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 228
SCALE: Synthetic Calibration via Agreement Labeling in Embedding Space
Foundation models for computational pathology are usually evaluated using AUC and accuracy, while calibration is often left untested.Hard-Region Supervision: #1 on the Waymo Open Dataset 2D Video Panoptic Segmentation Leaderboard
We describe our winning entry to the Waymo Open Dataset 2D Video Panoptic Segmentation Challenge.SpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision--Language Models
Large Vision-Language Models (LVLMs) have made remarkable progress across visual perception tasks, yet spatial reasoning remains a persistent weakness, especially for questions that require…Soft Spatial Reasoning
Large Vision-Language Models (LVLMs) commonly perform spatial reasoning through chain-of-thought (CoT), encoding intermediate reasoning as autoregressive sequences of discrete language tokens.UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
Modern multimodal models bring generation and understanding into a single unified system, which enables them to provide and learn from their own feedback.Matisse: Evidence-Space Reasoning for Active 3D Reconstruction
How can a 3D reconstruction system acquire and retain useful information to understand the geometry of a scene from partial views under a limited computation budget?Consensus-Aware Multi-Source Fusion for Reference-Guided Camouflaged Object Detection
Reference-guided camouflaged object detection aims to segment a target whose visual appearance closely resembles its surroundings by exploiting auxiliary reference samples.Here the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation
Recent joint video-audio generation models have achieved strong semantic correspondence and temporal synchronization.Agentic Relative Camera Pose Estimation via Learned Ranking and Verification
A wide range of approaches have been developed for camera pose estimation, including correspondence-based methods, end-to-end pose regression, and recent 3D geometric foundation models.Event-Driven Refresh and Recurrence Memory to Reduce Stale Grounding in Referring Video Object Segmentation
Referring Video Object Segmentation (RVOS) aims to produce a pixel-accurate mask sequence for an object specified by natural language.Distill the Visual Evidence, Not Just the Answer: Cross-World On-Policy Distillation for Vision-Language Models
A central goal of vision-language model (VLM) distillation is to transfer both the teacher's language capabilities and its visual understanding.Recovering Off-Policy Supervision for Speculative Decoding
Block drafters for speculative decoding are commonly trained on corpora written by external models, where a single off-policy token invalidates supervision for all subsequent slots in a block.CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models
As vision language models are increasingly deployed in clinical diagnosis, under standing how they internally resolve competing visual and textual signals becomes a safety imperative.DCM-SAM: Defect-Conditioned Mixture of LoRA Experts for NPU-Deployed AM Defect Segmentation
Metal additive manufacturing parts are inspected by X-ray computed tomography, where labelled data is scarce, the pores and inclusions that matter span a few pixels, and inspection must happen at…Future Video Generation Better Aligns with the Human Visual Cortex than Observed Video
Studying the alignment between the internal representations of vision models and the responses of the visual cortex to the same observed visual stimuli has enabled us to better understand human…DecoMoE: Decoupling Visual Propagation and Expert Computation for Efficient Multimodal MoE Inference
Multimodal mixture-of-experts (MoE) models combine sparse expert activation with visual-language capabilities, yet their inference remains costly because long visual-token sequences repeatedly incur…FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation
Long-horizon video generation requires models to effectively leverage an increasingly long generation history.Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure Diagnosis
End-to-end accuracy on compositional tasks records how often MLLMs fail, but cannot distinguish whether a failure reflects an intrinsic deficit in the targeted capability or a cascading error from…Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation
The equirectangular projection (ERP) is widely used for panoramic depth estimation, but its spatially varying distortion makes geometry-consistent feature modeling challenging.AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Tasks
Embodied tasks demand accurate, flexible, and semantically rich 3D scene representations.