Articles tagged
Reasoning
3 articles
Demystifying Video Reasoning: Models Don't Think in Frames - They Think in Denoising Steps
Chain-of-Steps shows video diffusion models reason across denoising steps, not frames, exploring and self-correcting before converging on a single answer.
AIComputer VisionVideo Generation
SAGE: Your Reasoning Model Knows When to Stop Thinking — You Just Won't Let It
SAGE scores reasoning paths by cumulative log-probability instead of next-token probability, letting models stop thinking 40-50% earlier at equal or better accuracy.
AILLMReasoning
Attention as a Compass – Teaching Reasoning Models to Explore Smarter
AttnRL uses a model's own attention to pick branching points in process-supervised RL, beating GRPO and TreeRL by 1.8 points on math while cutting training time 8%.
AIreinforcement learningLLM