IVRA: Improving Visual-Token Relations for Robot Action Policy with Training-Free Hint-Based Guidance Paper β’ 2601.16207 β’ Published 5 days ago β’ 6
IVRA: Improving Visual-Token Relations for Robot Action Policy with Training-Free Hint-Based Guidance Paper β’ 2601.16207 β’ Published 5 days ago β’ 6
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models Paper β’ 2601.07372 β’ Published 16 days ago β’ 38
HeartMuLa: A Family of Open Sourced Music Foundation Models Paper β’ 2601.10547 β’ Published 13 days ago β’ 38
Future Optical Flow Prediction Improves Robot Control & Video Generation Paper β’ 2601.10781 β’ Published 12 days ago β’ 19
Future Optical Flow Prediction Improves Robot Control & Video Generation Paper β’ 2601.10781 β’ Published 12 days ago β’ 19
Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA Paper β’ 2406.09396 β’ Published Jun 13, 2024 β’ 4