AI.info

Latest Research — Page 52

Browse Latest Research on AI.info.

• Do speech foundation models really learn words?
• MovSemCL: Movement-Semantics Contrastive Learning for Trajectory Similarity (Extension)
• Calibrating Generative Models to Distributional Constraints
• SenseNova-U1.5: Towards Native Unified Visual Intelligence
• MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models
• BackTrend: Evaluating Scientific Weak-Signal Prediction via Backward Reconstruction
• Learning Neural Exposure Fields for View Synthesis
• VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning
• GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks
• Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning
• Accountable AI with Grounded, Faithful, Consistent, Actionable Rationales: A Case Study in Clinical Trial Matching with VERDICT
• Rare Diseases, Common Dilemmas: LLMs Prioritize Equal Resource Distribution over Patient Benefit in Decision-Making
• Evidence-Bounded Mental Health Reasoning from Heterogeneous Speech Protocols
• Agile perceptive multi-skill locomotion for quadrupedal robots in the wild
• HypCBC: Domain-Invariant Hyperbolic Cross-Branch Consistency for Generalizable Medical Image Analysis
• ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment
• Edit-aware RAW Reconstruction
• Human-Centric Open-Future Task Discovery: Formulation, Benchmark, and Scalable Tree-Based Search
• CIPHER: Scalable Time Series Analysis for Physical Sciences with Application to Solar Wind Phenomena
• Dr. Zero: Self-Evolving Search Agents without Training Data
• Beyond Hallucinations: A Composite Score for Measuring Reliability in Open-Source Large Language Models
• Chow-Liu Ordering for Long-Context Reasoning in Chain-of-Agents
• Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning
• Active Learning with Selective Time-Step Acquisition for PDEs
• Distributionally Robust Cooperative Multi-Agent Reinforcement Learning via Robust Value Factorization
• Plug-and-Play Traffic Element Awareness for End-to-End Autonomous Driving
• Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training
• GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR
• SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning
• PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments
• AEMA: Verifiable Evaluation Framework for Trustworthy and Controlled Agentic LLM Systems
• From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection
• DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization
• Training Diffusion Policies via Prior-Mapping Co-Evolution
• A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents
• Web-Scale Collection of Video Data for 4D Animal Reconstruction
• Massively Parallel Imitation Learning of Mouse Forelimb Musculoskeletal Reaching Dynamics
• DISCO: Diversifying Sample Condensation for Efficient Model Evaluation
• PanFlow: Decoupled Motion Control for Panoramic Video Generation
• Accelerating Benchmarking of Functional Connectivity Modeling via Structure-aware Core-set Selection