TL;DR
It is argued that recent progress in video understanding is measured by benchmarks and protocols that can be solved without reliably perceiving spatiotemporal evidence, rewarding language-driven plausibility over video-grounded inference.
GlanceWAM is introduced, which decouples imagination from control within a single video DiT: an asynchronous proposer glances ahead on a slow clock to imagine a single lookahead frame seconds into the future in the background, while an action head decodes action chunks at control rate purely in latent space without blo...
A diagnostic toolkit for auditing what benchmark scores for open-source Video-LLM models actually measure, and finds the accuracy does not come from character tracking.
This work introduces MotionPhys, a lightweight and interpretable framework that treats sparse motion trajectories as physical evidence rather than relying on appearance artifacts or generator-specific traces and reveals subtle motion inconsistencies that are difficult to capture with conventional visual cues and transf...
It is indicated that current VLMs can identify anomalies within individual frames but struggle to integrate information across frames to reason about temporal consistency, and TimeCatch provides a controlled benchmark for evaluating temporal grounding in vision-language models.
StreamFlow is introduced, an efficient visual memory framework that enables dynamic, on-demand access to historical visual information and improves the visual attention score while reducing end-to-end latency and peak memory, enabling more visually grounded and efficient reasoning.
An inference-time adaptive guidance method is proposed, which exploits this intrinsic feature attention pattern to dynamically amplify compositional video conditioning signals precisely when the policy relies on future rollouts, and mitigates the OOD-ID compositional generalization gap.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
