34 papers
Certified Multi-Turn Robustness for LLM Safety via Compositional Bounds and Safety Persistence
Yang Liu, Bin Chong, Wenkai Yang +9
Large language models (LLMs) are vulnerable to multi-turn jailbreak attacks that progressively manipulate conversation context. Existing certified robustness methods are limited to…
Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling
Changze Lv, Zhenghua Wang, Yiran Ding +9
Large Language Models (LLMs) still struggle with the ``lost-in-the-middle'' problem, where critical information located in the middle of long-context inputs is often underrepresent…
AMix-1: A Pathway to Test-Time Scalable Protein Foundation Model
Changze Lv, Jiang Zhou, Siyu Long +22
We introduce AMix-1, a powerful protein foundation model built on Bayesian Flow Networks and empowered by a systematic training methodology, encompassing pretraining scaling laws,…
Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation
Changze Lv, Jie Zhou, Wentao Zhao +12
Nowadays, developing reliable DeepResearch-style long-form report generation remains challenging, as training and evaluation lack verifiable reward signals. Accordingly, rubric-bas…
AMix-2: Establishing Protein as a Native Modality in Large Language Models
Keyue Qiu, Yixin Wu, Lihao Wang +19
We present AMix-2, a protein-text foundation model that establishes protein as a native modality in large language models (LLMs), unifying protein understanding and sequence design…
From Static Context to Calibrated Interactive RL: Mitigating Distribution Shift in Multi-turn Dialogue with Aligned Simulator
Xiaohua Wang, Jiakang Yuan, Zisu Huang +5
A long-standing goal of the research community is to develop highly interactive LLM-based dialogue agents. Recent research focuses on optimizing policies based on fixed offline log…