858 citations
- Shanghai Artificial Intelligence LaboratoryCN93 papers
- Peking UniversityCN59 papers
- University of Chinese Academy of SciencesCN59 papers
- Chinese Academy of SciencesCN55 papers
- Tsinghua UniversityCN50 papers
- Institute of AutomationCN42 papers
- Shanghai Jiao Tong UniversityCN31 papers
- Shandong Institute of AutomationCN28 papers
- Beihang UniversityCN23 papers
- Fudan UniversityCN23 papers
- Chinese University of Hong KongHK17 papers
- University of Hong KongHK16 papers
39 papers · 1 filter
CausalMoE: A Billion-Scale Multimodal Foundation Model for Granger Causal Discovery with Pattern-Routed Heterogeneous Experts
Bo Liu, Di Dai, Jingwei Liu +5
Granger Causal Discovery (GCD) is fundamental for analyzing temporal dependencies in complex systems. However, existing neural GCD methods predominantly rely on a "one-size-fits-al…
MemNovo: Look Back at the Spectrum for Balanced De Novo Peptide Sequencing from Mass Spectrometry
Dongxin Lyu, Jingbo Zhou, Hongxin Xiang +2
De novo peptide sequencing from tandem mass spectrometry is pivotal in proteomics, enabling identification of novel peptides without reference databases. While recent Transformer-b…
LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective Experimentation
Zhuo Chen, Xinzhe Yuan, Jianshu Zhang +8
The high cost and data scarcity in scientific exploration have motivated the use of large language models (LLMs) as knowledge-driven components in Bayesian optimization (BO). Howev…
CoFEH: LLM-driven Feature Engineering Empowered by Collaborative Bayesian Hyperparameter Optimization
Beicheng Xu, Keyao Ding, Wei Liu +2
Feature Engineering (FE) is pivotal in automated machine learning (AutoML) but remains a bottleneck for traditional methods, which operate within rigid search spaces and lack domai…
The Two-Stage Decision-Sampling Hypothesis: Understanding the Emergence of Self-Reflection in RL-Trained LLMs
Zibo Zhao, Yuanting Zha, Haipeng Zhang +1
Self-reflection capabilities emerge in Large Language Models after RL post-training, with multi-turn RL achieving substantial gains over SFT counterparts. Yet the mechanism of how…
SLMQuant:Benchmarking Small Language Model Quantization for Practical Deployment
Jiacheng Wang, Yejun Zeng, Jinyang Guo +3
Despite the growing interest in Small Language Models (SLMs) as resource-efficient alternatives to Large Language Models (LLMs), their deployment on edge devices remains challengin…