model generalization across diverse and complex anomaly patterns. To address these challenges, we introduce MAU-Set, a comprehensive dataset for Multi-type industrial Anomaly Understanding. It spans multiple industrial domains and features a hierarchical task structure, ranging from binary classification to complex reasoning. Alongside this dataset, we establish a rigorous evaluation protocol to facilitate fair and comprehensive model assessment. Building upon this foundation, we further present MAU-GPT, a domain-adapted multimodal large model specifically designed for industrial anomaly understanding. It incorporates a novel AMoE-LoRA mechanism that unifies anomaly-aware and generalist experts adaptation, enhancing both understanding and reasoning across diverse defect classes. Extensive experiments show that MAU-GPT consistently outperforms prior state-of-the-art methods across all domains, demonstrating strong potential for scalable and automated industrial inspection.

cs.CV↗

arXiv2026

DynaHOI: Benchmarking Hand-Object Interaction for Dynamic Target

Most existing hand motion generation benchmarks for hand-object interaction (HOI) focus on static objects, leaving dynamic scenarios with moving targets and time-critical coordination largely untested. To address this gap, we introduce the DynaHOI-Gym, a unified online closed-loop platform with parameterized motion generators and rollout-based metrics for dynamic capture evaluation. Built on DynaHOI-Gym, we release DynaHOI-10M, a large-scale benchmark with 10M frames and 180K hand capture trajectories, whose target motions are organized into 8 major categories and 22 fine-grained subcategories. We also provide a simple observe-before-act baseline (ObAct) that integrates short-term observations with the current frame via spatiotemporal attention to predict actions, achieving an 8.1% improvement in location success rate.

cs.CV↗

arXiv2026

When Rules Fall Short: Agent-Driven Discovery of Emerging Content Issues in Short Video Platforms

Trends on short-video platforms evolve at a rapid pace, with new content issues emerging every day that fall outside the coverage of existing annotation policies. However, traditional human-driven discovery of emerging issues is too slow, which leads to delayed updates of annotation policies and poses a major challenge for effective content governance. In this work, we propose an automatic issue discovery method based on multimodal LLM agents. Our approach automatically recalls short videos containing potential new issues and applies a two-stage clustering strategy to group them, with each cluster corresponding to a newly discovered issue. The agent then generates updated annotation policies from these clusters, thereby extending coverage to these emerging issues. Our agent has been deployed in the real system. Both offline and online experiments demonstrate that this agent-based method significantly improves the effectiveness of emerging-issue discovery (with an F1 score improvement of over 20%) and enhances the performance of subsequent issue governance (reducing the view count of problematic videos by approximately 15%). More importantly, compared to manual issue discovery, it greatly reduces time costs and substantially accelerates the iteration of annotation policies.

cs.CV↗

arXiv2025

Adaptive Hopfield Network: Rethinking Similarities in Associative Memory

Associative memory models are content-addressable memory systems fundamental to biological intelligence and are notable for their high interpretability. However, existing models evaluate the quality of retrieval based on proximity, which cannot guarantee that the retrieved pattern has the strongest association with the query, failing correctness. We reframe this problem by proposing that a query is a generative variant of a stored memory pattern, and define a variant distribution to model this subtle context-dependent generative process. Consequently, correct retrieval should return the memory pattern with the maximum a posteriori probability of being the query's origin. This perspective reveals that an ideal similarity measure should approximate the likelihood of each stored pattern generating the query in accordance with variant distribution, which is impossible for fixed and pre-defined similarities used by existing associative memories. To this end, we develop adaptive similarity, a novel mechanism that learns to approximate this insightful but unknown likelihood from samples drawn from context, aiming for correct retrieval. We theoretically prove that our proposed adaptive similarity achieves optimal correct retrieval under three canonical and widely applicable types of variants: noisy, masked, and biased. We integrate this mechanism into a novel adaptive Hopfield network (A-Hop), and empirical results show that it achieves state-of-the-art performance across diverse tasks, including memory retrieval, tabular classification, image classification, and multiple instance learning.

