Papers

Filtered to vision-language models · clear filter

Browse by term

continual learning 89reinforcement learning 43vision-language models 19benchmarking 12benchmarks 12robotics 12language models 9world models 9large language models 8video generation 7multimodal models 5recursive self-improvement 5video world models 5agents 4diffusion models 4embodied AI 4foundation models 4generative models 4human-computer interaction 4multimodal large language models 4natural language processing 4policy optimization 4reasoning 4self-supervised learning 4spatial reasoning 4agentic models 3conversational AI 3dialogue systems 3evaluation benchmarks 3LLMs 3

Matching papers

Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving

360 upvotes · 31 AUG 2026 · Xin Zhou, Zongchuang Zhao, Zhibo Yang et al.

This paper develops a vision-language model for autonomous driving that combines 3D perception, question answering, and motion planning. A practitioner might care because it demonstrates a promising approach to integrating multiple tasks in autonomous driving.

MJev-Spatial: System One Spatial Intelligence via Native Attention Matching

353 upvotes · 15 OCT 2026 · Luozheng Qin, Yuhan Zhu, Changhai Zhou et al.

This paper introduces MJev-Spatial, a new AI model that can quickly understand and act in the physical world by using a unified classification framework to answer spatial intelligence tasks. Practitioners may care about this model because it can solve real-world problems faster and more efficiently than existing models.

WeVisOne-VL: Unified Visual Perception from Objects to Pixels

242 upvotes · 22 OCT 2026 · Tianming Liang, Junyi Pan, Yuxi Li et al.

This paper develops a vision-language model (VLM) that can accurately perceive objects and pixels in images, which can be useful for various applications such as self-driving cars, medical imaging, and augmented reality. Practitioners in these fields may care about the potential improvements in visual perception and object detection that this model can bring.

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

238 upvotes · 30 SEP 2026 · Qize Yu, Lianrui Fan, Boyu Chen et al.

This paper introduces GroundingPI, a new AI model that improves its ability to understand and interact with the physical world by learning to precisely identify objects and their locations, even in cluttered environments. Practitioners may care about GroundingPI's potential to enhance applications like robotics, autonomous driving, and object recognition.

RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment

202 upvotes · 14 OCT 2026 · Qingchuan Ma, Yuexiao Ma, Xiang Meng et al.

This paper evaluates how well vision-language models can understand 3D objects from 2D observations and make precise actions. Practitioners might care because it highlights the limitations of current models in tasks that require inferring object geometry and anticipating the effects of rotation.

PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models

172 upvotes · 14 SEP 2026 · DeepCybo Team, Yu Bin, Haipeng Cao et al.

This paper develops a unified model that can understand physical environments, generate actions, and predict future states, using a combination of vision, language, and embodied interactions. Practitioners may care about this model because it could be used to create robots or other agents that can interact with and adapt to their physical surroundings.

OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction

164 upvotes · 1 OCT 2026 · Xiangyu Zeng, Yuandong Yang, Zhiqiu Zhang et al.

This paper develops a unified model that combines perception, memory, and response for streaming video interaction, allowing for efficient and accurate processing of video content in real-time. Practitioners in the field of natural language processing and computer vision may care about this research as it aims to improve the performance of streaming video understanding models.

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

155 upvotes · 18 AUG 2026 · Keyu Tu, Zhuowei Chen, Mengqi Huang et al.

This paper introduces a new benchmark for video generation tasks that require both achieving a desired outcome and maintaining semantic consistency with a reference image. Practitioners might care about this research because it can help evaluate and improve the performance of video generation models in real-world applications.

PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations

147 upvotes · 27 OCT 2026 · Hanqing Wang, Zhaotian Cai, Ruichuan An et al.

This paper introduces a new model called PDRVLA that helps robots understand the physical world from visual and language inputs, and generate actions accordingly. Practitioners in robotics and AI might care about this research because it aims to improve robots' ability to perform tasks in real-world environments.

SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem

134 upvotes · 7 SEP 2026 · Soohyun Ryu, Sohee Kim, Eunho Yang

This paper helps large Vision-Language Models (LVLMs) better understand and reason about 3D scenes from 2D images, a key aspect of spatial intelligence, by training them on a synthetic dataset of block-stacking problems. Practitioners might care because improving spatial intelligence can lead to better performance on various visual tasks.

SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?

128 upvotes · 19 OCT 2026 · Zhaoxi Zhang, Hao Liang, Linxuan Wu et al.

This paper introduces a benchmark, SpatialScout, to evaluate vision-language model (VLM) agents on active 3D mapping, where agents must explore and map 3D scenes to construct accurate metric maps. Practitioners in AI and robotics might care about this research because it aims to develop agents that can build reliable 3D spatial representations through active perception.

Hy-Nomas: Towards Free-form Interactive World Generation

104 upvotes · 27 OCT 2026 · Qiaoling Chen, Jiaxiang Cheng, Xueqing Deng et al.

This paper develops a new AI model, Hy-Nomas, that can generate interactive worlds in response to user commands, allowing for more realistic and dynamic environments. Practitioners in fields like game development or virtual reality might care about this work because it could enable more immersive and interactive experiences.

VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding

104 upvotes · 5 NOV 2026 · Yu-Cheng Chou, Shihao Wang, Jin Huang et al.

This paper introduces VFlash, a method that enables fast and accurate visual planning for robots and autonomous vehicles by predicting the coordinates of visual primitives simultaneously, rather than one token at a time. Practitioners in robotics and autonomous driving may care about VFlash because it can reduce prediction errors and generate plans much faster than existing autoregressive vision-language models.

Transferring the Intelligence of VLMs to Robotic Control

101 upvotes · 19 SEP 2026 · Meng-Hao Guo, Zhe-Han Mo, Jia-Jun Wang et al.

This paper investigates whether the intelligence of vision-language models (VLMs) can be transferred to robotic control, enabling robots to learn and adapt in both digital and physical worlds. Practitioners might care because it could lead to more human-like robots that can seamlessly adapt to new environments and tasks.

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

92 upvotes · 19 AUG 2026 · Yunhao Yang, Yuexin Bian, Yunjie Tian et al.

This paper introduces Co-RL, a framework for unsupervised multi-agent reinforcement learning that enables diverse and accurate reasoning in language and vision-language models. Practitioners can use Co-RL to improve their models' ability to reason and respond without relying on expensive ground-truth supervision.

SLA: Scaling Spatial-Language-Action Model via Continual Pre-training

92 upvotes · 5 NOV 2026 · Fuhao Li, Wenxuan Song, Qizhou Huang et al.

This paper develops a model that improves robotic manipulation by learning to understand spatial relationships and manipulate objects in 3D space, and how to use this understanding in conjunction with visual and language inputs. Practitioners working on robotics and AI might care about this research because it could lead to more reliable and precise robotic systems.

Show-Harness: Just a VLM Agent Can Play Robots

89 upvotes · 9 SEP 2026 · Yanzhe Chen, Zechen Bai, Zhijun Cao et al.

This paper shows how a vision-language model (VLM) can control robots without needing extensive pretraining or specialized hardware, by providing a compact interface that links the model's intentions to specific actions. Practitioners might care about this because it could make robots more accessible and user-friendly.