TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video Paper • 2411.18671 • Published 25 days ago • 20
LLM2CLIP Collection LLM2CLIP makes SOTA pretrained CLIP modal more SOTA ever. • 10 items • Updated 11 days ago • 47
StdGEN: Semantic-Decomposed 3D Character Generation from Single Images Paper • 2411.05738 • Published Nov 8 • 14
Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale Paper • 2409.17115 • Published Sep 25 • 60
Seeing Faces in Things: A Model and Dataset for Pareidolia Paper • 2409.16143 • Published Sep 24 • 15
RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning Paper • 2409.14674 • Published Sep 23 • 41
WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling Paper • 2408.16532 • Published Aug 29 • 47
Can Large Language Models Understand Symbolic Graphics Programs? Paper • 2408.08313 • Published Aug 15 • 7
D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning Paper • 2408.08441 • Published Aug 15 • 7
JPEG-LM: LLMs as Image Generators with Canonical Codec Representations Paper • 2408.08459 • Published Aug 15 • 45
PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation Paper • 2408.07547 • Published Aug 14 • 7
Rethinking Open-Vocabulary Segmentation of Radiance Fields in 3D Space Paper • 2408.07416 • Published Aug 14 • 6
InfinityMATH: A Scalable Instruction Tuning Dataset in Programmatic Mathematical Reasoning Paper • 2408.07089 • Published Aug 9 • 13