activity
20242026
collaborators

8 papers

cs.CL2026

HybridThinker: Efficient Chain-of-Thought Reasoning via Compressed Memory and Transient Thought Steps

Xin Liu, Runsong Zhao, Xinyu Liu +8

Extended chain-of-thought (CoT) traces improve LLM reasoning but incur substantial computational and memory costs. While existing CoT compression methods mitigate this by condensin…

cs.CL2026

PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction

Runsong Zhao, Shilei Liu, Jiwei Tang +8

While context compression can mitigate the growing inference costs of Large Language Models (LLMs) by shortening contexts, existing methods that specify a target compression ratio…

cs.CL2026

Read As Human: Compressing Context via Parallelizable Close Reading and Skimming

Jiwei Tang, Shilei Liu, Zhicheng Zhang +9

Large Language Models (LLMs) demonstrate exceptional capability across diverse tasks. However, their deployment in long-context scenarios is hindered by two challenges: computation…

cs.LG2026

CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling

Runsong Zhao, Shilei Liu, Jiwei Tang +8

The quadratic complexity and indefinitely growing key-value (KV) cache of standard Transformers pose a major barrier to long-context processing. To overcome this, we introduce the…

cs.CL2025

MTP-S2UT: Enhancing Speech-to-Speech Translation Quality with Multi-token Prediction

Jianjin Wang, Runsong Zhao, Xiaoqian Liu +6

Current direct speech-to-speech translation methods predominantly employ speech tokens as intermediate representations. However, a single speech token is not dense in semantics, so…

cs.CL2025

Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors

Xin Liu, Runsong Zhao, Pengcheng Huang +7

Context compression is an advanced technique that accelerates large language model (LLM) inference by converting long inputs into compact representations. Existing methods primaril…