6 papers
RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States
Yi Yang, Zhennan Chen, Yihong Zhuang +5
Learning-based memory systems for self-evolving LLM agents face two tightly coupled challenges. First, trajectory-indexed utilities grow with the interaction history, thereby dispe…
Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning
Chen Zhao, Jiajun Ma, Qilong Huang +6
While Multimodal Large Language Models (MLLMs) have advanced video understanding, achieving precise temporal and cross-modal alignment in audiovisual video captioning remains a for…
UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset
Chen Zhao, En Ci, Yunzhe Xu +5
Ultra-high-resolution (UHR) text-to-image (T2I) generation has seen notable progress. However, two key challenges remain : 1) the absence of a large-scale high-quality UHR T2I data…
MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs
Yipeng Du, Tiehan Fan, Kepan Nan +6
Despite advancements in Multimodal Large Language Models (MLLMs), their proficiency in fine-grained video motion understanding remains critically limited. They often lack inter-fra…
OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
Kepan Nan, Rui Xie, Penghao Zhou +6
Text-to-video (T2V) generation has recently garnered significant attention thanks to the large multi-modality model Sora. However, T2V generation still faces two important challeng…
InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption
Tiehan Fan, Kepan Nan, Rui Xie +6
Text-to-video generation has evolved rapidly in recent years, delivering remarkable results. Training typically relies on video-caption paired data, which plays a crucial role in e…