collaborators

14 papers

cs.CL2026

Enhancing Multilingual Reasoning via Steerable Model Merging

Zhuoran Li, Rui Xu, Jian Yang +8

Model merging is an effective technique for composing the capabilities of a multilingual model and a reasoning model. It has achieved promising generalization in multilingual reaso…

cs.CL2026

OpenCompass: A Universal Evaluation Platform for Large Language Models

Maosong Cao, Kai Chen, Haodong Duan +27

In recent years, the field of artificial intelligence has undergone a paradigm shift from task-specific small-scale models to general-purpose large language models (LLMs). With the…

cs.LG2026

SinkRouter: Sink-Aware Routing for Efficient Long-Context Decoding in Large Language and Multimodal Models

Junnan Liu, Xinyan Liu, Peifeng Gao +4

In long-context decoding for LLMs and LMMs, attention becomes increasingly memory-bound because each decoding step must load a large amount of KV-cache data from GPU memory. Existi…

cs.CL2026

Rectifying LLM Thought from Lens of Optimization

Junnan Liu, Hongwei Liu, Songyang Zhang +1

Recent advancements in large language models (LLMs) have been driven by their emergent reasoning capabilities, particularly through long chain-of-thought (CoT) prompting, which ena…

cs.CL2025

ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning

Hongwei Liu, Junnan Liu, Shudong Liu +33

The rapid advancement of Large Language Models (LLMs) has led to performance saturation on many established benchmarks, questioning their ability to distinguish frontier models. Co…

cs.MA2025

How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity

Zihan Ma, Dongsheng Zhu, Shudong Liu +6

Current safety evaluations for LLM-driven agents primarily focus on atomic harms, failing to address sophisticated threats where malicious intent is concealed or diluted within com…