LIFT: Layout-In-Future Video Generation under Large Viewpoint Change via On-Policy Self-Distillation
Paper • 2609.38146 • Published • 10
AI & ML interests
None defined yet.
Recent Activity
xuhaiyang3110
authored a
paper 8 days ago
wchai
submitted a
paper to Daily Papers 8 days ago
wchai
submitted a
paper to Daily Papers 23 days ago
xuhaiyang3110
authored 9
papers about 1 month ago
RECAP-Forcing: Retaining Content Appearances for Long Video Generation
Paper • 2608.26671 • Published • 6
CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning
Paper • 2512.08135 • Published
VideoNSA: Native Sparse Attention Scales Video Understanding
Paper • 2510.02295 • Published • 10
OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps
Paper • 2509.19282 • Published • 8
YOLO-Count: Differentiable Object Counting for Text-to-Image Generation
Paper • 2508.00728 • Published
Bayesian Diffusion Models for 3D Shape Reconstruction
Paper • 2403.06973 • Published
DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion
Paper • 2507.22825 • Published
Science-T2I: Addressing Scientific Illusions in Image Synthesis
Paper • 2504.13129 • Published • 3
OmniControlNet: Dual-stage Integration for Conditional Image Generation
Paper • 2406.05871 • Published
xuhaiyang3110
submitted a
paper to Daily Papers about 1 month ago
sainx
authored a
paper 4 months ago
Fiaa
authored 4
papers 8 months ago
Science-T2I: Addressing Scientific Illusions in Image Synthesis
Paper • 2504.13129 • Published • 3
Learning Human-Perceived Fakeness in AI-Generated Videos via Multimodal LLMs
Paper • 2509.22646 • Published • 17
UEval: A Benchmark for Unified Multimodal Generation
Paper • 2601.22155 • Published • 2
Reinforced Attention Learning
Paper • 2602.04884 • Published • 30
sainx
authored a
paper 8 months ago
sainx
authored a
paper 9 months ago