4 papers
Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models
Cheng-Yu Yang, Shao-Yuan Lo, Yu-Lun Liu
Vision-language models (VLMs) project images into hundreds to thousands of visual tokens, making decoder inference expensive in both attention computation and KV-cache memory. Exis…
Finding What Matters: Anchoring Context Knowledge with Evolving Indices for Iterative Retrieval
Mingyan Wu, Zhenghao Liu, Xinze Li +7
Retrieval-Augmented Generation (RAG) has become a dominant paradigm for mitigating hallucinations in Large Language Models (LLMs) by incorporating external knowledge. However, exis…
MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization
Haidong Xin, Xinze Li, Zhenghao Liu +6
Existing memory systems enable Large Language Models (LLMs) to support long-horizon human-LLM interactions by persisting historical interactions beyond limited context windows. How…
Boosting LLMs for Mutation Generation
Bo Wang, Ming Deng, Mingda Chen +5
LLM-based mutation testing is a promising testing technology, but existing approaches typically rely on a fixed set of mutations as few-shot examples or none at all. This can resul…