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 217
MoSE3: Learning World-Space SE(3) at Every Pixel
Dense 3D point tracking has been a prominent paradigm for modeling motion in dynamic scenes, but a point track is just a 3-DoF translation curve per pixel: it captures where pixels go, not the…Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis
This paper examines the role of Novel View Synthesis (NVS) in geometric representation learning.Beyond Token Accuracy: Prioritizing What Matters for Visual Reconstruction
Tokens have become a unified interface for multimodal foundation models, making visual-token communication a natural paradigm for efficient image delivery.Are We Measuring Anticipation? Auditing Privileged Information in Procedural Video Evaluation
Benchmark scores license claims about the capabilities being evaluated.GOTT: Object-centric Dexterous Manipulation with a Reusable Cross-Embodiment Primitive
Foundation models and large-scale human data provide rich sources of manipulation intent, but translating this intent into multi-fingered robot behavior remains difficult.Streaming Multi-Track Timeline Control for 3D Human Motion Generation
Text-driven human motion generation has advanced substantially, yet most methods assume instructions are available before synthesis.DABACO: A Multi-Camera Dataset and Benchmark for Screen Localization and Pointing Estimation
Screen localization and pointing estimation are key to low-cost interactive devices.Dynamic Time Step Prediction in Inverse Heat Dissipation for Blur-Like Image Restoration Tasks
When using diffusion models to target image restoration problems, diffusion inversion is typically employed to retain relevant image information from the degraded images.FADE: Frame-Aware Diffusion-Transformer-based Multi-Concept Erasure for Video Unlearning
Text-to-video (T2V) diffusion models can reproduce copyrighted, violent, or explicit content, which motivates concept erasure: removing designated concepts from a pretrained model while preserving…Masked Privileged-Information Distillation for Multimodal Skin Lesion Classification Under Missing Clinical Metadata
Multimodal skin lesion classification combines clinical images with patient metadata to improve diagnostic accuracy.Selective Backpropagation for Efficient Few-Shot Class-Incremental Learning
Few-Shot Class-Incremental Learning (FSCIL) requires models to continuously learn new classes from limited samples while retaining prior knowledge, under strict constraints on compute and memory.Verifier-Guided Synthetic Augmentation for 3D Human Shape Generation
Limited training data diversity constrains generative modeling of 3D human bodies: conservative models remain close to observed examples, whereas exploratory models often violate basic body…VolS-GS: Relightable Gaussian Splatting with Volumetric Subsurface Scattering
We present VolS-GS, a relightable Gaussian splatting framework that reconstructs objects from one-light-at-a-time (OLAT) captures and renders them under novel lighting and viewpoints.SUAVE: Unified Video-Action Models via Masked Diffusion
Vision-language-action models (VLAs) inherit strong semantic grounding from pretrained vision-language backbones but are typically optimized for predicting actions rather than future observations.PhysMamba: Selective State Space Models as Learned Articulated Body Simulators
We introduce the first learned articulated body simulator based on a selective state space model (SSM), called PhysMamba.ClasSAE: Class-Aligned Sparse Autoencoders via Differentiable Feature-Class Affinity
Sparse Autoencoders (SAEs) began as an unsupervised tool for decomposing neural representations into sparse, interpretable features, and are increasingly used not only for passive analysis but also…Learning Subject-Specific Anatomical Representations via Manifold Expansion: Application to Accelerated Multi-Contrast MRI
Clinical MRI routinely acquires multiple contrast-weighted images of the same anatomy for complementary tissue characterization.MAGEFormer: Learning Metric-Consistent Representations for Anisotropic CT Segmentation
Vision Transformers (ViTs) have shown strong performance in volumetric segmentation, but their effectiveness on clinical CT is limited by an isotropic Euclidean lattice assumption.Dynamic Quadtree Tokenization and Transformer for Adaptive Mesh PDE Forecasting
The quadratic attention cost of Vision Transformers (ViTs) forces a trade-off between spatial resolution and rollout horizon, particularly for fine-scale PDEs where shocks, reaction fronts, and…ASD-FEAT: A Multi-Modal Infant Video-Derived Dataset for Early ASD Risk Prediction
Accurate early screening for Autism Spectrum Disorder (ASD) is a precursor to timely intervention, which is critical for improving cognitive and behavioral outcomes.