Lang3DSeg introduces a point‑transformer backbone for open‑vocabulary, annotation‑free 3D LiDAR segmentation, trained from scratch without geometric pre‑training. It tackles noise from 2D‑to‑3D label projections by applying a class‑priority rule and truncating projected instances at depth gaps, thereby correcting depth‑ambiguity errors. The method achieves state‑of‑the‑art results on nuScenes (52.8 % mIoU) and SemanticKITTI (41.4 % mIoU) while operating in real‑time on a single LiDAR sweep.
By Cigdem Kokenoz, Amir Salarpour, Alkim Domeke, Christopher Salas, Pedram MohajerAnsari, Long Cheng, Mert D. Pes\'e, Bing Li
The paper reviews end‑to‑end autonomous driving (E2E‑AD) training, framing it as a Data‑Strategy‑Platform system. It surveys recent advances in data pipelines, learning paradigms, and training infrastructures, and discusses how these layers interact to influence model performance, robustness, and deployability. The authors highlight current limitations and propose a future vision that prioritizes data value, foundation‑driven generalization, and integrated training‑testing loops for more robust, scalable, and trustworthy autonomous driving systems.
By Chengkai Xu, Yiming Cui, Jiaqi Liu, Yicheng Guo, Cheng Qin, Geyuan Zhang, Xinwei Dong, Shiyu Fang, Peng Hang, Jian Sun
The paper introduces PCSR-Bench, a benchmark of 84,373 question‑answer pairs derived from 2,600 omnidirectional images across 26 indoor environments, designed to evaluate perspective‑conditioned spatial reasoning (PCSR) in multimodal large language models (MLLMs). It reports a significant perception–reasoning gap, with accuracy dropping from 57.59% on limited field‑of‑view reasoning to as low as 0.64% on open‑ended compositional directional chains. An RL‑based diagnostic study on a 7B‑scale model shows that reward shaping can improve performance to 60.06% on a controlled task, indicating partial plasticity of PCSR capabilities.
By Yuangong Chen, Wai Keung Wong, Jiaxing Li, Ioannis Patras, Xu Zheng
The paper introduces GTA‑VLA, an interactive Vision‑Language‑Action framework that lets users guide robot policies with explicit visual cues such as affordance points, boxes, and traces. Unlike traditional direct sense‑to‑act models, GTA‑VLA incorporates a spatial‑visual Chain‑of‑Thought that blends human guidance with internal task planning, and couples this reasoning module with a lightweight reactive action head for efficient execution. Experiments on the SimplerEnv WidowX benchmark show a state‑of‑the‑art 81.2 % success rate, and the framework significantly improves task success under out‑of‑domain visual shifts and spatial ambiguities, demonstrating the benefit of interactive reasoning for failure recovery in embodied control.
By Yiran Ling, Qing Lian, Jinghang Li, Qing Jiang, Tianming Zhang, Xiaoke Jiang, Chuanxiu Liu, Jie Liu, Lei Zhang
AiSearch is a flexible multimodal retrieval framework that uses Vision Language Models (VLMs) to enable natural language search over images and videos. It supports interactive search refinement through user feedback, allowing results to be tailored to the user's intent in real time. The system also provides visual benchmarking across multiple VLMs, enabling users to choose the most suitable model for their specific task.
By Ali Koksal, Mei Chee Leong, Vicky Sintunata, Ching Ling Chin, Wee Teck Fong
arXiv:2610.00604v1 Announce Type: cross
Abstract: Vision-language-action policies often see only one or a few recent frames, which makes it difficult to evaluate how they use information that disappe...
By Egor Cherepanov, Nikita Kachaev, Aleksandr I. Panov, Alexey K. Kovalev
arXiv:2610.00024v1 Announce Type: new
Abstract: Across three vision-language model architectures (LLaVA-1.5-7B, Qwen2.5-VL-7B, InternVL3-8B), we report a universal negative finding for mid-layer inte...
