3 papers
cs.LG2026
Representation Collapse in Sequential Post-Training of Large Language Models
Yichen Liu, Mingyu Chen, Hao Wang +7
Large language models are now adapted through chains of post-training stages rather than through a single instruction-tuning pass. This paper studies whether such sequential post-t…
cs.LG2026
FAAR: Format-Aware Adaptive Rounding for NVFP4
Hanglin Li, Shuchang Tian, Chen Lin +2
Deploying large language models (LLMs) on edge devices requires extremely low-bit quantization. Ultra-low precision formats such as NVFP4 offer a promising solution for reducing me…
cs.CL2026
From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation
Jiahao Wang, Weiyu Xie, Mingxing Zhang +10
Retrieval-Augmented Generation enhances Large Language Models by integrating external knowledge, which reduces hallucinations but increases prompt length. This increase leads to hi…