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 226
SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation
High-resolution 3D generation increasingly relies on voxel latents and multi-stage pipelines that first predict active structure and then synthesize local geometry.Embedding Prediction Helps Image Generation
In diffusion transformers, a class label or a text prompt is embedded once, and the same condition is reused at every denoising step.PROWBench: Do Video Models Render What the Program Specifies?
Programmable world models separate executable dynamics from visual generation, offering a promising foundation for next-generation game engines.One Basis to Animate Them All: Gaussian Blendshape Distillation for Real-Time Avatars
3D Gaussian avatars support fast rendering, however, their real-time animation is often challenged by the costly neural inference.Sphere Encoder 2
Sphere Encoder is an autoencoder that generates images by decoding random points from a high-dimensional latent sphere.Moore, Escher, Penrose: A Conformal Golden Braid
I don't think I have ever done anything as peculiar in my life.ZAGNet: Zone-Aware Graph Aggregation Network for Patient-Level Lung Ultrasound Diagnosis
Patient-level lung ultrasound (LUS) diagnosis requires integrating findings acquired across multiple anatomical zones, yet clinical examinations frequently involve variable and incomplete scanning…Event-guided Neural Video Compression
Neural video codecs derive motion and temporal contexts mainly from RGB frames, leaving room for cross-modal guidance from complementary temporal observations.Confidence-Gated Cloud-Edge Cascade Triage via Variational Risk Minimization for Medical Imaging
Emergency chest X-ray (CXR) triage has a structural modality gap: reports arrive after triage decisions, yet multimodal foundation models require image-text inputs.Reliability Stress Tests and Decision-Time Routing for Chest X-ray Vision-Language Models
Medical vision-language model (VLM) evaluation is sensitive to workflow design, prompting strategy, and benchmark construction, yet most studies treat these factors in isolation.EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling
3D editing methods are usually tested on a single edit, yet an asset is built through a long sequence of revisions, each of which must implement the requested change while leaving everything else…DeskForge: Dense Supervision from Desktop Environments for Computer-Use Agents
Computer-use agents need to reliably ground action targets in complex desktop scenes, where multiple applications, overlapping windows, and visually similar controls compete for attention.SCION: Scene Composition with Instanced Neural Primitives
Real-world scenes are compositional: bricks, blades of grass, pebbles, and tree leaves recur across human-built and natural environments.World-Calibrated Proposal-to-Action Flow for Vision-Language-Action Models
Flow-based Vision-Language-Action (VLA) policies generate action chunks by transporting samples from a task-agnostic isotropic Gaussian source.SCOPE-4D: Endoscopic 4D Geometry Foundation Models
Geometric understanding supports endoscopic navigation and robotic assistance, but learning reliable endoscopic geometry faces two challenges: scarce geometric annotations and ambiguity between…Confidence-Controlled XAI Auditing for Pedestrian Detection under Domain Shift
Explainability is increasingly required for perception models in intelligent vehicles, yet whether explanations remain faithful under driving domain shift is still poorly understood.EviDent-CBCT: Evidence-Bottlenecked Report Generation from Dental CBCT under Non-Exhaustive Report Supervision
Dento-maxillofacial cone-beam CT (CBCT) reports may contain dozens of tooth-specific, anatomical, and spatial findings from a single 3D scan.FactorSplat: Appearance-Controllable Gaussian Proxies for Medical Volume Rendering
Transfer functions (TFs) control color and visibility in medical volume rendering, but image-trained Gaussian proxies typically bake one transfer function into their appearance.Octrees as an Explicit 3D Language
Existing 3D large language models (LLMs) compromise on two fronts: they compress shapes into latent codebook indices or coordinate text, which removes spatial structure from what the model observes…An AI-Based Multi-Stage Approach for Androgenetic Alopecia Assessment from Low-Magnification Scalp Images
Androgenetic alopecia (AGA) is characterized by patterned follicular miniaturization, increased single-hair follicular units, and altered hair-shaft diameter.