Longhui Yu
8 papers · 2022–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
๐ Cross-Pollinator (13) ๐ Renaissance Researcher (6) ๐ Interdisciplinary Bridge ๐ Conference Polyglot (4) ๐บ๏ธ Taxonomy Completionist (16)
๐งญ
Keyword Pioneer
๐
Trend Setter
Conferences
ICLR (4)
ACL (2)
CVPR (1)
NIPS (1)
Top co-authors
Keywords
reinforcement learning
(2)
policy optimization
(1)
transfer learning
(1)
mathematical reasoning
(1)
chain-of-thought reasoning
(1)
token efficiency
(1)
majority voting
(1)
language model
(1)
reward model
(1)
process supervision
(1)
transformer decoder
(1)
ai alignment
(1)
neural scene representation
(1)
easy-to-hard generalization
(1)
backward reasoning
(1)
bezier curve
(1)
large language model
(1)
glyph generation
(1)
answer verification
(1)
outline generation
(1)
Papers
Towards A Better Initial Policy Model For Scalable Long-CoT Reinforcement Learning
ACL 2025
Forward-Backward Reasoning in Large Language Models for Mathematical Verification
ACL 2024
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
NIPS 2024
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
ICLR 2024
Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
ICLR 2024
Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap
ICLR 2023
DeepVecFont-v2: Exploiting Transformers To Synthesize Vector Fonts With Higher Quality
CVPR 2023
Memory Replay with Data Compression for Continual Learning
ICLR 2022