-
When can transformers reason with abstract symbols?
Paper • 2310.09753 • Published • 3 -
In-Context Pretraining: Language Modeling Beyond Document Boundaries
Paper • 2310.10638 • Published • 28 -
Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
Paper • 2310.09520 • Published • 11 -
Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Paper • 2309.08532 • Published • 52
Lu Yu
VoladorLuYu
AI & ML interests
Neuro-Symbolic, Large Language Models, Graph Machine Learning
Recent Activity
upvoted a paper 5 days ago
SWE-Trail: History-Guided Trajectory Collection for Coding Agent Training updated a collection 11 months ago
LLM+Self-Play RL upvoted a paper 11 months ago
SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution ScenariosOrganizations
None yet