20 papers
ZoomCap: Evidence-Routed Visual Zooming for Recoverable Visual Information Transfer
Hao Shi, Jiafeng Wang, Yuzhuo Fu +5
Detailed captions transfer visual information into vision-language model supervision, but quality is easily conflated with length: long single-pass outputs still miss small objects…
MEMO: Multimodal Evidence Memory Organization for Long-Horizon LLM Agents
Xian Gao, Jinpeng Wang, Jiacheng Ruan +3
Long-running LLM agents rely on external memory to store and reuse information beyond a single context window, yet there is a fundamental tension between the continuous accumulatio…
Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ
Zongyun Zhang, Jiacheng Ruan, Xian Gao +5
Although multimodal large language models (MLLMs) have shown substantial potential in visual understanding and graphic code generation, editing scientific figures through code pres…
Contrastive On-Policy Distillation
Jiacheng Ruan, Jun Tang, Wenzhen Yuan +5
On-policy distillation (OPD) trains a student model on trajectories sampled from its own policy, providing dense token-level supervision by minimizing the divergence between the te…
MMGist: A Comprehensive Multimodal Benchmark for 2027
Wenzhen Yuan, Jiacheng Ruan, Wutao Xiong +3
We conduct a systematic study of 18 widely used vision-language benchmarks and identify three major issues: 1) many items do not rely on visual cues and therefore fail to effective…
BasketHAR: A Multimodal Dataset for Human Activity Recognition and Sport Analysis in Basketball Training Scenarios
Xian Gao, Haoyue Zhang, Zongyun Zhang +3
Human Activity Recognition (HAR) involves the automatic identification of user activities and has gained significant research interest due to its broad applicability. Most HAR syst…
Small Model as Master Orchestrator: Learning Unified Agent-Tool Orchestration with Parallel Subtask Decomposition
Wenzhen Yuan, Wutao Xiong, Fanchen Yu +7
Multi-agent systems (MAS) demonstrate clear advantages in tackling complex problems by coordinating diverse agents and external tools. However, most existing orchestration methods…
ExFusion: Efficient Transformer Training via Multi-Experts Fusion
Jiacheng Ruan, Daize Dong, Xiaoye Qu +5
Mixture-of-Experts (MoE) models substantially improve performance by increasing the capacity of dense architectures. However, directly training MoE models requires considerable com…
ARA: Adaptive Rank Allocation for Efficient Large Language Model SVD Compression
Lin Xv, Jingsheng Gao, Xian Gao +2
In the field of large language model (LLM) compression, singular value decomposition (SVD) is a widely studied and adopted low-rank decomposition technique. Since SVD operates excl…
Beyond Uniform SVD:Dual-Level Optimization across Columns and Modules for LLM Compression
Lin Xv, Xian Gao, Ting Li +1
Low-rank decomposition, particularly Singular Value Decomposition (SVD), is a pivotal technique for mitigating the storage and computational demands of Large Language Models (LLMs)…
OnlineMate: An LLM-Based Multi-Agent Companion System for Cognitive Support in Online Learning
Xian Gao, Zongyun Zhang, Ting Liu +1
In online learning environments, students often lack personalized peer interactions, which are crucial for cognitive development and learning engagement. Although previous studies…
MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models
Jiacheng Ruan, Dan Jiang, Xian Gao +3
Recently, multimodal large language models (MLLMs) have achieved significant advancements across various domains, and corresponding evaluation benchmarks have been continuously ref…
Wisdom of the Crowd: Reinforcement Learning from Coevolutionary Collective Feedback
Wenzhen Yuan, Shengji Tang, Weihao Lin +8
Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs), but its reliance on expensive human-labeled data or complex rewar…
MMReview: A Multidisciplinary and Multimodal Benchmark for LLM-Based Peer Review Automation
Xian Gao, Jiacheng Ruan, Zongyun Zhang +3
With the rapid growth of academic publications, peer review has become an essential yet time-consuming responsibility within the research community. Large Language Models (LLMs) ha…
VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models
Jiacheng Ruan, Wenzhen Yuan, Xian Gao +6
Although large visual-language models (LVLMs) have demonstrated strong performance in multimodal tasks, errors may occasionally arise due to biases during the reasoning process. Re…
EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Models
Zongyun Zhang, Jiacheng Ruan, Xian Gao +2
Industrial Anomaly Detection (IAD) is critical to ensure product quality during manufacturing. Although existing zero-shot defect segmentation and detection methods have shown effe…
GoAI: Enhancing AI Students' Learning Paths and Idea Generation via Graph of AI Ideas
Xian Gao, Zongyun Zhang, Ting Liu +1
With the rapid advancement of artificial intelligence technology, AI students are confronted with a significant "information-to-innovation" gap: they must navigate through the rapi…
ReviewAgents: Bridging the Gap Between Human and AI-Generated Paper Reviews
Xian Gao, Jiacheng Ruan, Zongyun Zhang +3
Academic paper review is a critical yet time-consuming task within the research community. With the increasing volume of academic publications, automating the review process has be…
From Motion Signals to Insights: A Unified Framework for Student Behavior Analysis and Feedback in Physical Education Classes
Xian Gao, Jiacheng Ruan, Jingsheng Gao +4
Analyzing student behavior in educational scenarios is crucial for enhancing teaching quality and student engagement. Existing AI-based models often rely on classroom video footage…
SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback
Jingsheng Gao, Linxu Li, Weiyuan Li +2
RAG systems consist of multiple modules to work together. However, these modules are usually separately trained. We argue that a system like RAG that incorporates multiple modules…