AI.info

Latest Research — Page 92

Browse Latest Research on AI.info.

• RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation
• LiteraryTaste: A Preference Dataset for Creative Writing Personalization
• StructRL: Online Structured Reinforcement Learning for Long-Horizon Vision-Language-Action Tasks
• Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers
• Policy4OOD: A Knowledge-Guided World Model for Policy Intervention Simulation against the Opioid Overdose Crisis
• Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"
• 3D Blood Pulsation Maps
• Concept Heterogeneity-aware Representation Steering
• What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents?
• On the Problem of Consistent Anomalies in Zero-Shot Industrial Anomaly Detection
• IPR-1: Interactive Physical Reasoner
• Quantum Model Parallelism for MRI-Based Classification of Alzheimer's Disease Stages
• Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA
• EarlySelectKV: Anticipatory KV Selection via Cross-Layer Query Proxies
• Knowledge Completes the Vision: A Multimodal Entity-aware Retrieval-Augmented Generation Framework for News Image Captioning
• Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method
• Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs
• Adaptive Latent Capacity for World Models
• Single-Round Scalable Analytic Federated Learning
• Don't Lose the Thread: Empowering Long-Horizon LLM Agents with Cognitive Resource Self-Allocation
• CompassNav: Steering From Path Imitation To Decision Understanding In Navigation
• CurConMix+: A Unified Spatio-Temporal Framework for Hierarchical Surgical Workflow Understanding
• A Solver-in-the-Loop Framework for Improving LLMs on Answer Set Programming for Logic Puzzle Solving
• TextME: Bridging Unseen Modalities Through Text Descriptions
• HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents
• VibeEdit: Image Editing with Canvas Instructions
• Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective
• MPQ: A Message-Passing View of Post-Training Quantization
• Velox: Spatial Memory Makes World Models Efficient
• PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents
• VidDub: Replacement-Aware Distillation for Two-Step Video Dubbing
• Knowing When to Answer: Adaptive Confidence Refinement for Reliable Audio-Visual Question Answering
• The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
• Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work
• UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City
• DynaStride: Dynamic Stride Windowing with MMCoT for Instructional Multi-Scene Captioning
• Selecting or Solving? What Best-of-N Verification Delivers in Video Reasoning
• Rufus-Air: An Open LLM Post-Training Recipe
• EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL
• Multiclass Classification with Rare Useful Features: Fundamental Limits and the Optimality of Diversity Pursuit Higher Criticism Thresholding