Training Large Language Models to Reason in a Continuous Latent Space
Paper
• 2412.06769 • Published
• 94
reasoning
-
-
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
Paper • 2408.03314 • Published • 63 -
ICAL: Continual Learning of Multimodal Agents by Transforming Trajectories into Actionable Insights
Paper • 2406.14596 • Published • 5 -
A Comprehensive Survey of LLM Alignment Techniques: RLHF, RLAIF, PPO, DPO and More
Paper • 2407.16216 • Published -
Thinking LLMs: General Instruction Following with Thought Generation
Paper • 2410.10630 • Published • 20 -
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
Paper • 2501.04519 • Published • 288 -
TextGrad: Automatic "Differentiation" via Text
Paper • 2406.07496 • Published • 31 -
Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving
Paper • 2002.03629 • Published -
LIMO: Less is More for Reasoning
Paper • 2502.03387 • Published • 62