Sparse Weight Decomposition for Efficient Circuit Extraction
arXiv 2026.08
Re:Form -- Reducing Human Priors in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny
TMLR 2026
A Definition of AGI
arXiv 2025.10
Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking
ACL 2025, Oral (243 out of 8360 submissions)
Unlocking Emergent Modularity in Large Language Models
NAACL 2024, Outstanding Paper Award, (6 out of 2434 submissions)
Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
NeurIPS 2024 Spotlight
Tracking single cell evolution via clock-like chromatin accessibility
Nature Biotechnology 2024
Think Before You Act: Decision Transformers with Working Memory
ICML 2024
Massive Editing for Large Language Models via Meta Learning
ICLR 2024
Unifying Likelihood-free Inference with Black-box Sequence Design and Beyond
ICLR 2022 Spotlight
Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with 1/n Parameters
ICLR 2021 Outstanding Paper Award (8 out of 2997 submissions)