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: 4,996 arXiv preprints and 4 OpenAlex records.
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 244
Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL
Multi-reward guided reinforcement learning (i.e., RL) offers a promising way to improve joint audio-video diffusion models along several complementary objectives, including modality-specific…ResComEmb: Effective and Efficient Multimodal Embedding via Residual Homogeneity Compression
Multimodal large language models (MLLMs) have shown strong potential for universal multimodal representation learning.AESOP: Asymmetric Human-Camera Generation with Translation-Intensity Control
Human motion defines an action, while a camera trajectory determines how it is presented.Seeing Is Not Addressing: Auditing Linguistic Access to Frozen Visual Geometry
Visual distinctions are often finer than those reflected in linguistic conceptualization.Codebook-Guided Cross-Modal Knowledge Distillation for Structurally Heterogeneous Features
Cross-modal knowledge distillation transfers knowledge from a teacher modality to a student modality.V-JEPA Policy: Building Effective World-Action Models on Predictive Visual Latents
World-action models (WAMs) couple future visual-state prediction with action generation.Collision-Aware and Observation-Aligned Object-Centric Scene Reconstruction from Point Cloud
Object-centric scene reconstruction requires completing partial object observations while preserving metric alignment and avoiding collisions with the surrounding.Beyond Attention Imbalance: Mitigating Hallucinations via Spectral Surgery
While Large Vision-Language Models (LVLMs) achieve remarkable success, hallucinations remain a significant barrier to their reliable deployment.UniAfford: Token-Routed Multitask Learning for Generalizable 2D-3D Affordance Perception
Affordance perception aims to localize actionable regions supporting embodied interaction, yet 2D and 3D affordance grounding have evolved as separate problems, with different task definitions…SAM Meets VLM: Parameter-Decoupled Full-Parameter Training for Unified Medical Reasoning and Segmentation
Medical multimodal large language models (MLLMs) are increasingly expected not only to answer clinical questions, but also to localize the visual evidence behind their predictions.VISTA-Bench: Benchmarking Multilingual Image Translation with Image-Specific Rubrics
Image translation is a fundamental capability of multimodal models for multilingual applications, requiring visual understanding and meaning preservation across languages.Why Cross-Skeleton Retargeting Is Non-Identifiable: Structural Limits of Generative Motion Models
Cross-skeleton motion generation trains generative models to carry action structure and motion intention from one body to another.Scaling Full Conformal Image Classifiers
Conformal prediction provides set-valued predictions with distribution-free coverage guarantees, making it attractive for high-stakes image classification.Technical note on: Zero-Training Feature-Space Alignment via Information Geometry
Deep vision models often degrade under distribution shift.FLASH: A "Generate Once, Synthesize Many" Framework for Synthetic Anomaly Generation in Industrial Anomaly Detection
Synthetic anomaly generation helps expand industrial anomaly datasets when real defects are scarce or unavailable.What Comes Next? Omni-StoryBench for Evaluating Story-Grounded Omnimodal Generation
Omnimodal evaluation should go beyond independent text, image, and speech production: individually plausible outputs may not express a coherent shared event.The Domain Is a Residue: Adapting Self-Supervised Features, Not Generators
Clearing fog, rain or snow from footage, or turning renders into photographs, must remove the source domain and keep the scene.OFBD: Object-Focused Background Debiasing for Long-Tailed Learning
Balancing performance trade-offs on long-tailed data distributions remains a long-standing challenge in visual recognition.UGO: Unified Architecture for General Multi-Object Tracking by Segmentation
General multi-object tracking (GMOT) tracks all instances of a user-specified category from a single first-frame exemplar.HyperSAM: A Promptable Foundation Model for Hyperspectral Remote Sensing
Hyperspectral remote sensing provides dense spectral measurements that are indispensable for material-level Earth observation, yet the construction of a general-purpose hyperspectral foundation…