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 126
Can Visual Generation Expand What Unified Multimodal Models Know?
Unified multimodal models (UMMs) receive image-generation supervision that exposes them to visual information not fully documented in text.Cross-Prompt Inference Mitigates Rare-Class Suppression in Imbalanced VLM Finetuning
When a vision-language model is finetuned on class-imbalanced data, rare-class recall can fall well below the model's own zero-shot performance.AI-Driven Disaster Response and Displacement Monitoring
ARTIFICIAL INTELLIGENCE (AI) has demonstrated its potential across a wide range of humanitarian tasks, offering scalable and data-driven solutions to some of the world's most pressing challenges.GRASE: Geometry-native Real-to-sim Agentic Scene Modeling from Video
Real-to-sim conversion aims to turn a captured video of a real environment into an editable 3D scene while preserving the geometry and layout of what was observed.FilterFusion: Prior-Guided Adaptive Filter Fusion for Efficient Video Denoising
Real-world video denoising for communication systems must handle mixed degradations such as sensor noise, compression artifacts, and motion-induced inconsistency while remaining deployable under…Rethinking Classifier-Free Guidance for TI2I Flow Matching
We study Text-and-Image-to-Image (TI2I) flow matching methods for controllable image editing.Decoupled Safety Control: A Safety-Control Algorithm for Training-Free Safety Guidance
Diffusion models achieve strong performance in text-to-image generation, but they can still produce unsafe content.MYOPIA: Understanding the Limits of Tree-Based Reasoning in Vision-Language Models
Decision trees can make vision-language model (VLM) classification interpretable by replacing a single prediction with a sequence of root-to-leaf questions.Hear, Localize, and Reason: Spatially Aware Scene Understanding for Audio-Visual LLMs
Audio-visual large language models (AV-LLMs) have made strong progress in multimodal understanding, yet most treat audio as monaural semantic content, limiting their ability to reason about where…A Decision-Aware Evaluation Protocol for Uncertainty in Medical Image Segmentation
Medical segmentation uncertainty is often evaluated with calibration error or pixel-level error-detection scores, but these metrics do not show whether uncertainty improves downstream review…Training-Free Target-Aware Refinement of 3D Gaussian Language Map
Distilling vision-language features into 3D Gaussian Splatting yields a language map that can be queried with arbitrary text.Anchor3DGS: Feed-Forward 3D Gaussian Splatting with Compact Anchor-Based Representation
Recent feed-forward 3D Gaussian Splatting (3DGS) methods have enabled effective multi-view 3D reconstruction by predicting Gaussian primitives in a single forward pass.Spurious Attention Heads in Vision Transformers: Mechanistic Identification of Annotation-Driven Bias in Medical Chest X-Ray Analysis
Vision Transformers deployed in medical imaging exploit spurious correlations, yet the internal mechanisms remain unidentified and impossible to fix.DIAL: Dynamic and Informed Adjustment of the Native Stochastic Law for Reliable Weather Ensembles
Ensemble weather forecasts can look reliable in global averages while hiding too little spread in some cases and too much in others.SCMerge: Spatial-Consistency-Aware Token Pair Merging for Efficient Semantic Segmentation
Vision Transformer architectures have showcased impressive performance on semantic segmentation, yet their quadratic attention complexity hinders practical applications.Digital Typhoon Dataset V3: Benchmarking for Multi-spectral Extension and Analyzing Systematic Bias in Intensity Regression
This paper presents the Digital Typhoon Dataset V3, a new version of the longest typhoon satellite image dataset spanning nearly 50 years, designed to benchmark machine learning models on long-term…FusionAudit: Pathway-Conditioned Robustness Auditing for Native Multimodal Models
As vision-language models (VLMs) transition from frozen-encoder pipelines to native multimodal architectures, the visual channel increasingly serves as both a perceptual input and a carrier of…Edit4D: Editable 4D Scene Generation with Textual Control
We introduce Edit4D, an editable text-to-4D scene generation framework that constructs 4D scenes from separate background and dynamic character representations.Bridging the Markerless Tracking Validation Gap: Intraoperative X-ray Workflow Integration
Markerless intraoperative tracking of spinal anatomy via RGB-D sensors is a promising alternative to invasive bone-anchored fiducials, yet no existing clinical dataset provides independent…Mixture of Multi-Sequence Feature Difference for Contrast-Enhanced MRI Synthesis
Contrast-enhanced magnetic resonance imaging (CE-MRI) is crucial for accurately diagnosing and segmenting brain tumors.