arXiv subjects

Jinhao Chen

Publications and source records attributed to Jinhao Chen.

10 recordsLinked to original sources

arXiv2026

MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding

Long-form video understanding requires locating sparse, question-relevant evidence in long, multimodal videos. Real-world video distributions differ in modality-specific information density, content structure, and evidence patterns, causing fixed video-agent designs to incur redundant processing or fail when mismatched. Extending automated agent evolution from text to video is challenging because full long-video execution makes candidate validation expensive, failures propagate across coupled evidence-processing stages, and complex preprocessing, perception tools, and localization strategies make code-level updates difficult to implement reliably. We introduce MetaVideoAgent, a framework that automatically evolves a video agent for a target distribution. It profiles information density and evidence requirements from sparsely sampled frames and associated queries to guide initial design, then compresses localized failures into independently executable minimal validation tasks. It constructs evidence-grounded Gold Paths, audits Student trajectories, aggregates recurring failures across samples, and attributes them to responsible modules. A modular agent representation constrains each update to the primary responsible module and its necessary dependencies. We further introduce VA-EvoBench, covering eight video distributions with separate evolution and held-out splits. With four evolution iterations per distribution, MetaVideoAgent improves every initial agent and raises macro-average accuracy from 38.44% to 51.47%, at an average evolution cost of 3.54M tokens per distribution. The evolved agents outperform the strongest prior fixed-design video agent by 6.39 percentage points while using the fewest tokens and video frames per question among the compared video agents. We will release all code and data to support reproducible research.

cs.CV↗

arXiv2026

Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety

General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI safety. We present Yuvion VL, a family of multimodal large language models purpose-built for content and AI safety, with both instruction-tuned and reasoning-oriented variants. Yuvion VL addresses this gap by treating safety as an inherently adversarial and multimodal problem and designing the entire pipeline around adversarial robustness. For data construction, we develop an automated pipeline integrating adversarial-aware data synthesis with multi-stage quality control, producing large-scale, high-quality multimodal samples augmented with domain knowledge and reasoning annotations. For training, we adopt a three-stage pipeline that includes continued pretraining for risk-concept cross-modal alignment, instruct post-training for production-grade safety tasks, and reasoning post-training for enhanced interpretability and performance in complex tasks. We further introduce Confuse-then-Contrast Fine-Tuning, a contrastive framework that mines model-specific confusions and constructs multi-image contrastive groups to enforce explicit discrimination of fine-grained visual-semantic elements, enabling the model to distinguish between visually similar cases with different safety implications in adversarial safety tasks. To support rigorous evaluation, we further introduce Yuvion VL RiskEval (YVRE), a collection of benchmarks covering diverse open and internal evaluations, with a focus on content and AI safety, adversarial robustness, and real-world capability requirements. Experiments show that Yuvion VL-32B achieves industry-leading safety performance, surpassing comparably sized open-source models and best closed-source commercial models, while maintaining comparable general capabilities.

cs.CV↗

arXiv2025

MathSE: Improving Multimodal Mathematical Reasoning via Self-Evolving Iterative Reflection and Reward-Guided Fine-Tuning

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language answering tasks. Despite their strengths, these models often encounter challenges in achieving complex reasoning tasks such as mathematical problem-solving. Previous works have focused on fine-tuning on specialized mathematical datasets. However, these datasets are typically distilled directly from teacher models, which capture only static reasoning patterns and leaving substantial gaps compared to student models. This reliance on fixed teacher-derived datasets not only restricts the model's ability to adapt to novel or more intricate questions that extend beyond the confines of the training data, but also lacks the iterative depth needed for robust generalization. To overcome these limitations, we propose \textbf{\method}, a \textbf{Math}ematical \textbf{S}elf-\textbf{E}volving framework for MLLMs. In contrast to traditional one-shot fine-tuning paradigms, \method iteratively refines the model through cycles of inference, reflection, and reward-based feedback. Specifically, we leverage iterative fine-tuning by incorporating correct reasoning paths derived from previous-stage inference and integrating reflections from a specialized Outcome Reward Model (ORM). To verify the effectiveness of \method, we evaluate it on a suite of challenging benchmarks, demonstrating significant performance gains over backbone models. Notably, our experimental results on MathVL-test surpass the leading open-source multimodal mathematical reasoning model QVQ. Our code and models are available at \texttt{https://zheny2751\allowbreak-dotcom.github.io/\allowbreak MathSE.github.io/}.

