Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression
Paper • 2512.05081 • Published • 33
yoonheeji
heez
AI & ML interests
None yet
Recent Activity
updated a model about 2 months ago
heez/qwen-omni-pos-lora128 published a model about 2 months ago
heez/qwen-omni-pos-lora128 updated a model about 2 months ago
heez/qwen-omni-cnt-lora128Organizations
None yet
upvoted a paper 7 months ago
upvoted a paper 9 months ago
upvoted 4
papers about 1 year ago
Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation
Paper • 2506.11924 • Published • 35
Fine-Grained Perturbation Guidance via Attention Head Selection
Paper • 2506.10978 • Published • 25
Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs
Paper • 2504.15280 • Published • 25
URECA: Unique Region Caption Anything
Paper • 2504.05305 • Published • 35
upvoted a paper over 1 year ago