9 papers
One Skill Does Not Fit All: Automatic Discovery and Taxonomy-Guided Routing of Frame-Selection Skills for Long-Video Question Answering
Jian Hu, Zixu Cheng, Da Li +3
Long-Video Question Answering (LVQA) requires locating decisive evidence in hour-scale videos under a limited frame budget. Most training-free methods apply the same frame-selectio…
Each Judge Its Own Yardstick: Discovering Per-VLM Taxonomies for Physical Video Evaluation
Yu Cao, Ziquan Liu, Zhensong Zhang +3
Maintaining physical consistency in video generators and world models increasingly relies on vision-language models (VLMs) as automated judges that provide reward signals, ranking…
LiteVSR: Lightweight Adaptation of Frozen Diffusion Transformers for Video Super-Resolution
Yu Cao, Ziquan Liu, Zhensong Zhang +3
Adapting large-scale pre-trained video generators for Video Super-Resolution (VSR) in novel domains remains computationally prohibitive. Methods that reformulate generation as dire…
Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation
Zengqun Zhao, Yanzuo Lu, Ziquan Liu +3
Autoregressive video diffusion has recently emerged as a promising paradigm for long-video generation, enabling causal synthesis beyond the temporal limits of bidirectional models.…
LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion
Zengqun Zhao, Ziquan Liu, Yu Cao +5
The recent success of inference-time scaling in large language models has inspired similar explorations in video diffusion. In particular, motivated by the existence of "golden noi…
GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking
Zixu Cheng, Da Li, Jian Hu +4
Video reasoning requires a fine-grained understanding of the temporal dependencies and event-level relations between objects and events in videos. Current Multimodal Large Language…
V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning
Zixu Cheng, Jian Hu, Ziquan Liu +3
Human processes video reasoning in a sequential spatio-temporal reasoning logic, we first identify the relevant frames ("when") and then analyse the spatial relationships ("where")…
AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Data
Zengqun Zhao, Ziquan Liu, Yu Cao +2
Recent advances in generative models have sparked research on improving model fairness with AI-generated data. However, existing methods often face limitations in the diversity and…
Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization
Zhaohan Zhang, Ziquan Liu, Ioannis Patras
Large Language Models (LLMs) have been found to memorize and recite some of the textual sequences from their training set verbatim, raising broad concerns about privacy and copyrig…