Learning from Failures in Multi-Attempt Reinforcement Learning
arXiv
Mar 4, 2025
Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking
ACL 2025, Oral (243 out of 3000 accepted papers)
Feb 27, 2025
Unlocking Emergent Modularity in Large Language Models
NAACL 2024, Outstanding Paper Award, (6 out of 2434 submissions)
Jun 29, 2024
Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
NeurIPS 2024 Spotlight
May 30, 2024
Tracking single cell evolution via clock-like chromatin accessibility
Nature Biotechnology 2024
May 20, 2024
Think Before You Act: Decision Transformers with Working Memory
ICML 2024
May 19, 2024
Massive Editing for Large Language Models via Meta Learning
ICLR 2024
Jan 16, 2024
Unifying Likelihood-free Inference with Black-box Sequence Design and Beyond
ICLR 2022 Spotlight
Jan 20, 2022
Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with 1/n Parameters
ICLR 2021 Outstanding Paper Award (8 out of 2997 submissions)
Apr 2, 2021