8 papers
EasyBCI Agent: Towards Universal Neural Data Preprocessing for Brain-Computer Interfaces
Yu Zhu, Runkai Zhao, Zhimin Zhou +15
Brain-computer interfaces translate neural activity into device commands, yet their performance hinges on preprocessing that remains manual, expert-dependent and poorly reproducibl…
SeekBrain: An Autonomous Multi-Agent System for Accelerating Neuroscience Discovery
Jiamin Wu, Peishan Xiang, Jingyang Chen +26
Modern neuroscience relies on integrating multi-scale, multimodal datasets to uncover the neural principles underlying intelligence. However, analytical challenges posed by highly…
SciDataCopilot: An Agentic Data Preparation Framework for AGI-driven Scientific Discovery
Jiyong Rao, Yicheng Qiu, Jiahui Zhang +29
The current landscape of AI for Science (AI4S) is predominantly anchored in large-scale textual corpora, where generative AI systems excel at hypothesis generation, literature sear…
Spark-Prover-X1: Formal Theorem Proving Through Diverse Data Training
Xinyuan Zhou, Yi Lei, Xiaoyu Zhou +7
Large Language Models (LLMs) have shown significant promise in automated theorem proving, yet progress is often constrained by the scarcity of diverse and high-quality formal langu…
Adaptive Reinforcement Learning for Dynamic Configuration Allocation in Pre-Production Testing
Yu Zhu
Ensuring reliability in modern software systems requires rigorous pre-production testing across highly heterogeneous and evolving environments. Because exhaustive evaluation is inf…
Early Stopping Chain-of-thoughts in Large Language Models
Minjia Mao, Bowen Yin, Yu Zhu +1
Reasoning large language models (LLMs) have demonstrated superior capacities in solving complicated problems by generating long chain-of-thoughts (CoT), but such a lengthy CoT incu…
Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models
Yang Zhang, Yu Yu, Bo Tang +8
With the rapid development of Large Language Models (LLMs), aligning these models with human preferences and values is critical to ensuring ethical and safe applications. However,…
Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
Yu Zhu, Chuxiong Sun, Wenfei Yang +8
Reinforcement Learning from Human Feedback (RLHF) is the prevailing approach to ensure Large Language Models (LLMs) align with human values. However, existing RLHF methods require…