Lychee Team

university

HITsz-TMG

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

crazyofapple submitted a paper about 8 hours ago

Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning

crazyofapple submitted a paper 7 days ago

LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding

Yuki131 authored a paper 16 days ago

Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation

View all activity

Papers

Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning

LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding

View all Papers

HIT-TMG 's Papers 5

Submitted by

Dongfang Li

Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning

HIT-TMG

Submitted by

Dongfang Li

LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding

HIT-TMG

Submitted by

Yunxin Li

Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data

HIT-TMG

Submitted by

ZhenyuLiu

UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE

HIT-TMG

Submitted by

ZhenyuLiu

Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models

HIT-TMG