66 citations · 132 across the 26 of their papers we have counts for
26 papers
Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling
Xinmu Ge, Zizhuo Zhang, Yu Huang +9
On-policy distillation (OPD) has emerged as a promising post-training technique for enhancing LLM reasoning. Under the reverse KL objective, the idealized optimum of OPD aligns the…
SeqLLM: Augmenting LLMs with Behavioral-Sequence Modeling for High-Stakes Decisions at WeChat Pay
Guilin Li, Jiaxing Zhang, Matthias Hwai Yong Tan +2
Merchant risk control at large payment platforms screens tens of millions of merchants daily, where false positives harm legitimate merchants and false negatives leave harmful acti…
CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition
Lai Wei, Chengqi Li, Jiapeng Li +3
Real-world tasks often require models to learn from task-specific context rather than relying only on pre-trained knowledge. While recent work has highlighted this capability as co…
Evidence-Grounded AI for Musculoskeletal Care
Wenjie Li, Yujie Zhang, Fanrui Zhang +34
Musculoskeletal diseases are among the leading causes of disability and drive the greatest global need for rehabilitation. Because recovery, remodelling and degeneration of bones,…
Distill Where the Student Goes: Teacher-Regularized RL for English-Evidence Cross-Lingual RAG
Haotian Zhou, Weiran Huang, Siqi Liu +3
Cross-lingual retrieval-augmented generation (RAG) is often deployed in an English-evidence regime, where users query in diverse languages but retrieved passages remain English. In…
Black-Box Continual Learning for Vision-Language Models
Yuting Li, Weihang Fang, Haoyuan Gao +4
The rapid deployment of Vision-Language Models (VLMs) in dynamic environments necessitates the ability to learn continuously without forgetting. However, traditional continual lear…
Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR
Ruina Hu, Chen Wang, Lai Wei +5
Reinforcement learning with verifiable rewards (RLVR) improves vision-language models (VLMs) by optimizing outcome rewards derived from final answers. However, such outcome-only re…
Targeted Exploration via Unified Entropy Control for Reinforcement Learning
Chen Wang, Lai Wei, Yanzhi Zhang +5
Recent advances in reinforcement learning (RL) have improved the reasoning capabilities of large language models (LLMs) and vision-language models (VLMs). However, the widely used…
Camyla: Scaling Autonomous Research in Medical Image Segmentation
Yifan Gao, Haoyue Li, Feng Yuan +3
We present Camyla, a system for fully autonomous research within the scientific domain of medical image segmentation. Camyla transforms raw datasets into literature-grounded resear…
IDER: IDempotent Experience Replay for Reliable Continual Learning
Zhanwang Liu, Yuting Li, Haoyuan Gao +4
Catastrophic forgetting, the tendency of neural networks to forget previously learned knowledge when learning new tasks, has been a major challenge in continual learning (CL). To t…
Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
Lai Wei, Liangbo He, Jun Lan +9
Multimodal Large Language Models (MLLMs) excel at broad visual understanding but still struggle with fine-grained perception, where decisive evidence is small and easily overwhelme…
RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration
Xiuyuan Chen, Jian Zhao, Yuchen Yuan +8
Existing safety evaluation methods for large language models (LLMs) suffer from inherent limitations, including evaluator bias and detection failures arising from model homogeneity…
PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling
Guilin Li, Yun Zhang, Xiuyuan Chen +6
Large language models (LLMs) have shown that generative pretraining can distill vast world knowledge into compact token representations. While LLMs encapsulate extensive world know…
Generalized Category Discovery via Reciprocal Learning and Class-Wise Distribution Regularization
Duo Liu, Zhiquan Tan, Linglan Zhao +3
Generalized Category Discovery (GCD) aims to identify unlabeled samples by leveraging the base knowledge from labeled ones, where the unlabeled set consists of both base and novel…
EFRame: Deeper Reasoning via Exploration-Filter-Replay Reinforcement Learning Framework
Chen Wang, Lai Wei, Yanzhi Zhang +5
Recent advances in reinforcement learning (RL) have significantly enhanced the reasoning capabilities of large language models (LLMs). Group Relative Policy Optimization (GRPO), a…
Improved Iterative Refinement for Chart-to-Code Generation via Structured Instruction
Chengzhi Xu, Yuyang Wang, Lai Wei +2
Recently, multimodal large language models (MLLMs) have attracted increasing research attention due to their powerful visual understanding capabilities. While they have achieved im…
Revisiting Visual Understanding in Multimodal Reasoning through a Lens of Image Perturbation
Yuting Li, Lai Wei, Kaipeng Zheng +6
Despite the rapid progress of multimodal large language models (MLLMs), they have largely overlooked the importance of visual processing. In a simple yet revealing experiment, we i…
First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training
Lai Wei, Yuting Li, Chen Wang +4
Improving Multi-modal Large Language Models (MLLMs) in the post-training stage typically relies on supervised fine-tuning (SFT) or reinforcement learning (RL), which require expens…
Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
Lai Wei, Yuting Li, Kaipeng Zheng +5
Recent advancements in large language models (LLMs) have demonstrated impressive chain-of-thought reasoning capabilities, with reinforcement learning (RL) playing a crucial role in…
Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?
Kun Xiang, Zhili Liu, Zihao Jiang +13
In this paper, we address the challenging task of multimodal mathematical reasoning by incorporating the ability of "slow thinking" into multimodal large language models (MLLMs). O…
Enhanced Continual Learning of Vision-Language Models with Model Fusion
Haoyuan Gao, Zicong Zhang, Yuqi Wei +6
Vision-Language Models (VLMs) represent a significant breakthrough in artificial intelligence by integrating visual and textual modalities to achieve impressive zero-shot capabilit…
SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models
Linglan Zhao, Xuerui Zhang, Ke Yan +2
Continual learning aims to incrementally acquire new concepts in data streams while resisting forgetting previous knowledge. With the rise of powerful pre-trained models (PTMs), th…
Investigating the Impact of Model Complexity in Large Language Models
Jing Luo, Huiyuan Wang, Weiran Huang
Large Language Models (LLMs) based on the pre-trained fine-tuning paradigm have become pivotal in solving natural language processing tasks, consistently achieving state-of-the-art…
A Statistical Theory of Regularization-Based Continual Learning
Xuyang Zhao, Huiyuan Wang, Weiran Huang +1
We provide a statistical analysis of regularization-based continual learning on a sequence of linear regression tasks, with emphasis on how different regularization terms affect th…