cs.LG↗

arXiv2025

Understanding Dynamic Scenes in Ego Centric 4D Point Clouds

Understanding dynamic 4D scenes from an egocentric perspective-modeling changes in 3D spatial structure over time-is crucial for human-machine interaction, autonomous navigation, and embodied intelligence. While existing egocentric datasets contain dynamic scenes, they lack unified 4D annotations and task-driven evaluation protocols for fine-grained spatio-temporal reasoning, especially on motion of objects and human, together with their interactions. To address this gap, we introduce EgoDynamic4D, a novel QA benchmark on highly dynamic scenes, comprising RGB-D video, camera poses, globally unique instance masks, and 4D bounding boxes. We construct 927K QA pairs accompanied by explicit Chain-of-Thought (CoT), enabling verifiable, step-by-step spatio-temporal reasoning. We design 12 dynamic QA tasks covering agent motion, human-object interaction, trajectory prediction, relation understanding, and temporal-causal reasoning, with fine-grained, multidimensional metrics. To tackle these tasks, we propose an end-to-end spatio-temporal reasoning framework that unifies dynamic and static scene information, using instance-aware feature encoding, time and camera encoding, and spatially adaptive down-sampling to compress large 4D scenes into token sequences manageable by LLMs. Experiments on EgoDynamic4D show that our method consistently outperforms baselines, validating the effectiveness of multimodal temporal modeling for egocentric dynamic scene understanding.

cs.CV↗

arXiv2025

Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content Governance

Short video platforms are evolving rapidly, making the identification of inappropriate content increasingly critical. Existing approaches typically train separate and small classification models for each type of issue, which requires extensive human-labeled data and lacks cross-issue generalization. We propose a reasoning-enhanced multimodal large language model (MLLM) pretraining paradigm for unified inappropriate content detection. To address the distribution gap between short video content and the original pretraining data of MLLMs, as well as the complex issue definitions, we introduce three targeted pretraining tasks: (1) \textit{Caption}, to enhance the MLLM's perception of video details; (2) \textit{Visual Question Answering (VQA)}, to deepen the MLLM's understanding of issue definitions and annotation guidelines; (3) \textit{Chain-of-Thought (CoT)}, to enhance the MLLM's reasoning capability. Experimental results show that our pretraining approach significantly improves the MLLM's performance in both zero-shot and supervised fine-tuning (SFT) settings. In addition, our pretrained model demonstrates strong generalization capabilities to emergent, previously unseen issues.

cs.CV↗

arXiv2025

Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding

Real-world clinical decision-making requires integrating heterogeneous data, including medical text, 2D images, 3D volumes, and videos, while existing AI systems fail to unify all these signals, limiting their utility. In this paper, we introduce Hulu-Med, a transparent, generalist medical Vision-Language Model (VLM) designed to unify language-only, 2D/3D vision-language, and video understanding within a single architecture. Hulu-Med is trained on a curated corpus of 16.7 million samples, comprising exclusively public or synthetic data, spanning 12 major anatomical systems and 14 medical imaging modalities. Hulu-Med employs a medical-aware token-reduction strategy that prunes redundant visual tokens, achieving up to a 55% reduction for 3D and video inputs, improving cross-modal efficiency, and enabling training at 7B-32B parameter scales in approximately 4,000-40,000 GPU hours. Across 30 public in-domain and out-of-domain medical benchmarks-covering text reasoning, visual question answering, report generation, multilingual dialogue, video understanding, and rare disease diagnosis-Hulu-Med surpasses existing open-source models on 27 of 30 benchmarks and outperforms proprietary systems such as GPT-4o on 16 benchmarks. Despite being a VLM, Hulu-Med outperforms GPT-4o and matches GPT-o1 on the text-only HealthBench. For the first time in the community, we provide a fully transparent, reproducible and cost-effective pipeline for holistic medical vision-language understanding by releasing our end-to-end data curation, training procedures, and model parameters. Code and models are available at https://github.com/ZJUI-AI4H/Hulu-Med.

cs.CV↗

arXiv2025

Direct Mapping of Intrinsic Topology of Bound States in the Continuum via Nonlinear Emission

The direct mapping of the intrinsic topology in a leaky photonic band is crucial and challenging in topological photonics. For instance, observables in bound states in the continuum (BICs) feature complex topological textures such as a polarization vortex in momentum space, which nonetheless is difficult to be characterized in far-field scattering, especially considering the dominant direct channel. Here, we propose and experimentally demonstrate a hybrid nonlinear metasurface that enables a direct visualization of the intrinsic topology in BICs via second-harmonic generation (SHG). The enhanced local-source of SHG from the ultrathin indium tin oxide can effectively excite the emissions from the eigenmodes of a TiO2 photonics crystal slab, achieving three-order enhancement of SHG magnitudes. Importantly, these enhanced SH emissions carry topological polarization textures of BICs to the far field. With this, we can directly construct polarization vector maps of symmetry-protected BICs and chiral symmetry-broken quasi-BICs, clearly visualizing the winding structure around V points, the generation and evolution of chiral C points. This work provides a universal approach for characterizing topological photonic systems via coherent nonlinearity processes, opening new avenues for studying topological phenomena in non-Hermitian photonic systems.

physics.optics↗