6 papers
SkillOS: Learning Skill Curation for Self-Evolving Agents
Siru Ouyang, Jun Yan, Yanfei Chen +13
LLM-based agents are increasingly deployed to handle streaming tasks, yet they often remain one-off problem solvers that fail to learn from past interactions. Reusable skills disti…
Decocted Experience Improves Test-Time Inference in LLM Agents
Maohao Shen, Kaiwen Zha, Zexue He +6
There is growing interest in improving LLMs without updating model parameters. One well-established direction is test-time scaling, where increased inference-time computation (e.g.…
Physiology as Language: Translating Respiration to Sleep EEG
Kaiwen Zha, Chao Li, Hao He +7
This paper introduces a novel cross-physiology translation task: synthesizing sleep electroencephalography (EEG) from respiration signals. To address the significant complexity gap…
RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
Kaiwen Zha, Zhengqi Gao, Maohao Shen +3
Reinforcement learning (RL) has recently emerged as a compelling approach for enhancing the reasoning capabilities of large language models (LLMs), where an LLM generator serves as…
Transformer Model Detects Antidepressant Use From a Single Night of Sleep, Unlocking an Adherence Biomarker
Ali Mirzazadeh, Simon Cadavid, Kaiwen Zha +10
Antidepressant nonadherence is pervasive, driving relapse, hospitalization, suicide risk, and billions in avoidable costs. Clinicians need tools that detect adherence lapses prompt…
REG: Rectified Gradient Guidance for Conditional Diffusion Models
Zhengqi Gao, Kaiwen Zha, Tianyuan Zhang +2
Guidance techniques are simple yet effective for improving conditional generation in diffusion models. Albeit their empirical success, the practical implementation of guidance dive…