AI.info

Latest Research — Page 43

Browse Latest Research on AI.info.

• Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models
• Anonpsy: A Graph-Based Framework for Structure-Preserving De-identification of Psychiatric Narratives
• Think-Verify-Revise: Neuro-Symbolic Visual Reasoning with Vision-Language Models and Dynamic Logic Tensor Networks
• Reinforced sequential Monte Carlo for amortised sampling
• Diversifying Counterattacks: Orthogonal Exploration for Robust CLIP Inference
• Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Models
• Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models
• UCPO: Uncertainty-Aware Policy Optimization
• Unified Video Dense Prediction from Disjoint Data
• Foveation Improves Payload Capacity in Steganography
• PhaSR: Generalized Image Shadow Removal with Physically Aligned Priors
• ACE-SLAM: Scene Coordinate Regression for Neural Implicit Real-Time SLAM
• From Vision to Language: Investigating Causal Information Flow in Multimodal Decision-Making
• LaneDiffusion: Improving Centerline Graph Learning via Prior Injected BEV Feature Generation
• Out-of-Distribution Generalization in Climate-Aware Yield Prediction with Earth Observation Data
• Bridging the Skills Gap: A Course Model for Modern Generative AI Education
• Densemarks: Learning Canonical Embeddings for Human Heads Images via Point Tracks
• Test-Time Iterative Error Correction for Efficient Diffusion Models
• Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval
• Personalized targeted memory reactivation enhances consolidation of challenging memories via slow wave and spindle dynamics
• A New Strategy for Verifying Reach-Avoid Specifications in Neural Feedback Systems
• A multi-centre, multi-device benchmark dataset for landmark-based comprehensive fetal biometry
• Group Orthogonal Low-Rank Adaptation for RGB-T Tracking
• Patient Pose Assessment Using a CT-Based Framework for Synthetic Data Generation
• BEP: A Binary Error Propagation Algorithm for Binary Neural Networks Training
• Disco-RAG: Discourse-Aware Retrieval-Augmented Generation
• UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer
• Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models
• FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
• RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots
• BeyondMasks: Evaluating Causal and Physical Consistency in Video Object Removal
• Lemma Dilemma: On Lemma Generation Without Domain- or Language-Specific Training Data
• Advancing Multimodal Fusion on Heterogeneous Medical Data with Hybrid Geometry Attention
• Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch
• MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation
• ViInfographicVQA: A Benchmark for Single and Multi-image Visual Question Answering on Vietnamese Infographics
• Epanechnikov nonparametric kernel density estimation based feature-learning in respiratory disease chest X-ray images
• DoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time Series
• Executable Governance for AI: Translating Policies into Rules Using LLMs
• MigrationNarrate: A Dataset for Detection of Migration Narratives in YouTube Videos