4 papers
System 1&2 Synergy via Dynamic Model Interpolation
Chenxu Yang, Qingyi Si, Chong Tian +6
Training a unified language model that adapts between intuitive System 1 and deliberative System 2 remains challenging due to interference between their cognitive modes. Recent stu…
VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization
Dingyu Yao, Chenxu Yang, Zhengyang Tong +4
The Key-Value (KV) cache introduces substantial memory overhead during large language model (LLM) inference. Although existing vector quantization (VQ) methods reduce KV cache usag…
Test-time Prompt Intervention
Chenxu Yang, Qingyi Si, Mz Dai +5
Test-time compute has led to remarkable success in the large language model (LLM) community, particularly for complex tasks, where longer chains of thought (CoTs) are generated to…
TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization
Dingyu Yao, Bowen Shen, Zheng Lin +4
The Key-Value (KV) cache in generative large language models (LLMs) introduces substantial memory overhead. Existing works mitigate this burden by offloading or compressing the KV…