IVRA: Improving Visual-Token Relations for Robot Action Policy with Training-Free Hint-Based Guidance Paper โข 2601.16207 โข Published 5 days ago โข 5
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models Paper โข 2601.07372 โข Published 15 days ago โข 38
HeartMuLa: A Family of Open Sourced Music Foundation Models Paper โข 2601.10547 โข Published 12 days ago โข 38
Future Optical Flow Prediction Improves Robot Control & Video Generation Paper โข 2601.10781 โข Published 12 days ago โข 19
Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA Paper โข 2406.09396 โข Published Jun 13, 2024 โข 4
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy Paper โข 2406.20095 โข Published Jun 28, 2024 โข 18