activity
20242026
collaborators

6 papers

cs.LG2026

Not Every Divergence Should Be Suppressed: Counterfactual Recoverability in On-Policy Distillation

De Jiang, Zhengyang Zhang, Kehong Yuan +1

On-policy distillation (OPD) supervises student-visited trajectories, yet divergence-based rules cannot determine whether an erroneous prefix remains correctable. We formulate this…

cs.CL2026

Unveiling Super Experts in Mixture-of-Experts Large Language Models

Zunhai Su, Qingyuan Li, Hao Zhang +6

In this study, we report, for the first time, the discovery and systematic investigation of a distinct subset of experts that play a pivotal role in the MoE LLMs' forward inference…

cs.CL2025

KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs

Zunhai Su, Kehong Yuan

Key-Value (KV) cache quantization has become a widely adopted optimization technique for efficient large language models (LLMs) inference by reducing KV cache memory usage and miti…

cs.LG2025

RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations

Zunhai Su, Zhe Chen, Wang Shen +4

Key-Value (KV) cache facilitates efficient large language models (LLMs) inference by avoiding recomputation of past KVs. As the batch size and context length increase, the oversize…

cs.CL2025

AKVQ-VL: Attention-Aware KV Cache Adaptive 2-Bit Quantization for Vision-Language Models

Zunhai Su, Wang Shen, Linge Li +4

Vision-language models (VLMs) show remarkable performance in multimodal tasks. However, excessively long multimodal inputs lead to oversized Key-Value (KV) caches, resulting in sig…

cs.CV2024

Sharingan: Extract User Action Sequence from Desktop Recordings

Yanting Chen, Yi Ren, Xiaoting Qin +7

Video recordings of user activities, particularly desktop recordings, offer a rich source of data for understanding user behaviors and automating processes. However, despite advanc…