Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
Paper • 2504.02821 • Published • 10
cool
-
-
TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos
Paper • 2504.17343 • Published • 13 -
ViSMaP: Unsupervised Hour-long Video Summarisation by Meta-Prompting
Paper • 2504.15921 • Published • 7 -
Causal-Copilot: An Autonomous Causal Analysis Agent
Paper • 2504.13263 • Published • 7 -
Distilling semantically aware orders for autoregressive image generation
Paper • 2504.17069 • Published • 7 -
VideoDeepResearch: Long Video Understanding With Agentic Tool Using
Paper • 2506.10821 • Published • 19 -
Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models
Paper • 2506.07177 • Published • 23 -
lym00/Wan2.2_T2V_A14B_VACE-test
17B • Updated • 1.65k • 42 -
Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation
Paper • 2509.18824 • Published • 23 -
SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
Paper • 2509.24695 • Published • 47 -
DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
Paper • 2509.25182 • Published • 39 -
lovis93/next-scene-qwen-image-lora-2509
Image-to-Image • Updated • 20.2k • • 599 -
Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting
Paper • 2510.08696 • Published • 15 -
TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control
Paper • 2510.09561 • Published • 9 -
JunhaoZhuang/FlashVSR
Video-to-Video • Updated • 2.56k • 178 -
QingyanBai/Ditto_models
Video-to-Video • Updated • 74 -
meituan-longcat/LongCat-Video
Text-to-Video • Updated • 896 • • 454 -
krea/krea-realtime-video
Text-to-Video • Updated • 300 • 274 -
TencentARC/RollingForcing
Text-to-Video • Updated • 15 -
Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation
Paper • 2510.24821 • Published • 41 -
Scaling Latent Reasoning via Looped Language Models
Paper • 2510.25741 • Published • 229