The paper introduces EquiSD, a label‑free training method that exploits scale equivariance to improve metric grounding in vision‑language models. By projecting model predictions onto a scale‑equivariant family and fine‑tuning on the resulting targets, EquiSD boosts a 3B model’s median response slope from 0.66 to 0.94 and raises mean relative accuracy by 9.2 points across simulated scales, with positive transfer to real QuantiPhy videos.
Metric questions about video require vision-language models to use supplied real-world references to convert visual measurements into physical units. Yet we find that current models use this scale inf...
arXiv:2606. 15134v1 Announce Type: cross Abstract: Vision encoders for retrieval are typically trained with class-label supervision: each training pair reduces to a scalar that uniformly pushes the embedding apart or pulls it together, as if every visual attribute either differed or matched.
arXiv:2605. 16713v2 Announce Type: replace-cross Abstract: Modern Vision-Language Models (VLMs) achieve strong semantic recognition, yet remain brittle on elementary spatial relations such as left of, on, behind, and between.
arXiv:2608. 02150v2 Announce Type: replace-cross Abstract: Embodied intelligence and world models require video understanding systems to go beyond recognizing objects and actions and develop an understanding of physical regularities.
The paper introduces Clue-OPSD, a clue‑privileged on‑policy self‑distillation framework that improves long‑video understanding by focusing on short, question‑relevant clue intervals rather than the entire video. Experiments on multiple benchmarks and Qwen3.5 model scales show that this approach consistently outperforms standard backbone models and competes strongly with supervised post‑training baselines, all while requiring fewer input frames and no additional inference modules.
arXiv:2606. 00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models.
Embodied intelligence and world models require video understanding systems to go beyond recognizing objects and actions and develop an understanding of physical regularities. However, despite their strong performance on general video understanding tasks, current video-language models still struggle to reliably determine whether an observed event conforms to specific physical laws.
VKnowU is a benchmark that tests multimodal large language models (MLLMs) on their grasp of visual knowledge—intuitive, human-like understanding of physical and social principles in videos. The benchmark contains 1,680 questions across 1,249 videos, covering eight core types of visual knowledge, and shows that current state‑of‑the‑art MLLMs still lag behind human performance, especially on world‑centric tasks. To address this gap, the authors release VKnowQA and VideoKnow+, a baseline model that incorporates visual knowledge via a See‑Think‑Answer framework and reinforcement learning, improving performance on VKnowU and related datasets.
arXiv:2510. 01483v3 Announce Type: replace-cross Abstract: Vision-language models (VLMs) demonstrate strong image-level scene understanding, but reasoning over long egocentric video remains costly: because VLMs maintain no persistent memory or explicit spatial representation, all sampled frames must be re-processed for every new query.
arXiv:2607. 11862v1 Announce Type: cross Abstract: Current Video Large Language Models (Video LLMs) excel in question answering (QA) but largely operate as black boxes, providing textual answers without verifiable visual grounding.
PhysMLLMs introduces physics-inspired spatial continuity priors into video multimodal large language models to address spatio‑temporal inconsistencies such as jitter, drift, and identity switches. The method, called Global Representation Prior Alignment (REPA‑Global), distills global visual representations from a frozen DINOv2 teacher during training, aligning student representations without affecting inference speed. Experiments on multiple video benchmarks show improved segmentation mask quality and cross‑frame consistency, especially for challenging scenarios involving small targets, fast motion, occlusion, and distractors, while maintaining comparable performance on single‑frame image segmentation and general VLM tasks.
Video generation models are increasingly capable of producing realistic videos, but they still struggle to generate videos that follow basic physical laws. Compounding this is a lack of reliable granular evaluation methods for localizing and specifying physical law violations in videos.