5 papers
Probing Diffusion Denoising Dynamics for Contrastive Representation Learning
Yasong Dai, Zeeshan Hayder, David Ahmedt-Aristizabal +1
Text-to-image diffusion models exhibit unprecedented generative capability and contain rich intermediate representations that can be useful for discriminative vision tasks. Motivat…
Fast-dLLM++: Fréchet Profile Decoding for Faster Diffusion LLM Inference
Siva Rajesh Kasa, Yasong Dai, Sumit Negi +1
Diffusion large language models promise parallel token generation, yet inference remains bottlenecked by deciding which masked tokens can be safely committed together. Fast-dLLM ad…
BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation
Yasong Dai, Zeeshan Hayder, David Ahmedt-Aristizabal +1
Recent diffusion and flow matching models have demonstrated strong capabilities in image generation and editing by progressively removing noise through iterative sampling. While th…
Rethinking Test Time Scaling for Flow-Matching Generative Models
Qingtao Yu, Changlin Song, Minghao Sun +6
The performance of text-to-image diffusion models may be improved at test-time by scaling computation to search for a generated image that maximizes a given reward function. While…
Probability Density Geodesics in Image Diffusion Latent Space
Qingtao Yu, Jaskirat Singh, Zhaoyuan Yang +5
Diffusion models indirectly estimate the probability density over a data space, which can be used to study its structure. In this work, we show that geodesics can be computed in di…