arXiv:2604. 03497v2 Announce Type: replace-cross Abstract: Vision-language-model (VLM)-guided reinforcement learning (RL) has recently attracted significant attention for it, replacing brittle hand-crafted rewards with semantically grounded signals; however, deploying such simulation-trained policies on real vehicles remains a fundamental challenge, because they rely on simulator-native observations and simulator-coupled action semantics with no counterpart on physical hardware.
By Zilin Huang, Zhengyang Wan, Zihao Sheng, Boyue Wang, Junwei You, Sikai Chen
arXiv:2512. 14157v2 Announce Type: replace Abstract: Recent medical MLLMs have made significant progress in generating step-by-step textual reasoning chains.
By Yankai Jiang, Yujie Zhang, Peng Zhang, Wenjie Li, Yichen Li, Jintai Chen, Xiaoming Shi, Shihui Zhen
arXiv:2607. 01876v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal understanding, yet their enormous parameter scale and cross-modal computation incur substantial memory and latency overhead, severely limiting real-world deployment on resource-constrained devices.
By Qi Lyu, Jiahua Dong, Baichen Liu, Xudong Wang, Mingfei Han, Yulun Zhang, Fahad Shahbaz Khan, Salman Khan, Lianqing Liu, Zhi Han
arXiv:2607. 01978v1 Announce Type: new Abstract: Online multimodal knowledge editing requires injecting a continual stream of visual-textual corrections into multimodal large language models (MLLMs) with bounded overhead and minimal disruption to unrelated behaviors.
By Siyuan Li, Youyuan Zhang, Ruitong Liu, Junxi Wang, Jing Li
arXiv:2507. 05624v2 Announce Type: replace Abstract: Multimodal emotion and intent recognition is essential for automated human-computer interaction, It aims to analyze users' speech, text, and visual information to predict their emotions or intent.
By Yuhan Li, Wei Zhang, Juan Chen, Jiangjia Yan, Peng Xiangli, Liangze Yin
arXiv:2607. 01751v1 Announce Type: cross Abstract: Existing medical video benchmarks primarily evaluate whether a model produces the correct answer, but rarely assess whether it answers at the right time.
By Yuan Wang, Shujian Gao, Songtao Jiang, Zhengyu Hu, Zuozhu Liu
Humans can selectively attend to a target sound and estimate its direction in complex scenarios, whereas such selective localization remains challenging for current deep learning-based systems. Sound source localization (SSL) has achieved remarkable success with deep learning, yet most methods localize all active sources without selectivity.
Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image by editing a reference image with a natural-language instruction, without relying on domain-specific annotated triplets. Most existing ZS-CIR methods rely on textual inversion to translate the reference image into pseudo-text tokens and then compose them with the instruction via simple concatenation in the text space, which can be lossy and brittle for fine-grained semantics.
License Plate Recognition (LPR) systems are critical tools in traffic monitoring, security enforcement, and urban mobility management. Traditional LPR systems often rely on a multi-stage pipeline involving object detection using You Only Look Once (YOLO) and Optical Character Recognition (OCR), which suffer from limitations such as high resource demands, poor performance in unstructured environments, and the need for large annotated datasets.
Multimodal large language models must adapt to evolving tasks and domains, yet continual improvement under bounded deployment footprint remains difficult because repeated parameter updates or growing replay stores can accumulate adaptation state over time. We study fixed-footprint continual adaptation: the deployed adaptation state is kept under a fixed memory budget, while the backbone model is left unchanged and task-specific updates are externalized.
Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal understanding, yet their enormous parameter scale and cross-modal computation incur substantial memory and latency overhead, severely limiting real-world deployment on resource-constrained devices. Binarization offers an attractive solution by drastically reducing storage and computational costs.
On-policy exploration is a crucial component for training robust Vision-Language Navigation agents, as it exposes the policy to a broader state distribution. However, such exploration inevitably leads to trajectories that deviate from expert demonstrations, resulting in a semantic mismatch between the executed visual stream and the original language instruction.
Recent multimodal large language models (MLLMs) have substantially advanced video understanding, yet long-form video QA remains challenging under fixed input token budgets, where uniform sampling can be inefficient for evidence localization. We propose ReQuest , an uncertainty-driven, question-adaptive keyframe selection pipeline that aligns question intent with relevant video content through selective computation.
arXiv:2607. 00374v1 Announce Type: cross Abstract: Composed Image Retrieval (CIR) retrieves a target image from a reference image and a textual modification.
By Jingjing Zhang, Lei Zhang, Zheren Fu, Zhendong Mao
arXiv:2607. 01212v1 Announce Type: cross Abstract: Current work on robot furniture assembly mostly focuses on toy-scale settings or single-arm manipulation.
By Chenyang Ma, Yue Yang, Radu Corcodel, Siddarth Jain, Andrew Wu, Chiori Hori, Diego Romeres
arXiv:2607. 00174v1 Announce Type: cross Abstract: We present a black-box model-stealing attack that recovers private vision-tokenizer configurations of deployed vision-language models (VLMs), including the visual patch size and input preprocessing pipeline.
By Kai Hu, Akash Bharadwaj, Weichen Yu, Matt Fredrikson
arXiv:2607. 00858v1 Announce Type: cross Abstract: Contrastive pre-training has propelled video-text alignment, yet models often inherit the critical limitations of their image-text predecessors like CLIP, resulting in entangled representations.
By Peiyuan Zhu, Shaoan Xie, Zijian Li, Yifan Shen, Namrata Deka, Harsh Shrivastava, Guangyi Chen, Kun Zhang
arXiv:2505. 19614v2 Announce Type: replace Abstract: Multimodal learning has seen remarkable progress, particularly with large-scale pre-training across various modalities.
By Sanghyuk Chun, Olga Russakovsky
arXiv:2607. 00228v1 Announce Type: cross Abstract: Modern time-domain surveys such as the Zwicky Transient Facility (ZTF) generate hundreds of thousands of alerts each night, making real-time decisions for follow-up observations a central challenge in time-domain astronomy.
By Ved G. Shah, Nabeel Rehemtulla, Adam A. Miller, Sushant Sharma Chaudhary, Michael W. Coughlin, Antoine Le Calloch, Matthew J. Graham, Joahan Castaneda Jaimes, Theophile Jegou du Laz, Ashish A. Mahabal, Frank J. Masci, Josiah Purdum, Reed Riddle, Jesper Sollerman, Anastasia Wei, Mansi M. Kasliwal
arXiv:2607. 00746v1 Announce Type: cross Abstract: The bird's-eye view (BEV) representation enables multi-sensor features to be fused within a unified space, serving as the primary approach for achieving comprehensive 3D perception.
By Xiao Zhao, Chang Liu, Mingxu Zhu, Zheyuan Zhang, Linna Song, Qingliang Luo, Chufan Guo, Kuifeng Su