435 citations · 503 across the 62 of their papers we have counts for
68 papers
Joint Class-Time Learning for Video Classification with Multi-Instance Partial-Label Learning
Lingyu Shen, Wei Tang, Fakhri Karray +1
Multi-instance partial-label learning (MIPL) addresses inexact supervision in both the instance and label spaces, which can be applied to video classification. However, bag-level l…
Outcome-Guided On-Policy Self-Distillation
ZheXu Wang, Mao-Lin Luo, Yankun Hong +6
On-policy self-distillation (OPSD) provides denser token-level supervision and better computational efficiency than Reinforcement Learning with Verifiable Rewards (RLVR). However,…
Learning Process Rewards via Reasoning State Propagation
Kai Gan, Zi-Hao Zhou, Bo Ye +3
Process reward models (PRMs) have demonstrated notable effectiveness in test-time scaling and reinforcement learning by providing fine-grained signals for evaluating intermediate r…
When Collaboration Becomes a Trigger: Collective Evidence-Threshold Backdoors in Multi-Agent Systems
Jia-Hao Xiao, Lei Feng, Min-Ling Zhang
LLM-based multi-agent systems (MAS) extend LLM capabilities through iterative communication and shared contexts. However, this collaboration introduces a vulnerability: backdoor be…
AI-generated Images Challenge Visual Trust in High-risk Scenarios
Yi-Zhi Wang, Yichen Xiao, Linan Yue +5
Rapid advances in image generation are eroding the evidentiary value of visual content in settings where authenticity can affect public safety and personal reputation. Yet existing…
RL Forgets! Towards Continual Policy Optimization
Mao-Lin Luo, Zhe-Xu Wang, Zi-Hao Zhou +4
Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks. Recent studies report that reinforcement learning is less prone to for…
KeepLoRA++: Continual Learning with Layer-Scaled Residual Gradient Adaptation
Mao-Lin Luo, Yi-Lin Zhang, Zi-Hao Zhou +5
Continual learning for pre-trained vision-language models requires balancing three competing objectives: retaining pre-trained knowledge, preserving knowledge from a sequence of le…
EpiAgent: An Agent-Centric System for Ancient Inscription Restoration
Shipeng Zhu, Ang Chen, Na Nie +3
Ancient inscriptions, as repositories of cultural memory, have suffered from centuries of environmental and human-induced degradation. Restoring their intertwined visual and textua…
Sparsity Hurts: Simple Linear Adapter Can Boost Generalized Category Discovery
Bo Ye, Kai Gan, Tong Wei +1
Generalized Category Discovery (GCD) seeks to identify novel categories from unlabeled data while retaining the classification ability of seen categories. Prior GCD methods commonl…
DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation
Bo Ye, Xinyu Cui, Jian Zhao +2
Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity with static early-frame sinks…
When AI reviews science: Can we trust the referee?
Jialiang Wang, Yuchen Liu, Hang Xu +7
The volume of scientific submissions continues to climb, outpacing the capacity of qualified human referees and stretching editorial timelines. At the same time, modern large langu…
RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs
Liang Yao, Shengxiang Xu, Fan Liu +7
Earth Observation (EO) systems are essentially designed to support domain experts who often express their requirements through vague natural language rather than precise, machine-f…
FactReview: Evidence-Grounded Peer Review with Execution-Based Claim Verification
Ling Yue, Chaoqian Ouyang, Hang Xu +8
AI is accelerating scientific research, but providing timely and trustworthy feedback remains challenging. Such feedback requires evaluating specific claims against verified eviden…
DC-Merge: Improving Model Merging with Directional Consistency
Han-Chen Zhang, Zi-Hao Zhou, Mao-Lin Luo +3
Model merging aims to integrate multiple task-adapted models into a unified model that preserves the knowledge of each task. In this paper, we identify that the key to this knowled…
Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation
Jianan Chen, Zhifang Zhang, Shuo He +3
Large reasoning models (LRMs) achieved remarkable performance via chain-of-thought (CoT), but recent studies showed that such enhanced reasoning capabilities are at the expense of…
ToolRosella: Translating Code Repositories into Standardized Tools for Scientific Agents
Shimin Di, Xujie Yuan, Hanghui Guo +10
Large Language Model (LLM)-based agent systems are increasingly used for scientific tasks, yet their practical capability remains constrained by the narrow scope of manually curate…
Learning to Compose for Cross-domain Agentic Workflow Generation
Jialiang Wang, Shengxiang Xu, Hanmo Liu +5
Automatically generating agentic workflows -- executable operator graphs or codes that orchestrate reasoning, verification, and repair -- has become a practical way to solve comple…
Bridging Efficiency and Transparency: Explainable CoT Compression in Multimodal Large Reasoning Models
Yizhi Wang, Linan Yue, Min-Ling Zhang
Long chains of thought (Long CoTs) are widely employed in multimodal reasoning models to tackle complex tasks by capturing detailed visual information. However, these Long CoTs are…
PeroMAS: A Multi-agent System of Perovskite Material Discovery
Yishu Wang, Wei Liu, Yifan Li +8
As a pioneer of the third-generation photovoltaic revolution, Perovskite Solar Cells (PSCs) are renowned for their superior optoelectronic performance and cost potential. The devel…
AtomBridge: Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experiments
Yiwen Pang, Bo Zhou, Changjin Li +7
Robotic laboratories play a critical role in autonomous scientific discovery by enabling scalable, continuous experimental execution. Recent vision-language-action (VLA) models off…
Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation
Hao Gu, Mao-Lin Luo, Zi-Hao Zhou +3
Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge. Most existing approaches treat continu…
Guided by Trajectories: Repairing and Rewarding Tool-Use Trajectories for Tool-Integrated Reasoning
Siyu Gong, Linan Yue, Weibo Gao +4
Tool-Integrated Reasoning (TIR) enables large language models (LLMs) to solve complex tasks by interacting with external tools, yet existing approaches depend on high-quality synth…
KeepLoRA: Continual Learning with Residual Gradient Adaptation
Mao-Lin Luo, Zi-Hao Zhou, Yi-Lin Zhang +3
Continual learning for pre-trained vision-language models requires balancing three competing objectives: retaining pre-trained knowledge, preserving knowledge from a sequence of le…
Training Multimodal Large Reasoning Models Needs Better Thoughts: A Three-Stage Framework for Long Chain-of-Thought Synthesis and Selection
Yizhi Wang, Linan Yue, Min-Ling Zhang
Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex reasoning tasks through long Chain-of-Thought (CoT) reasoning. Extending these successes to multim…