cs.AI↗

arXiv2025

GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

We present GLM-4.1V-Thinking, GLM-4.5V, and GLM-4.6V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the reasoning-centric training framework. We first develop a capable vision foundation model with significant potential through large-scale pre-training, which arguably sets the upper bound for the final performance. We then propose Reinforcement Learning with Curriculum Sampling (RLCS) to unlock the full potential of the model, leading to comprehensive capability enhancement across a diverse range of tasks, including STEM problem solving, video understanding, content recognition, coding, grounding, GUI-based agents, and long document interpretation. In a comprehensive evaluation across 42 public benchmarks, GLM-4.5V achieves state-of-the-art performance on nearly all tasks among open-source models of similar size, and demonstrates competitive or even superior results compared to closed-source models such as Gemini-2.5-Flash on challenging tasks including Coding and GUI Agents. Meanwhile, the smaller GLM-4.1V-9B-Thinking remains highly competitive-achieving superior results to the much larger Qwen2.5-VL-72B on 29 benchmarks. We open-source both GLM-4.1V-9B-Thinking and GLM-4.5V. We further introduce the GLM-4.6V series, open-source multimodal models with native tool use and a 128K context window. A brief overview is available at https://z.ai/blog/glm-4.6v. Code, models and more information are released at https://github.com/zai-org/GLM-V.

cs.CV↗

arXiv2025

MedVKAN: Efficient Feature Extraction with Mamba and KAN for Medical Image Segmentation

Medical image segmentation has traditionally relied on convolutional neural networks (CNNs) and Transformer-based models. CNNs, however, are constrained by limited receptive fields, while Transformers face scalability challenges due to quadratic computational complexity. To over-come these issues, recent studies have explored alternative architectures. The Mamba model, a selective state-space design, achieves near-linear complexity and effectively captures long-range dependencies. Its vision-oriented variant, the Visual State Space (VSS) model, extends these strengths to image feature learning. In parallel, the Kolmogorov-Arnold Network (KAN) enhanc-es nonlinear expressiveness by replacing fixed activation functions with learnable ones. Moti-vated by these advances, we propose the VSS-Enhanced KAN (VKAN) module, which integrates VSS with the Expanded Field Convolutional KAN (EFC-KAN) as a replacement for Transformer modules, thereby strengthening feature extraction. We further embed VKAN into a U-Net frame-work, resulting in MedVKAN, an efficient medical image segmentation model. Extensive exper-iments on five public datasets demonstrate that MedVKAN achieves state-of-the-art performance on four datasets and ranks second on the remaining one. These results underscore the effective-ness of combining Mamba and KAN while introducing a novel and computationally efficient feature extraction framework. The source code is available at: https://github.com/beginner-cjh/MedVKAN.

eess.IV↗

arXiv2025

Motion Forecasting for Autonomous Vehicles: A Survey

In recent years, the field of autonomous driving has attracted increasingly significant public interest. Accurately forecasting the future behavior of various traffic participants is essential for the decision-making of Autonomous Vehicles (AVs). In this paper, we focus on both scenario-based and perception-based motion forecasting for AVs. We propose a formal problem formulation for motion forecasting and summarize the main challenges confronting this area of research. We also detail representative datasets and evaluation metrics pertinent to this field. Furthermore, this study classifies recent research into two main categories: supervised learning and self-supervised learning, reflecting the evolving paradigms in both scenario-based and perception-based motion forecasting. In the context of supervised learning, we thoroughly examine and analyze each key element of the methodology. For self-supervised learning, we summarize commonly adopted techniques. The paper concludes and discusses potential research directions, aiming to propel progress in this vital area of AV technology.

cs.RO↗

arXiv2024

MathGLM-Vision: Solving Mathematical Problems with Multi-Modal Large Language Model

Large language models (LLMs) have demonstrated significant capabilities in mathematical reasoning, particularly with text-based mathematical problems. However, current multi-modal large language models (MLLMs), especially those specialized in mathematics, tend to focus predominantly on solving geometric problems but ignore the diversity of visual information available in other areas of mathematics. Moreover, the geometric information for these specialized mathematical MLLMs is derived from several public datasets, which are typically limited in diversity and complexity. To address these limitations, we aim to construct a fine-tuning dataset named MathVL, and develop a series of specialized mathematical MLLMs termed MathGLM-Vision by conducting Supervised Fine-Tuning (SFT) on MathVL with various parameter-scale backbones. To extensively evaluate the effectiveness of MathGLM-Vision, we conduct experiments on several public benchmarks and our curated MathVL-test consisting of 2,000 problems. Experimental results demonstrate that MathGLM-Vision achieves significant improvements compared with some existing models, including backbone models and open-source mathematical MLLMs. These findings indicate the importance of diversity dataset in enhancing the mathematical reasoning abilities of MLLMs.

