Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification
Paper • 2607.24027 • Published • 34
Xin Jin
Xin1118
AI & ML interests
None yet
Recent Activity
authored a paper 10 days ago
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers authored a paper 10 days ago
AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein RecognitionOrganizations
upvoted a paper 1 day ago
authored 3
papers 10 days ago
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers
Paper • 2607.04033 • Published • 76
AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition
Paper • 2607.02271 • Published • 17
EarlyTom: Early Token Compression Completes Fast Video Understanding
Paper • 2605.30010 • Published • 32
upvoted 2
papers 14 days ago
upvoted a paper 21 days ago
submitted a
paper to Daily Papers 27 days ago
updated a
dataset about 1 month ago
published a
dataset about 1 month ago
upvoted a paper 2 months ago
authored 3
papers 2 months ago
MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
Paper • 2510.23479 • Published • 18
LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs
Paper • 2603.19217 • Published • 29
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
Paper • 2605.21195 • Published • 20
upvoted a paper 2 months ago
upvoted 4
papers 3 months ago
Fast Byte Latent Transformer
Paper • 2605.08044 • Published • 12
PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks
Paper • 2605.10977 • Published • 10
World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
Paper • 2604.24764 • Published • 119
Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
Paper • 2604.23775 • Published • 46
upvoted a collection 4 months ago