activity
20242026
collaborators

6 papers

cs.CV2026

Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility

Yiheng Li, Feng Liang, Dan Kondratyuk +3

The substantial training cost of diffusion models hinders their deployment. Immiscible Diffusion recently showed that reducing diffusion trajectory mixing in the noise space via li…

cs.CV2026

PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation

Yuanhao Cai, Kunpeng Li, Menglin Jia +11

Recent advances in text-to-video (T2V) generation have achieved good visual quality, yet synthesizing videos that faithfully follow physical laws remains an open challenge. Existin…

cs.CL2025

NeSTR: A Neuro-Symbolic Abductive Framework for Temporal Reasoning in Large Language Models

Feng Liang, Weixin Zeng, Runhao Zhao +1

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, temporal reasoning, particularly under comp…

cs.CV2025

Synthesizing Artifact Dataset for Pixel-level Detection

Dennis Menn, Feng Liang, Diana Marculescu

Artifact detectors have been shown to enhance the performance of image-generative models by serving as reward models during fine-tuning. These detectors enable the generative model…

cs.CV2025

Looking Backward: Streaming Video-to-Video Translation with Feature Banks

Feng Liang, Akio Kodaira, Chenfeng Xu +3

This paper introduces StreamV2V, a diffusion model that achieves real-time streaming video-to-video (V2V) translation with user prompts. Unlike prior V2V methods using batches to p…

cs.CV2024

Similarity Trajectories: Linking Sampling Process to Artifacts in Diffusion-Generated Images

Dennis Menn, Feng Liang, Hung-Yueh Chiang +1

Artifact detection algorithms are crucial to correcting the output generated by diffusion models. However, because of the variety of artifact forms, existing methods require substa…