10 papers
Denser Better: Limits of On-Policy Self-Distillation for Continual Post-Training
Meng Wang, Haohan Zhao, Wenzhuo Liu +7
Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities. Recent work suggests that on-policy learning can mitigate forgett…
Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
Song Lai, Haohan Zhao, Rong Feng +9
Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to ever-evolving downstream tasks. While exi…
Constraint-Aware Corrective Memory for Language-Based Drug Discovery Agents
Maochen Sun, Youzhi Zhang, Gaofeng Meng
Large language models are making autonomous drug discovery agents increasingly feasible, but reliable success in this setting is not determined by any single action or molecule. It…
Intent Mismatch Causes LLMs to Get Lost in Multi-Turn Conversation
Geng Liu, Fei Zhu, Rong Feng +3
Multi-turn conversation has emerged as a predominant interaction paradigm for Large Language Models (LLMs). Users often employ follow-up questions to refine their intent, expecting…
Practical Continual Forgetting for Pre-trained Vision Models
Hongbo Zhao, Fei Zhu, Bolin Ni +3
For privacy and security concerns, the need to erase unwanted information from pre-trained vision models is becoming evident nowadays. In real-world scenarios, erasure requests ori…
VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?
Hongbo Zhao, Meng Wang, Fei Zhu +5
The computational and memory overheads associated with expanding the context window of LLMs severely limit their scalability. A noteworthy solution is vision-text compression (VTC)…