Test-Time Training with Self-Supervision for Generalization under Distribution Shifts Paper • 1909.13231 • Published Sep 29, 2019 • 1
The Surprising Effectiveness of Test-Time Training for Abstract Reasoning Paper • 2411.07279 • Published 10 days ago • 3
Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models Paper • 2410.11081 • Published Oct 14 • 18
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context Paper • 2403.05530 • Published Mar 8 • 60
A Moral Imperative: The Need for Continual Superalignment of Large Language Models Paper • 2403.14683 • Published Mar 13 • 1
nGPT: Normalized Transformer with Representation Learning on the Hypersphere Paper • 2410.01131 • Published Oct 1 • 9
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models Paper • 2410.05229 • Published Oct 7 • 18
Aligning Machine and Human Visual Representations across Abstraction Levels Paper • 2409.06509 • Published Sep 10 • 1
Training Language Models to Self-Correct via Reinforcement Learning Paper • 2409.12917 • Published Sep 19 • 135
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters Paper • 2408.03314 • Published Aug 6 • 33
Large Language Monkeys: Scaling Inference Compute with Repeated Sampling Paper • 2407.21787 • Published Jul 31 • 3
Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking Paper • 2403.09629 • Published Mar 14 • 73
Prompt Cache: Modular Attention Reuse for Low-Latency Inference Paper • 2311.04934 • Published Nov 7, 2023 • 28
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model Paper • 2405.04434 • Published May 7 • 13
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models Paper • 2401.06066 • Published Jan 11 • 43