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.
By Kaizhen Tan, Yang Feng, Heqing Du, Siru Tao, Xin Xu, Hanzhe Hong
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.
By Shubhang Bhatnagar, Dheeraj Baiju, Narendra Ahuja
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.
By Renjie Gu, Kaichen Zhou, Yan Luo, Mengyu Wang
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.
By Zhongjie Ba, Shengwang Xu, Peng Cheng, Jinyang Zou, Ting Yu, Zhibo Wang, Zhan Qin
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.
By Kaishen Wang, Dongdi Zhao, Yijun Liang, Dingqiang Ye, Ruibo Chen, Heng Huang, Di Fu
arXiv:2606. 29416v1 Announce Type: cross Abstract: Can a vision model truly see an object, or does it only fit surface-level visual cues?
By Xingyu Peng, Junran Wu, Yue Hou, Zhongliang Qiao, Jiaheng Liu, Shangzhe Li, Jichang Zhao, Wenjun Wu, Xianglong Liu, Yongxin Tong, Li Dong, Ke Xu
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.
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.
By Shijie Wang, Honglu Zhou, Ziyang Wang, Ran Xu, Caiming Xiong, Silvio Savarese, Chen Sun, Juan Carlos Niebles
Falcon Perception-HD applies reinforcement learning (GRPO) to autoregressive perception models, aligning them directly with precision and recall metrics rather than relying on maximum‑likelihood fine‑tuning. The RL framework introduces reward design for set‑structured outputs and multi‑head sampling control, enabling state‑of‑the‑art performance in very dense scenes (up to 500 objects) and eliminating common issues such as mask repetitions, NMS, and coordinate deduplication. Hybrid self‑annotation pipelines tailored for difficult referring expressions and dense scenes further boost RL training, with improvements observed across all difficulty levels on PBench and SACO‑Gold, and the model preserves object existence knowledge without negative samples.
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.
By Tianxiang Jiang, Sheng Xia, Yicheng Xu, Linquan Wu, Xiangyu Zeng, Limin Wang, Yu Qiao, Yi Wang
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.
By Mohamad Al Mdfaa, Svetlana Lukina, Timur Akhtyamov, Arthur Nigmatzyanov, Dmitrii Nalberskii, Sergey Zagoruyko, Gonzalo Ferrer
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.
By Siyao Yan, Bo Han, Jisheng Dang, Bimei Wang, Shude Wang, Hong Peng, Yulan Guo, Jianhuang Lai, Bin Hu, Tat-SengChua