Overview

Structured prediction studies how to make interdependent decisions, such as labeling a sentence, assembling an object set, extracting a diagram’s topology, or assigning coherent labels in a medical hierarchy. Common approaches include structured losses and decoding, set prediction with matching, autoregressive selection, and models that encode constraints or topology. The field spans language, vision, scientific measurement, and time-series tasks, with evaluations often testing both task accuracy and properties such as consistency, connectivity, and robustness to ambiguity. A central tension is how to capture dependencies among outputs while keeping inference efficient and ensuring predictions remain reliable under distribution shifts and difficult subgroups.

Latest papers

CardsList

35 papers4 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.

  1. STaR-DRO: Stateful Tsallis Reweighting for Group-Robust Structured Prediction

    Apr 9, 2026Samah Fodeh, Ganesh Puthiaraju, Elyas Irankhah +5Structured PredictionDistributionally Robust Optimization

  2. AgentGate: A Lightweight Structured Routing Engine for the Internet of Agents

    Apr 8, 2026Yujun Cheng, Enfang Cui, Hao Qin +2LLM Agent RoutingStructured Prediction

  3. Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing

    Apr 3, 2026Fuyuan Liu, Dianyu Yu, He Ren +10Document ParsingDocument Layout Analysis

  4. Emotion Entanglement and Bayesian Inference for Multi-Dimensional Emotion Understanding

    Apr 1, 2026Hemanth Kotaprolu, Kishan Maharaj, Raey Zhao +2Emotion RecognitionAffective Computing

  5. Learning Constituent Headedness

    Mar 16, 2026Zeyao Qi, Yige Chen, KyungTae Lim +2Constituency ParsingStructured Prediction