Latest Research in Information Retrieval
104 research papers · 2026 median publication year
Top Research Topics in Information Retrieval
- Computer Vision and Pattern Recognition — 44 papers
- Artificial Intelligence — 22 papers
- Machine Learning — 16 papers
- Computation and Language — 16 papers
- Information Retrieval — 3 papers
- Information Theory — 1 papers
- Multimodal Machine Learning Applications — 1 papers
- Machine Learning and Data Classification — 1 papers
Highest-Cited Papers
- Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
- Region-Level Policy Optimization for Fine-grained MLLM Perception
- Absence is Presence: Understanding Visual Scene Negative Events Under Safety Cognitive Constraint
- RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
- What Counts as Strategic Reasoning? A Systematic Mapping of Chess Research on Humans, Engines, and Language Models
- RLLBC-Lib: An Educational Code Library for Reinforcement Learning and Learning-Based Control
- Towards Faithful and Efficient Semantic Communication: An Ontological Approach
- Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning
- Stress Tests REVEAL Fragile Temporal and Visual Grounding in Video-Language Models
- BRACE: Anchored Bellman-Residual Correction for Stale Critics in Asynchronous RL
- AMALIA-VL: A Native European Portuguese Open-Source Vision and Language Model
- BrainFocus: EEG-Guided ROI Selection for Efficient Vision-Language Models
- Learning Heterogeneous Preferences
- Uncertainty-Aware Multimodal AI: Detecting Ambiguity Instead of Guessing in Vision-Language Systems
- Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization
- Tackling GNARLy Problems: Graph Neural Algorithmic Reasoning Reimagined through Reinforcement Learning
- TwinICL: Diagnosing Multimodal In-Context Learning through Paired Counterfactuals
- Human-Grounded Calibration for Long-Text Image-Text Congruence in Vision-Language Models
- CapGeo-Bench: Decoupling Visual Perception from Reasoning and Evaluating Geometric Understanding
- Towards Scalable RLVR: Multimodal Instruction Following Data Synthesis and Distillation