AI.info

Latest Research — Page 67

Browse Latest Research on AI.info.

• Align When They Want, Complement When They Need! Human-Centered Ensembles for Adaptive Human-AI Collaboration
• SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding
• Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers
• The Environmental Impacts of Language Model Training Keep Rising Now is the Time to Catch Impacts on the Rebound
• BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using Agents
• 3D-Agent:Tri-Modal Multi-Agent Collaboration for Scalable 3D Object Annotation
• Reconstructing 12-Lead ECG from 3-Lead ECG using Variational Autoencoder to Improve Cardiac Disease Detection of Wearable ECG Devices
• Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding
• You Need Reasoning to Learn Reasoning: The Limitations of Label-Free RL in Weak Base Models
• LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations
• Towards Neuro-Symbolic Procedural Reasoning for Long-Horizon Vision-Language-Action Manipulation
• HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone
• Do We Need Perfect Data? Leveraging Noise for Domain Generalized Segmentation
• Lightning Grasp: High Performance Procedural Grasp Synthesis with Contact Fields
• Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More
• DARA: Few-shot Budget Allocation in Online Advertising via In-Context Decision Making with RL-Finetuned LLMs
• You Need Better Attention Priors
• Integration of the TIAGo Robot into Isaac Sim with Mecanum Drive Modeling and Learned S-Curve Velocity Profiles
• PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching
• Confounding Factors in Relating Model Performance to Morphology
• 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos
• Variance-Reduced Model Predictive Path Integral via Quadratic Model Approximation
• ARES: Anomaly Recognition Model For Edge Streams
• Hyperbolic Hierarchical Alignment Reasoning Network for Text-3D Retrieval
• G2L:From Giga-Scale to Cancer-Specific Large-Scale Pathology Foundation Models via Knowledge Distillation
• Omnidirectional Solid-State mmWave Radar Perception for UAV Power Line Collision Avoidance
• EvTexture++: Event-Driven Texture Enhancement for Video Super-Resolution
• EDC: Equation Discovery for Classification
• SMRC: Aligning Large Language Models with Student Reasoning for Mathematical Error Correction
• It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks
• From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations
• Metric-Fair Prompting: Treating Similar Samples Similarly
• Towards a Foundation Model for Partial Differential Equations Across Physics Domains
• Field Converter: Geometry-Initialized Temporal Residual Refinement for World-Grounded Player Pose Estimation from Soccer Broadcasts
• HN-MVTS: HyperNetwork-based Multivariate Time Series Forecasting
• Explicit Temporal-Semantic Modeling for Dense Video Captioning via Context-Aware Cross-Modal Interaction
• 3EED: Ground Everything Everywhere in 3D
• Afterlife Delegation Protocol: Speculative Design of Self-Sovereign Agents that Outlive Their Principals
• GAVEL: Towards Rule-Based Safety Through Activation Monitoring
• LLMs for Medical Consultation Are Evaluated Too Late: The Preformulation Gap