Structured Prediction

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 21

All topics

Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision
Sep 28, 2026Hanoona Rasheed, Mohammed Irfan Kurpath, Bin Ren +3Vision Foundation Models Large Vision-Language Models
Mohamed bin Zayed University of Artificial Intelligence · Apertix
Provable Guarantees for Spectral Structured Prediction
Sep 16, 2026Violet Zheng, Jean HonorioSpectral Methods Node Classification
CIS, The University of Melbourne
Topology-Aware Query Selection for Surgical Instrument Instance Segmentation
Aug 12, 2026Ze Zhang, Yang ZhangInstance Segmentation Structured Prediction
Department of Biomedical Engineering, ShanghaiTech University, Shanghai, China · Wuhan United Imaging Surgical Co., Ltd., Wuhan, China
StepReflect: Structured UI Transition Reflection for Mobile GUI Agents
Aug 6, 2026Linqiang Guo, Wei Liu, Li Gu +3Mobile GUI Automation GUI Agents
Peter · Concordia University Montreal, Quebec, Canada
Better, Stronger, Faster, and Broader: Structured All-Mask Prediction for MLLM-Based Segmentation
Aug 3, 2026Jiazhen Liu, Mingkuan Feng, Long ChenEfficient Multimodal Inference Image Segmentation
The Hong Kong University of Science and Technology (HKUST), Hong Kong.
PrISM-IQA: Image Quality Assessment Made Practical for Smartphone Photography
Jun 30, 2026Shuyan Zhai, Jiaqi He, Weixia Zhang +4Ordinal Regression Image Quality Assessment
Department of Computer Science, City University of Hong Kong · School of Computer Science, Institute of AI, Shanghai Jiao Tong University · OPPO Research Institute +1
Rethinking Foundation Model Collaboration: Enhancing Specialized Models through Proxy Task Reasoning
Jun 30, 2026Hongyi Lin, Yang Liu, Jinhua Zhao +1VLM Reasoning Multimodal Foundation Models
School of Vehicle and Mobility, Tsinghua University, Beijing, China · Department of Urban Studies and Planning, Massachusetts Institute of Technology, Cambridge, MA, USA
Modular Diffusion Models for Structured Visual Recognition
Jun 21, 2026Siddhesh Khandelwal, Björn Ommer, Leonid SigalScene Graph Generation Uncertainty Quantification
Department of Compute Science, University of British Columbia · Vector Institute for AI · CompVis, Ludwig Maximilian University of Munich +2
Protein contacts are already in the attention: a single-forward-pass alternative to the Categorical Jacobian
Jun 20, 2026Rome ThorstensonProtein Structure Prediction Attention Head Analysis
Independent Researcher
S23DR 2026: End-to-End 3D Wireframe Prediction via DETR-Style Set Prediction with Contrastive Denoising
Jun 12, 2026Nitiz Khanal3D Reconstruction Point Cloud Learning
Pulchowk Campus, Lalitpur, Nepal
S23DR 2026 Winning Solution
Jun 4, 2026Jan Skvrna, Miroslav Purkrabek, Lukas Neumann3D Reconstruction Set Prediction
Visual Recognition Group, Czech Technical University in Prague
InstructSAM: Segment Any Instance with Any Instructions
May 25, 2026Yuqian Yuan, Wentong Li, Zhaocheng Li +6Image Segmentation Text-Guided Image Segmentation
Zhejiang University · Nanjing University of Aeronautics and Astronautics
DANCE: Detect and Classify Events in EEG
May 11, 2026Jarod Lévy, Hubert Banville, Jérémy Rapin +3Electroencephalography Brain-Computer Interfaces
1Meta AI · 2Inria, Université Paris-Saclay, Palaiseau, France
Set Prediction for Next-Day Active Fire Forecasting
May 11, 2026Yuchen Bai, Georgios Athanasiou, Xin Yu +4Wildfire Forecasting Set Prediction
Max Planck Institute for Biogeochemistry, Jena, Germany · Orion Lab, National Technical University of Athens · University of Utah, Salt Lake City, USA +4
Contextual Plackett-Luce: An Efficient Neural Model for Probabilistic Sequence Selection under Ambiguity
May 9, 2026Noam Mizrachi, Nadav Har-Tuv, Shai Shalev-ShwartzDiscrete Choice Modeling Structured Prediction
Mobileye
XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction
May 7, 2026Hanyu Gao, Bin Cao, Yunyue Su +2Set Prediction Materials Science
New Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA) · School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · Guangzhou Municipal Key Laboratory of Materials Informatics, The Hong Kong University of Science and Technology (Guangzhou) +1
Coherent Hierarchical Multi-Label Learning to Defer for Medical Imaging
May 4, 2026Joshua Strong, Pramit Saha, Emma Sun +2Hierarchical Classification Multi-Label Classification
Department of Engineering Science, University of Oxford, UK · Nuffield Division of Anaesthetics, University of Oxford, The John Radcliffe Hospital, UK
Revisiting Semantic Role Labeling: Efficient Structured Inference with Dependency-Informed Analysis
May 4, 2026Sangpil Youm, Leah Jones, Bonnie J. DorrStructured Prediction
University of Florida, Gainesville, Florida
Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction
Apr 30, 2026Mehryar Mohri, Yutao ZhongClassification Structured Prediction
Google Research, New York, NY · Courant Institute of Mathematical Sciences, New York, NY
An event-based sequence modeling approach to recognizing non-triad chords with oversegmentation minimization
Apr 27, 2026Leekyung Kim, Jonghun ParkMusic Information Retrieval Sequence Modeling
Department of Industrial Engineering and Institute of Industrial Systems Innovation, Seoul National University, Seoul, Republic of Korea
Topology-Aware Skeleton Detection via Lighthouse-Guided Structured Inference
Apr 22, 2026Daoyong Fu, Xiang Zhang, Zhaohuan Zhan +2Structured Prediction
Nanjing University of Information Science and Technology · Shenzhen MSU-BIT University · Sichuan University +1

Sep 28, 2026, cs.CVJ/K move · Enter open · S save

Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision

Hanoona Rasheed, Mohammed Irfan Kurpath, Bin Ren, Hisham Cholakkal+2

Mohamed bin Zayed University of Artificial Intelligence · Apertix

Vision Foundation Models Large Vision-Language Models Visually Grounded Reasoning Fine-Grained Visual Perception Structured Prediction

Open paper AskPDF arXiv

Frontier general-purpose systems are rapidly expanding beyond visual understanding into capabilities traditionally handled by dedicated computer-vision models. As these capabilities expand, a central question for the computer-vision community is how far this reach extends, and what remains hard. We evaluate GPT-6 Astra alongside five frontier general-purpose AI systems across 34 capabilities and 55 benchmarks spanning nine areas of computer vision. We compare their performance with dedicated models and humans where suitable references are available. Astra demonstrates broad visual capability, with substantial gains over other frontier systems in visual and spatial reasoning and several forms of structured prediction. Across the state-of-the-art systems, a consistent pattern emerges. Capabilities involving semantic interpretation, reasoning, and object-centric prediction increasingly approach or reach available reference levels. In contrast, larger gaps remain when tasks require metric geometric accuracy, faithful reconstruction, temporally consistent dense prediction, or specialized fine-grained visual knowledge. Additional reasoning and specialist tools close selected gaps, but their benefits vary across capabilities. These results map a changing landscape of computer vision in which increasingly sophisticated visual tasks are accessible through a general-purpose interface, while precise and fidelity-sensitive perception remains an important frontier.

Momentum

Related topics

Latest papers 21