AI.info

Latest Research — Page 66

Browse Latest Research on AI.info.

• Quo Vadis? Scientific Discovery in the Age of Artificial Intelligence
• Learning to Solve PDEs on Neural Shape Representations
• Linear time small coresets for k-mean clustering of segments with applications
• Lightweight Optimal-Transport Harmonization on Edge Devices
• InfiniteDiffusion: Bridging Learned Fidelity and Procedural Utility for Open-World Terrain Generation
• Learning Sparse Visual Representations via Spatial-Semantic Factorization
• Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents
• From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models
• ScenicRules: An Autonomous Driving Benchmark with Multi-Objective Specifications and Abstract Scenarios
• If You Want to Be Robust, Be Wary of Initialization
• DeepSight: An All-in-One LM Safety Toolkit
• On Your Own: Pro-level Autonomous Drone Racing in Uninstrumented Arenas
• Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression
• Labels Matter More Than Models: Rethinking the Unsupervised Paradigm in Time Series Anomaly Detection
• Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks?
• GazeFormer-MoE: Context-Aware Gaze Estimation via CLIP and MoE Transformer
• Parallel Complex Diffusion for Scalable Time Series Generation
• SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL
• It is not always greener on the other side: Greenery perception across demographics and personalities in multiple cities
• LumiX: Structured and Coherent Text-to-Intrinsic Generation
• Real PMIDs, Wrong Papers: Harness Design for Biomedical Claim-Verification Agents
• Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch
• EvalBlocks: A Modular Pipeline for Rapidly Evaluating Foundation Models in Medical Imaging
• Evaluating the Applicability of LLM Inference Optimizations on Apple Silicon
• StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors
• A Privileged Teacher That Only Scores Cannot Search: Critique-Conditioned On-Policy Self-Distillation for Reasoning
• Local Guidance for Configuration-Based Multi-Agent Pathfinding
• Segment, Embed, and Align: A Universal Recipe for Aligning Subtitles to Signing
• VEDJE: Video-Efficient Discriminative Joint Encoder for Scalable Video-Text Retrieval
• Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Data
• LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces
• AnyTouch 2: General Optical Tactile Representation Learning For Dynamic Tactile Perception
• LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception
• FCMBench: The First Large-scale Financial Credit Multimodal Benchmark for Real-world Applications
• Learning the Boundary of Solvability: Aligning LLMs to Detect Unsolvable Problems
• A Fully Interpretable Statistical Approach for Roadside LiDAR Background Subtraction
• Toward Reliable Sim-to-Real Predictability for MoE-based Robust Quadrupedal Locomotion
• Can Coding Agents Sustain Continual Evolution without Forgetting?
• KINDER: Kernel-based Independence for Fair Representation Learning via Prototype-space Erasure
• Why Deterministic PRM Guidance Underperforms in Discrete Diffusion Reasoning