8 papers
ContextMaster: Interactive Multi-Shot Video Creation via Fixed-Budget Sparse Context Routing
Xu Guo, Zhengxuan Wei, Xinghui Li +11
Recent video models increasingly support generation, reference conditioning, and editing within a single model, yet typically expose them as separate operations over fixed inputs.…
Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching
Guanbo Huang, Jingjia Mao, Fanding Huang +9
Flow Matching (FM) has achieved remarkable generative performance, yet it suffers from exposure bias due to discrepancies between training and inference. Existing mitigation strate…
DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams
Cong Wan, Zeyu Guo, Zijian Cai +6
Raw multimodal streams are abundant but noisy, redundant, and unaligned with any particular training objective. Turning them into supervision today means either brittle heuristics…
LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis
Qingyue Zhang, Chang Chu, Tianren Peng +4
LoRA has become a widely adopted method for PEFT, and its initialization methods have attracted increasing attention. However, existing methods have notable limitations: many metho…
Beyond the Golden Data: Resolving the Motion-Vision Quality Dilemma via Timestep Selective Training
Xiangyang Luo, Qingyu Li, Yuming Li +6
Recent advances in video generation models have achieved impressive results. However, these models heavily rely on the use of high-quality data that combines both high visual quali…
ReflexFlow: Rethinking Learning Objective for Exposure Bias Alleviation in Flow Matching
Guanbo Huang, Jingjia Mao, Fanding Huang +8
Despite tremendous recent progress, Flow Matching methods still suffer from exposure bias due to discrepancies in training and inference. This paper investigates the root causes of…