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 139
RIGen: Beyond Action Following with Reciprocal Interaction in Generative Gameplay
Generative gameplay requires more than immediate responses to player actions.Actions should have persistent consequences, while the generated world should act according to its own state and rules…Intern Lumina U2: A Multi-Codebook Diffusion Large Language Model for Omni-Visual Understanding and Image Generation
Unified multimodal generation covers discrete, continuous, and hybrid paradigms.Temporal Specification Guidance for Text-to-Video Generation
Text-to-video models often generate the visual concepts requested in natural language prompts but fail to satisfy their intended ordering, timing, and persistence requirements.MARS - A foundational map auto-regressor
Map generation tasks feature extensive non-structural vectorized data (e.g., points, polylines, and polygons) and thus pose significant challenges to common pixel-wise generative models.Probing Negation Understanding in Vision-Language Models With Object Attention
Negation is a fundamental aspect of language understanding and it is important vision-language models (VLMs) are able to process it effectively.DefoliationCAM: An Edge-AI System for Real-Time Insect Defoliation Severity Assessment in Grapevines
Insect-induced defoliation threatens grapevine health and yield, yet severity assessment relies on subjective manual scouting.Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation
While foundation models and vision transformers (ViTs) have redefined visual representations, current active learning (AL) strategies for these backbones largely operate at the patch or region…EgoJEPA: Beyond Retargeting for Dexterous Manipulation from Egocentric Videos
Egocentric human videos offer a scalable alternative to costly robot demonstra- tions, yet transferring their manipulation priors to robot control remains chal- lenging.Decision-FLIP: Budget-Free Structured Pruning for Gaussian Occupancy Models
Occupancy predictors rely on large persistent banks of Gaussians or learned queries whose size is fixed by hand.Line-Augmented cuVSLAM: Robust Visual Odometry in Low-Texture Environments
Autonomous mobile robots in warehouses and production facilities operate in precisely the environments that defeat point-feature visual odometry: featureless aisles, uniform walls, repetitive…VELD-QA: A Large-Scale Dataset for Visual Evidence Grounding and Question Answering in Long Documents
Existing long-document QA benchmarks rarely combine large-scale human-authored questions with detailed visual evidence annotations, limiting diagnosis of evidence localization and interpretation…MSP: Modality Self-Play for Training Multimodal LLMs Without Paired Cross-Modal Data
Large multimodal models have achieved remarkable progress by scaling model capacity and training on massive paired multimodal data.PiCo: Physics-Informed Concept Probing for Geo-Foundation Models
Geo-foundation models (GFMs) are typically evaluated by downstream task predictive performance, revealing little about which physical features they are sensitive to or use in prediction.Do As I Do, Not As I Say: On-Policy Distillation Inherits the Teacher in Vision-Language Models
Improving the reasoning capabilities of vision-language models (VLMs) often relies on post-training with supervision from stronger models.DeSpatial: The devil of Agentic Spatial Reasoning Lies in 3D Itself
Spatial agents have access to reconstruction and segmentation tools, yet inconsistent predictions and fragmented object identities can prevent their outputs from becoming reliable 3D scene…EigDiff: Eigensample Diffusion - or how to significantly reduce training dataset size with marginal performance variation?
Diffusion models are notoriously expensive to train, requiring large-scale datasets to learn how to gradually reverse the noise from images over multiple small denoising steps.Mind the Tail: Data Selection Through Sparse Concepts
Data selection reallocates training support across visual concepts, including objects, attributes, color, texture, and backgrounds.Audio-Visual Dog Identification and Tracking in Real-World Videos
Identifying individual dogs from barks in real-world videos remains challenging and largely unexplored.ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation
Long-horizon GUI agents rely on visual history to maintain task states, but retaining historical screenshots increases visual-token usage and inference costs, while textual summaries can discard…ESC: Escaping 2D Diffusion Ambiguity with Geometric Constraints for Consistent Novel View Synthesis
Generating 3D-consistent novel views from 2D diffusion models remains a fundamental challenge in computer vision.