cs.CL↗

arXiv2024

VisScience: An Extensive Benchmark for Evaluating K12 Educational Multi-modal Scientific Reasoning

Multi-modal large language models (MLLMs) have demonstrated promising capabilities across various tasks by integrating textual and visual information to achieve visual understanding in complex scenarios. Despite the availability of several benchmarks aims to evaluating MLLMs in tasks from visual question answering to complex problem-solving, most focus predominantly on mathematics or general visual understanding tasks. This reveals a critical gap in current benchmarks, which often overlook the inclusion of other key scientific disciplines such as physics and chemistry. To address this gap, we meticulously construct a comprehensive benchmark, named VisScience, which is utilized to assess the multi-modal scientific reasoning across the three disciplines of mathematics, physics, and chemistry. This benchmark comprises 3,000 questions drawn from K12 education - spanning elementary school through high school - equally distributed across three disciplines, with 1,000 questions per discipline. The questions within VisScience span 21 distinct subjects and are categorized into five difficulty levels, offering a broad spectrum of topics within each discipline. With VisScience, we present a detailed evaluation of the performance of 25 representative MLLMs in scientific reasoning. Experimental results demonstrate that closed-source MLLMs generally outperform open-source models. The best performance observed include a 53.4\% accuracy in mathematics by Claude3.5-Sonnet, 38.2\% in physics by GPT-4o, and 47.0\% in chemistry by Gemini-1.5-Pro. These results underscore the strengths and limitations of MLLMs, suggesting areas for future improvement and highlighting the importance of developing models that can effectively handle the diverse demands of multi-modal scientific reasoning.

cs.AI↗

arXiv2021

Revealing the role of interfacial heterogeneous nucleation in metastable thin film growth of rare earth nickelates electronic transition materials

Although rare earth nickelates (ReNiO3) exhibit abundant electronic phases and widely adjustable metal to insulator electronic transition properties, their practical electronic applications are largely impeded by their intrinsic meta stability. Apart from elevating oxygen reaction pressures, heterogeneous nucleation is expected as an alternative strategy that enables the crystallization of ReNiO3 at low meta stability. In this work, the respective roles of high oxygen pressure and heterogeneous interface in triggering ReNiO3 thin films growth at metastable state are revealed. The ReNiO3 (Re:Nd, Sm, Eu, Gd, and Dy) heterogeneous thin films growth on LaAlO3 single crystal substrate have an effective crystallization at atmosphere without the necessity to apply high oxygen pressures, suggesting the interfacial bonding between the ReNiO3 and substrates can sufficiently reduce the positive Gibbs formation energy of ReNiO3, which is further verified by the first principles calculations. Nevertheless, the abrupt electronic transitions only appear in ReNiO3 thin films grown at high oxygen pressures, in which cases the oxygen vacancies are effectively eliminated via high oxygen pressure reactions as indicated by near edge X ray absorption fine structure (NEXAFS). This work unveils the synergistic effects of heterogeneous nucleation and high oxygen pressure on the growth of high quality ReNiO3 thin films.

cond-mat.mtrl-sci↗

arXiv2020

AC-frequency switchable correlated transports in rare-earth perovskite nickelates

Whilst electron correlations were previously recognized to trigger beyond conventional direct current (DC) electronic transportations (e.g. metal-to-insulator transitions, bad metal, thermistors), their respective influences to the alternation current (AC) transport are largely overlooked. Herein, we demonstrate active regulations in the electronic functionalities of d-band correlated rare-earth nickelate (ReNiO3) thin films, by simply utilizing their electronic responses to AC-frequencies (fAC). Assisted by temperature dependent near edge X-ray absorption fine structure analysis, we discovered positive temperature dependences in Coulomb viscosity of ReNiO3 that moderates their AC impedance. Distinguished crosslinking among R(Real)-fAC measured in nearby temperatures is observed that differs to conventional oxides. It enables active adjustability in correlated transports of ReNiO3, among NTCR-, TDelta- and PTCR- thermistors, via fAC from the electronic perspective without varying materials or device structures. The TDelta-fAC relationship can be further widely adjusted via Re composition and interfacial strains. The AC-frequency sensitivity discovered in ReNiO3 brings in a new freedom to regulating and switching the device working states beyond the present semiconductor technologies. It opens a new paradigm for enriching novel electronic applications catering automatic transmission or artificial intelligence in sensing temperatures and frequencies.

cond-mat.mtrl-sci↗