most citedMMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos

1 citations · 3 across the 4 of their papers we have counts for

collaborators

7 papers

cs.CV2025

BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations

Weixi Feng, Chao Liu, Sifei Liu +3

Existing video generation models struggle to follow complex text prompts and synthesize multiple objects, raising the need for additional grounding input for improved controllabili…

cs.CV2024

T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design

Jiachen Li, Qian Long, Jian Zheng +4

In this paper, we focus on enhancing a diffusion-based text-to-video (T2V) model during the post-training phase by distilling a highly capable consistency model from a pretrained T…

cs.CV20241 cited

MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos

Xuehai He, Weixi Feng, Kaizhi Zheng +11

Multimodal Language Language Models (MLLMs) demonstrate the emerging abilities of "world models" -- interpreting and reasoning about complex real-world dynamics. To assess these ab…

cs.LG20241 cited

Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning

Danqing Wang, Antonis Antoniades, Kha-Dinh Luong +6

Counterfactual explanations of Graph Neural Networks (GNNs) offer a powerful way to understand data that can naturally be represented by a graph structure. Furthermore, in many dom…

cs.CV20241 cited

TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation

Weixi Feng, Jiachen Li, Michael Saxon +3

Video generation has many unique challenges beyond those of image generation. The temporal dimension introduces extensive possible variations across frames, over which consistency…

cs.LG2024

BPO: Staying Close to the Behavior LLM Creates Better Online LLM Alignment

Wenda Xu, Jiachen Li, William Yang Wang +1

Direct alignment from preferences (DAP) has emerged as a promising paradigm for aligning large language models (LLMs) to human desiderata from pre-collected, offline preference dat…