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 12
Open-HumanWAM: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models
Egocentric human video offers a scalable source of manipulation priors for robot learning, yet translating raw data scale into generalizable robot policies demands rigorous data curation and…Context-Aware Autoregressive Image Generation for Emerging Reasoning Properties
Autoregressive image generation has recently emerged as a competitive visual generation paradigm, yet its generation order is often predefined or heuristic, such as next-patch prediction…Same Layout, Different Count: What Number Words Do Past Ten in Text-to-Image Models
Ask SD3.5-Medium for twelve of an object and then, from the same starting noise, for twenty-five.Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers
A central yet under-explored question in Multimodal Large Language Models (MLLMs) is where to connect---how visual information from a hierarchical vision encoder should be wired into the layer-wise…Trainspotting: Learning Object-Centric 3D Reconstruction from Found Photos
State-of-the-art feedforward reconstruction models perform poorly on in-the-wild object-centric photo collections.Visual Token Routing: Learning to keep tokens that matter
Computer-use agents (CUAs) have recently achieved superhuman performance on several long-horizon benchmarks.LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis
We introduce LongBanana, to our knowledge the first expert-designed and expert-verified benchmark for long-context multi-reference image synthesis in the age of agent-driven image generation.CounterFactual Retrieval for Evidence-Aware Individual Animal Identification
Automated identification of individual animals is moving from small curated studies toward shared benchmarks and reusable foundation models.PixelSpline: Continuous Space-Time Video Super-Resolution via Endpoint-Anchored Shared Pixel Trajectories
Existing continuous space-time video super-resolution methods often infer motion from only two endpoint frames and model the two motion directions independently, making them vulnerable to ambiguous…Procedural Adversarial Learning
For many computer vision tasks, neural networks can be trained to produce a low average error, yet they still fail on seemingly simple scenes.Occlusion for Free: Detecting Occlusion from the Disagreement Between Two Monocular Distance Cues
Knowing that a pedestrian is occluded is useful to a robot even when the detector cannot recover the hidden pixels, but occlusion estimators are normally trained on occlusion annotations that…Motion-guided Contrastive Regularization For Latent World Models
JEPA-style world models learn action-conditioned latent dynamics without reconstructing observations, but distributional regularization alone does not ensure that their representations preserve…Perceptive Humanoid Motion from Simulation
Humanoid robots have the potential to automate a wide range of physical tasks.From Pixels to Actions - Towards Native Vision-Language-Action Policies
Vision-language-action models are typically built on a simple premise: perception is first compressed by visual encoders, and action reasoning begins only afterwards.T$^2$-Splat: Adaptive Topology Mesh Splatting with Texture Residuals
Triangle-based splatting connects novel view synthesis with conventional graphics pipelines, but often requires excessive tessellation to preserve appearance details.Batch-Conditioned Semantic Anchors for Robust Transductive Adaptation of Vision--Language Models
Transductive adaptation improves vision-language models at test time by refining predictions on an unlabeled batch, but current methods face a key trade-off.TraCE: Trajectory-Aware Concepts for Explainable Video Understanding
Video understanding models often rely on motion, yet their explanations can obscure which motion sources support a prediction.Gaussians Can Subtract: Neural Dissolve Fields for Hybrid Scene Rendering
Hybrid Mesh-Gaussian rendering combines compact textured surfaces with flexible 3D Gaussian primitives, offering an efficient alternative to purely Gaussian scene representations for structured…Expanding the Quality-Coverage Frontier with Competitive Flow Matching
Flow matching (FM) generators often face a quality-coverage tradeoff.Segment What It Can Draw: Querying a Text-to-Image Generator with Its Own Images for Skin Lesion Segmentation
Skin lesion segmentation without annotated masks requires the target to be specified through other cues.