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 140
RL Teaches VLMs Where to Attend but Not How to Perceive
Although reinforcement learning (RL) effectively trains Vision-Language Model (VLM) agents, the mechanisms behind these capability gains are poorly understood.CÆNL: Collapse-Based Active Neural Learning with Objective-Aligned Representation Control
Active learning changes the representations used to acquire subsequent labels.Gaussian Splatting for Real-Time Scene Reconstruction: Methods, Systems, and Trade-offs
3D Gaussian Splatting (3DGS) allows for high-quality real-time novel-view synthesis.TwinPrune: Density-Aware Two-Phase Token Pruning for Vision-Language Models
We propose a unified spatial-density signal to score token importance for both inference phases: bipartite merge for prefill and KV eviction for decode, yielding measurable gains in each stage.CrossPortrait: Cross-Species Portrait Animation via Adversarial Motion Alignment
Cross-species portrait animation, which aims to animate a source portrait of species A using a driving video of species B, is particularly challenging due to substantial anatomical differences in…FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching
Recent video super-resolution (VSR) models achieve efficient one-step generation through diffusion distillation.Benchmarking Self-Supervised 3D Medical Vision Foundation Models and Transferability Estimation
Self-supervised pretraining has expanded the pool of 3D medical foundation models, but published evaluations use different datasets, endpoints and fine-tuning protocols.Physical-Field-Bridged Material Parameter Inference from Multi-View Deformation Videos
Estimating simulation-ready material parameters from visual observations is crucial for deformable-object manipulation but challenging because material properties are only indirectly revealed…Tanawpamana: Benchmarking Vision-Language Models on Philippine Cultural Heritage Sites
Vision-language models are increasingly used to identify and describe places, yet their recognition and knowledge of specific cultures remain poorly understood, particularly in underrepresented…Morphology-aware deep learning predicts colorectal cancer survival from whole-slide images
Five-year survival prediction from hematoxylin-and-eosin whole-slide images could support risk stratification, but the task is weakly supervised, and the tissue morphologies carrying prognostic…PLEDGE: Progressive Lossy Error-Bounded Compression of 3D Gaussian Splatting
Existing 3D Gaussian Splatting (3DGS) codecs report reconstruction quality after compression, and give users little control over the distortion of individual primitives.Background2Background: a self-supervised background removal framework for high dimensional microscopy
High-dimensional microscopy captures features across space, time, and spectrum, but complex backgrounds obscure signals.Smartphone-Based, Field-Deployed AI Inspection System for Power Distribution Infrastructure
Routine inspection of power distribution infrastructure remains challenging for utilities operating geographically dispersed networks, where conventional manual inspection can be difficult to…4LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling
For video generation in dynamic world modeling, observed static and dynamic content should be efficiently reused to provide conditions for repeated generation at different times and viewpoints.From Pixels to Executable Physics: Behavior-Grounded World Models for Embodied Action Consequence Prediction
In outdoor environments, varying terrain and contact conditions can cause identical action commands to produce different motion outcomes for quadruped robots.Calibrated Disambiguation for Partial Multi-label Learning
Partial multi-label learning (PML) aims to train a classifier on datasets whose instances are over-annotated with not only relevant labels but also irrelevant labels, which is common when datasets…FrameLite: Decision-Oriented Aesthetic Cropping with a Compact Vision-Language Model
Aesthetic image cropping improves composition by balancing subjects, context, and image boundaries.MemAct: Streaming Spatial Understanding with Memory and Active Exploration
Spatial understanding is essential for embodied agents navigating and interacting with the physical world.Code2Worlds-2: Physically Plausible Agent Harness for Embodied World Simulation
Recent coding large language models (LLMs) can synthesize dynamic 4D worlds from natural language, but the resulting content remains a visual artifact.Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence
Reliable video reasoning requires models to produce correct answers and expose supporting visual evidence.