AI & Machine Learning · Computer Science & AI
Computer Vision
The newest papers in Computer Vision that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 29 September 2026 to 5 November 2026: 4,999 arXiv preprints and 1 OpenAlex record.
Get the few papers worth your time in Computer Vision every morning.
Follow Computer Vision and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 179
Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement
Most robot policies keep a model in the control loop: a VLA maps observations to actions, and an Agent Harness, such as Agent-as-Policy or Harness VLA queries a VLM for decision making at run time.AgentGarten: Code Worlds for Evolving Agents
Interactive virtual worlds allow agents to learn through exploration and interaction.WorldAlign: Decoupled 4D Reward for World-Consistent Video Generation
Faithful visual world simulation requires generated videos to maintain 4D world consistency, encompassing both static and dynamic consistency.GenIA: Generative Reconstruction with Test-Time Input Alignment
Reconstructing complete 3D object assets from monocular or sparse multi-view observations remains challenging.SpaceFlow: Locally Controllable 3D Generation
Current 3D generation methods lack explicit local control: geometric adherence is often defined by a global control strength, and appearance cannot be specified locally.SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models
Existing spatial reasoning benchmarks mainly test spatial perception: reading off relations already visible in the input.ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills
Skill-augmented agents improve sample efficiency by distilling successful trajectories into reusable strategies.LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC
World action models (WAMs) predict actions and future observations, typically from a reconstruction-based representation that carries noisy, redundant information which can complicate downstream…WorldCast: Distributed Multiplayer World Models
Multiplayer world models must generate independently controlled views with consistent representations of both players and their shared environment.MAMHOI: Factorizing Scene-Aware Human-Object Interaction through Affordances
Generating realistic human-object interactions (HOI) in complex 3D scenes requires two complementary capabilities: reasoning about interaction feasibility in the environment and synthesizing…WOVEN: Weaving Visual World Modeling into Multimodal LLMs
Multimodal large language models (MLLMs) struggle with spatial, embodied, physical, and temporal reasoning.OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video
Single-image, multi-image, and video deep research require different visual operations but share a workflow of visual grounding, external retrieval, and fact composition.Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching
Dense correspondence matching has historically been bounded by simplifying spatio-temporal priors, such as smooth motion and rigid geometry.Pumpire: Unified Benchmark for Metric Distance Estimation
We present Pumpire, a unified benchmark for evaluating metric point-pair distance estimation capability of both image- and video-level 3D foundation models, with or without depth priors.FastBench: Can Streaming VLMs Perceive High-Dynamic Real-World Streams?
Streaming Video Large Language Models (VLMs) enable continuous video understanding, yet existing benchmarks focus on low-dynamic scenarios.LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation
Generating an egocentric video from a single exocentric recording is a challenging case of novel view synthesis, as the two cameras share little overlap and much of the target view is unobserved.One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
In this work, we show that a single Transformer block, applied recurrently, can match the accuracy of a full-depth vision encoder at comparable inference FLOPs without intermediate feature…VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation
Vision-Language-Action (VLA) models have emerged as powerful foundations for robotic manipulation, but their reliance on fixed camera configurations during training makes them brittle to changes in…BrickBench: Evaluating Agentic Brick Design
We propose BrickBench, a benchmark for agentic text-conditioned LEGO-set design.Hybrid Cinematography: Previsualizing and Managing Hallucination Risk in Generative Video Reshooting
On a film set, the camera move is committed during a take.