AI.info

Latest Research — Page 31

Browse Latest Research on AI.info.

• Spatially Aware Linear Transformer (SAL-T) for Particle Jet Tagging
• Sobolev Regularized Score Difference Estimation in Diffusion Models
• OmniGaze: Reward-inspired Generalizable Gaze Estimation In The Wild
• PermLLM: Learnable Channel Permutation for N:M Sparse Large Language Models
• Emergent Compositional Skills in Mixture-of-Experts VLAs
• Traj-CoA: Patient Trajectory Modeling via Chain-of-Agents for Lung Cancer Risk Prediction
• Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit
• Scaling Image Geo-Localization to Continent Level
• Context-Aware Mixture of Domain Experts for Bodily Expression of Emotion in the Wild
• Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training Recipe for Small-Model Dialogue Game Agents
• Attribute-Aware Controlled Product Generation with LLMs for E-commerce
• Glance-or-Gaze: Incentivizing LMMs to Adaptively Focus Search via Reinforcement Learning
• FairGU: Fairness-aware Graph Unlearning in Social Networks
• Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging
• AWM: Accurate Weight-Matrix Fingerprint for Large Language Models
• The Role of Implicit and Explicit Demographic Signals in Large Language Model-based Student Assessment
• Improving the Physics of Video Generation with VJEPA-2 Reward Signal
• PCEval: A Benchmark for Evaluating Physical Computing Capabilities of Large Language Models
• DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference
• StreamingTOM: Streaming Token Compression for Efficient Video Understanding
• From Knowledge to Inference: Formalizing Specialized Public Health Reasoning on GlobalHealthAtlas
• Re-understanding Graph Unlearning through Memorization
• A Systematic Benchmark of Intensity Normalisation Methods for 3D Knee MRI Segmentation and Cross-Domain Generalisability
• A Comparative Evaluation of Embeddings and LLMs in a Greek Book Publisher Setting - The CUP Dataset
• Evidence-Decision-Feedback: Theory-Driven Adaptive Scaffolding for LLM Agents
• Learning Cell-Aware Hierarchical Multi-Modal Representations for Robust Molecular Modeling
• HYPE-EDIT-1: Benchmark for Measuring Reliability in Frontier Image Editing Models
• Distributional Consistency Loss: Beyond Pointwise Data Terms in Inverse Problems
• Nip Rumors in the Bud: Retrieval-Guided Topic-Level Adaptation for Test-Time Fake News Video Detection
• PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards
• LAOF: Robust Latent Action Learning with Optical Flow Constraints
• ADVICE: Answer-Dependent Verbalized Confidence Estimation
• Multi-granularity Interactive Attention Framework for Residual Hierarchical Pronunciation Assessment
• MEGConformer: Conformer-Based MEG Decoder for Robust Speech and Phoneme Classification
• Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement
• MedEyes: Learning Dynamic Visual Focus for Medical Progressive Diagnosis
• Semi-Supervised Regression with Heteroscedastic Pseudo-Labels
• DART: A Structured Dataset of Regulatory Drug Documents in Italian for Clinical NLP
• Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection
• FEA-SLT: A Gloss-Free End-to-End Framework for Facial-Expression-Aware Sign Language Translation