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 133
Vision-Language Models Integrate Conflicting Evidence Like Biased Bayesian Observers
Vision-language models must reconcile conflicting text and images.WinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding
MLLM-based detectors formulate vision-language grounding as autoregressive coordinate generation, yet in dense scenes, they often collapse into a box repetition loop, repeatedly emitting identical…From Failures to Learnable Worlds: Policy-Conditioned Environment Generation for Navigation Agents
Simulated environments enable scalable training data generation for embodied agents, but more data does not necessarily provide what a particular agent needs to learn.VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness
LLM system capabilities depend not only on model parameters but also on the executable harnesses that organize information acquisition, tool use, reasoning, and memory.Learning to Select Features with Manifold Deep Unfolding PCA
Unsupervised feature selection (UFS) is of great significance in image processing and pattern recognition.DeBoneDiT: Depth-Driven Conditional Bridge Diffusion Transformers for Bone Suppression in Chest X-Ray Images
Chest X-Ray (CXR) is a primary modality for diagnosing pulmonary diseases, yet the overlap of bony structures often obscures critical radiographic findings, increasing the risk of diagnostic…ActICL: Post-Training for Agentic Multimodal In-Context Learning
Multimodal in-context learning (ICL) is an important capability of multimodal large language models (MLLMs).Robust Real-Time Monocular Human Pose Estimation with Insole-Based Sensor Fusion
Real-time monocular human pose estimation is an important sensing component for human-centered intelligent systems.Robota-Embed: Unified VLA Embeddings for Robot In-Context Learning and Evolution
Retrieving useful context for a robot requires matching its task, execution stage, and the continuation that should follow.Holi-Spatial 360: Generative Reconstruction from Sparse Panoramas for Spatial Rendering and Intelligence
Spatial intelligence requires scalable 3D environments that are both photorealistic and semantically grounded, yet existing indoor datasets are dominated by room-scale captures and costly LiDAR…Spectral World Renderer: Unified 3D Hyperspectral Unmixing
Cameras and the foundation models built on them recognize what a 3D scene contains, but not what it is made of: surfaces of the same colour can be different materials.HyrCap: Hybrid Rank-Calibration of Action Proposals for Temporal Event Understanding
Temporal action detection in long untrimmed videos suffers from inaccurate localization and low-quality proposals, especially with sparse annotations and ambiguous boundaries.Reducing the Gap Between Spatial and Space-Filling Curve Neighbors in 3D Point Cloud Segmentation
As a lightweight and highly accurate method for nearest-neighbor search in 3D point clouds, approaches based on space-filling curves (SFC) have been proposed.RDCompGS: Rate-Distortion Optimization for Compression of 3D Gaussian Splatting with Image Codecs
3D Gaussian Splatting (3DGS) enables high-quality, real-time novel view synthesis but requires significant storage and transmission resources.Cross-Scenario Industrial Defect Detection via Domain-Robust Training and Metric-Aligned Selection
Automated defect detection of industrial boards must remain highly reliable under cross-scenario variations in lighting, surface contaminants, and production line conditions.TextVerifier: Seeing Beyond Recognition to Verify Chinese Text Rendering
Text-to-image models increasingly generate readable Chinese text that still contains local rendering defects, such as a character with an extra or missing stroke or a malformed component.Learning Visual Speech Representations via Cross-Modal Distillation and Joint Face-Lip Modeling
Lipreading remains challenging due to the inherent ambiguity of visual speech cues and their sensitivity to head pose and video resolution.SaTPO: Text-to-Image Safety Alignment via Transition Preference Optimization
Safety alignment of text-to-image diffusion models aims to suppress harmful content without compromising useful generation capabilities.Frame Evidence:A Benchmark for Reference Frames and Visual Evidence in Multi-Image Spatial Reasoning
A spatial answer depends on the reference frame specified in language and its supporting visual evidence.LED-BENCH: A Benchmark for Large-format Engineering Drawing Understanding
Real-world engineering drawings are often large-format and information-dense.