AI.info

Latest Research — Page 20

Browse Latest Research on AI.info.

• Active Learning for Decision Trees with Provable Guarantees
• MonoCLUE : Object-Aware Clustering Enhances Monocular 3D Object Detection
• CLUIE: Clustering-Aware Recurrent Propagation with Local Structural Compensation for Underwater Image Enhancement
• EvoOntology: A Self-Evolving Ontology Layer for Data Agents
• GraphNet: A Large-Scale Computational Graph Dataset for Tensor Compiler Research
• DGH: Dynamic Gaussian Hair
• Barycentric Guidance: Turning Foundation Image Editors into Continuous Affective Controllers
• Benchmarking Patent Drafting from Inventor-Style Disclosures
• Alif: Advancing Urdu Large Language Models via Multilingual Synthetic Data Distillation
• Neurocircuitry-Inspired Hierarchical Graph Causal Attention Networks for Explainable Depression Identification
• LLM2Cert: LLM Synthesis of Certificates with SMT/Lean Verification
• We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents
• Group Representational Position Encoding
• SpatialBench: Can Agents Analyze Real-World Spatial Biology Data?
• A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness
• LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts
• Exploring the Limits of Combinatorial Generalization in Embodied Manipulation
• Stabilizing Physics-Informed Consistency Models via Structure-Preserving Training
• TileNet: Tile-Based CNN-SVM Architecture for Autonomous Unmanned Aerial Systems Inspection of Flat Roofs
• Certified Access: Test-Time Compute on Conservative Physics-Structured AI Memory
• ParkingTwin: Training-Free Streaming 3D Reconstruction for Parking-Lot Digital Twins
• SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports
• Mitigating Barren Plateaus in Quantum Denoising Diffusion Probabilistic Model
• Zoom in, Click out: Unlocking and Evaluating the Potential of Zooming for GUI Grounding
• MGML: A Plug-and-Play Meta-Guided Multi-Modal Learning Framework for Incomplete Multimodal Brain Tumor Segmentation
• Efficient Swap Regret Minimization in Combinatorial Bandits
• DND: Boosting Large Language Models with Dynamic Nested Depth
• Weak Segmentation-Guided GAN for~Realistic Color Edition
• SynthGait-19K: A Physically Grounded Synthetic Video Dataset for Gait Parameter Estimation
• Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning
• Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding
• Dory1.0-4B: A Looped Normalized-GPT
• Inference-Time Dynamic Modality Selection for Incomplete Multimodal Classification
• Continuous Degradation Modeling via Latent Flow Matching for Real-World Super-Resolution
• Where Does Vision Meet Language? Understanding and Refining Visual Fusion in MLLMs via Contrastive Attention
• Regret-Based Federated Causal Discovery with Unknown Interventions
• When Citations Mislead? A Claim-Level Benchmark for Legal Hallucination Detection
• Spoken Conversational Agents with Large Language Models
• STAvatar: Soft Binding and Temporal Density Control for Monocular 3D Head Avatars Reconstruction
• CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs