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 234
Revisiting On-policy Adversarial Black-Box Distillation: Calibrating Groupwise Reward Geometry for Effective Advantage Construction
Black-box distillation is a practical route for transferring capabilities from API-accessible large language models that expose only text outputs into smaller student models.Seeing as Humans Do: Learning from Motion to Segment Anything Without Supervision
The Segment Anything Model (SAM) relies heavily on massive manual annotations, creating a fundamental bottleneck for model scaling.Inline Memory Meets Reusable Skills: Memory-centric Framework for Vision-Language-Action Model
Vision-Language-Action (VLA) models have shown strong promise for general-purpose robotic manipulation, yet adapting them to new tasks and domains remains inefficient: existing methods often rely on…P-SRM: Selective Recovery of Rejected Predictions in Visual Tracking
Many visual tracking methods use rejection mechanisms to suppress unreliable predictions.Spherical Interpolation for Backward-Compatible Multimodal Representations
Contrastive vision-language models map visual and textual representations into a shared normalized embedding space, making cosine similarity the natural metric for cross-modal retrieval.DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes
Reconstructing dynamic driving scenes from recorded sensor data supports closed-loop evaluation of autonomous driving systems by synthesizing observations beyond the original trajectory.A PyTorch Library for Hyperspectral Image Models: Technical Report
Hyperspectral remote sensing has advanced across diverse deep learning paradigms, including spectral spatial CNNs, Vision Transformers, Mamba, graph neural networks, Kolmogorov Arnold networks, and…Grounding with Confidence: Controllable Generative Video Temporal Grounding
Video temporal grounding supports applications such as video search, content review, and automated editing by localizing events described in natural language.Spatial-Temporal Multi-scale Network for Screen Content Video Quality Enhancement
Different from natural videos, Screen Content Videos (SCVs) are characterized by abrupt motion, scene switches, and high-frequency details such as text and graphics.Learning Where to Look: Anatomical Grounding and Guided Attention for Cardiac MRI Vision-Language Models
Cardiac magnetic resonance imaging (CMR) enables assessment of cardiac anatomy, ventricular function, and myocardial tissue characteristics.NavHarness: Adaptive Goals for Agentic Vision-Language Navigation
Vision-Language Navigation (VLN) requires embodied agents to generate actions based on instructions and observations.MCD: Causal Distillation of Multimodal In-Context Learning in Large Vision-Language Models
Large vision-language models (LVLMs) exhibit strong multimodal in-context learning (ICL) capabilities, yet this ability degrades substantially as model size decreases.CoVisco: Codec-Native Vision Encoder with Native Token Compression for Unified Image-Video Understanding
Vision-language models face a fundamental scaling bottleneck: the number of visual tokens grows with both temporal duration and spatial resolution, making long-video understanding expensive for the…Super-Resolving Unseen Hyperspectral Sensors at Any Scale via Spatial Operators
Achieving cross-sensor generalization and arbitrary-scale reconstruction with a single model remains challenging in hyperspectral super-resolution (HSR).Reliability-Aware Checkpoint Selection for Domain Generalization
Checkpoint selection in domain generalization often relies on source-validation accuracy, yet the selected checkpoint need not provide reliable probabilities on unseen target domains.LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception
Hour-scale audio-visual question answering is constrained by a context dilemma: dense whole-recording encoding rapidly exhausts context limits, whereas uniform temporal compression severely dilutes…Learning to Reason with Compressed Context: Ground-Truth-Free Adaptation of OmniLLMs via Self-Distillation
Omni-modal large language models (OmniLLMs) enable unified audio-video understanding, but their long multimodal token sequences make deployment computationally expensive.Reconstructing the Dynamic World: A Representation-Centric View of 4D Scene Reconstruction
4D scene reconstruction aims to recover the evolving geometry, appearance, and motion of dynamic environments from visual observations.Multi-Link Safety Filtering for VLA Policies Around Moving Hazards
A vision-language-action (VLA) policy can finish a manipulation task while knocking over objects unrelated to it, so task success alone does not show that the policy is safe to deploy in clutter.Can We Anticipate Violence? Multimodal Learning from Pre-Incident Behavioral Cues
Detecting violence after it begins is important from recognizing behavioral cues that appear immediately beforehand.