By Genpei Zhang
The paper introduces a method to purify LoRA-tuned large language models (LLMs) against backdoor attacks without relying on trigger knowledge, clean references, or retraining. By extracting high‑fidelity backdoor directions and projecting LoRA updates onto orthogonal null spaces in input and output channels, the approach reduces attack success rates from nearly 100% to under 10%. Experiments demonstrate that this null‑space projection preserves both the base model’s general capabilities and the new downstream skills learned through the adapter across various tasks.
By Jianwei Li, Jung-Eun Kim
arXiv:2610.00899v1 Announce Type: cross
Abstract: Autoregressive Vision-Language-Action models often represent continuous robot actions as discrete token sequences, enabling action prediction with st...
By Keisuke Shirai, Tomohiro Motoda, Hanbit Oh, Ryoichi Nakajo, Roman Mykhailyshyn, Ryo Hanai, Shotaro Miwa, Yukiyasu Domae
arXiv:2610.01670v1 Announce Type: new
Abstract: Multimodal large language models (MLLMs) are increasingly used as automated judges for instruction-based image editing and as reward signals for model...
By Yuan Huang, Zirui Song, Xiuying Chen
arXiv:2610.02081v1 Announce Type: new
Abstract: There has been a proliferation of sampling algorithms based on Wasserstein gradient flows (WGF) and forward-only diffusion processes (FODP), often acco...
By Daniel McBride, Pratik Khandagale, Cristina Garcia-Cardona, Yen Ting Lin
arXiv:2610.02117v1 Announce Type: cross
Abstract: On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by supervising students with a froze...
By Sophia Sirko-Galouchenko, Monika Wysoczanska, Andrei Bursuc, Nicolas Thome, Spyros Gidaris
arXiv:2609.39995v2 Announce Type: new
Abstract: Diffusion planners exhibit strong capabilities in generating multimodal trajectories. However, existing methods primarily rely on expert demonstrations...
By Jiaxi Ye, Chunji Lv, Guoren Wang, Changsheng Li
arXiv:2609.32353v2 Announce Type: replace
Abstract: Visual token reduction is an effective way to accelerate multimodal large language models (MLLMs), but performance deteriorates rapidly under extre...
By Junxian Li, Ruixuan Yang, Tianao Zhang, Tiange Xu, Weisheng Dong, Yulun Zhang
arXiv:2609.40245v2 Announce Type: cross
Abstract: Robot navigation in dynamic, human-centered environments requires socially-compliant decisions grounded in robust scene understanding. Recent Vision-...
By Nathan Tsoi, Michael J. Munje, Tejas Oberoi, Rishab Maheshwari, Pengen Zheng, Tanush Chauhan, Peter Stone, Joydeep Biswas
arXiv:2610.00691v1 Announce Type: new
Abstract: Recent joint audio-video generative models can synthesize realistic videos with synchronized sound, but typically generate audio as a single mixed trac...
By Zhuo Ning, AmirHossein Naghi Razlighi, Sagi Polaczek, Daniel Cohen-Or, Ali Mahdavi-Amiri
The paper introduces a method for learning binaural sound localization by using egomotion as a supervisory signal. By tracking how a camera’s direction changes relative to a sound source during a video, the authors train an audio model to predict sound directions that align with visual estimates of camera motion derived from multi‑view geometry. They evaluate this approach on a newly proposed dataset of real‑world audio‑visual videos with egomotion, demonstrating that the model can learn from real data and perform well on sound localization tasks.
By Anna Min, Ziyang Chen, Hang Zhao, Andrew Owens
The ability of vision-language models (VLMs) to associate visual identities with biographical information creates a need for selective unlearning of personally identifiable information (PII) while pre...
Open multimodal reasoning models have benefited from large-scale reasoning supervision, yet reliable post-training remains challenging due to uneven data quality, inefficient supervision construction,...
Remote multimodal models offer strong numerical reasoning capabilities over charts and speech, but sending private inputs risks exposing sensitive content. Text-only sanitization cannot directly satis...