AI.info

Latest Research — Page 3

Browse Latest Research on AI.info.

• Auto-Regressive Masked Diffusion Models
• MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation
• Seg-VAR: Image Segmentation with Visual Autoregressive Modeling
• Mind-to-Face: Neural-Driven Photorealistic Avatar Synthesis via EEG Decoding
• QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation
• Adaptive Confidence Regularization for Multimodal Failure Detection
• Understanding the Effects of Distractors on Reasoning Vision-Language Models
• Know your Trajectory -- Trustworthy Reinforcement Learning deployment through Importance-Based Trajectory Analysis
• The False Promise of Zero-Shot Super-Resolution in Machine-Learned Operators
• Look and Tell: A Dataset for Multimodal Grounding Across Egocentric and Exocentric Views
• Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models
• GraspLDP: Towards Generalizable Grasping Policy via Latent Diffusion
• Enhancing Generalization of Depth Estimation Foundation Model via Weakly-Supervised Adaptation with Regularization
• Multimodal Bandits: Regret Lower Bounds and Optimal Algorithms
• CompanionHarm: A Multi-Turn Benchmark for Detecting Harms in Real-World AI Companion Conversations
• CoFEH: LLM-driven Feature Engineering Empowered by Collaborative Bayesian Hyperparameter Optimization
• DeepAnalyze: Agentic Large Language Models for Autonomous Data Science
• Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following
• Enrich and Detect: Video Temporal Grounding with Multimodal LLMs
• Anatomy Contextualized Adaption of CT Foundation Models
• Coarse-Grained Boltzmann Generators
• WED-Net: A Weather-Effect Disentanglement Network with Causal Augmentation for Urban Flow Prediction
• Integrating Multi-view Multi-light Surface Reconstruction into Cultural Heritage Workflows
• Zero-RAG: Towards Retrieval-Augmented Generation with Zero Redundant Knowledge
• Can Local Learning Match Self-Supervised Backpropagation?
• SPDMark: Selective Parameter Displacement for Robust Video Watermarking
• Bootstrap Dynamic-Aware 3D Visual Representation for Scalable Robot Learning
• TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards
• AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidance
• Saudi Sign Language Translation Using T5
• LLMs for Game Theory: Entropy-Guided In-Context Learning and Adaptive CoT Reasoning
• InterMoE: Individual-Specific 3D Human Interaction Generation via Dynamic Temporal-Selective MoE
• When One Modality Rules Them All: Backdoor Modality Collapse in Multimodal Diffusion Models
• Rethinking Language's Role in Efficient VLA for Autonomous Vehicles: Toward Smarter, Trustworthy Driving
• LogicSkills: A Structured Benchmark for Formal Reasoning in Large Language Models
• Metis-SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
• Overview of CHIP 2025 Shared Task 2: Discharge Medication Recommendation for Metabolic Diseases Based on Chinese Electronic Health Records
• Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning
• Nonlinear Model Predictive Control of a Robotic Soft Esophagus
• MetaCaDI: A Meta-Learning Framework for Causal Discovery from Multiple Environments with Unknown Interventions