arXiv:2604. 25834v2 Announce Type: replace Abstract: With the rapid development of the Internet, users have increasingly higher expectations for the recommendation accuracy of online content consumption platforms.
arXiv:2606. 24797v1 Announce Type: cross Abstract: Recent advances in Video Large Language Models (Video-LLMs) have yielded promising performance on video question answering (VideoQA).
arXiv:2608.05707v2 Announce Type: replace Abstract: Frame selection is essential for applying Large Multimodal Models (LMMs) to long videos due to severe frame redundancy and limited context windows....
CounterVid introduces a scalable counterfactual video generation framework that creates videos differing only in actions or temporal structure while keeping scene context intact. The approach uses multimodal LLMs for action proposals and diffusion models for editing, producing a synthetic dataset of ~26k preference pairs for action recognition and sequence ordering. With the MixDPO optimization method, the authors demonstrate significant improvements in action recognition and temporal ordering on Qwen2.5‑VL and InternVL3 backbones, while maintaining overall video understanding.
arXiv:2610.00757v1 Announce Type: new Abstract: Long-video question answering is limited by the high cost of visual tokens and by the fixed context width of current VLMs. A long-video question may re...
arXiv:2506. 01274v2 Announce Type: replace-cross Abstract: Recent progress in Large Multi-modal Models (LMMs) has enabled effective vision-language reasoning, yet the ability to video understanding remains constrained by suboptimal frame selection strategies, albeit with the rapid development of video-specialized LMMs.
arXiv:2608.23329v1 Announce Type: cross Abstract: Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video a...
CoRE is a weakly supervised framework that learns fine-grained temporal and entity support for perceived risk in driving videos using only coarse video-level judgments. It first trains a video-level predictor, freezes it, and then uses structured interventions over candidate temporal regions or entity tracks to generate graded prediction-effect targets. These targets train a student model that can predict temporal and entity support directly from the original video, enabling fine-grained evidence localization without requiring detailed annotations.
Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video and its parametric memory. While Thinking-with-Video...
arXiv:2606. 09181v1 Announce Type: cross Abstract: Recent advances in video multimodal models have significantly improved VideoQA performance.
arXiv:2608. 13990v1 Announce Type: new Abstract: Driven by the attention economy, short-video Recommender Systems (RSs) are primarily optimized to maximize user engagement by promoting videos that capture attention within seconds.
arXiv:2601. 07761v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) face a fundamental dilemma in video reasoning: they are caught between the prohibitive computational costs of verbose reasoning and the hallucination risks of efficient, ungrounded approaches.