ThinkVid: Benchmarking Visual Reasoning in Video Generative Models
Benchmarking visual reasoning in video generation.
Harold Haodong Chen
•
•
1 min read
Show, Don't Tell: Morphing Latent Reasoning into Image Generation
A framework that integrates implicit latent reasoning into autoregressive text-to-image generation.
Harold Haodong Chen
ScalingAR: Scaling Confidence for Autoregressive Image Generation
Confidence scaling for better autoregressive image generation.
Harold Haodong Chen
LoopViT: Scaling Visual ARC with Looped Transformers
Looped (weight-tied) Transformers for Visual ARC—scale reasoning with “thinking time”.
AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation
Training-free attention scaling for text-guided image-to-video semantic fidelity.
Yexin Liu
CMT: Cross Modulation Transformer with Hybrid Loss for Pansharpening
Cross Modulation Transformer with frequency-domain hybrid loss for pansharpening.
Exploring the Low-Pass Filtering Behavior in Image Super-Resolution
We explore frequency behavior in super-resolution models and its impact on reconstruction performance.
Haoyu Deng