AI.info

Latest Research — Page 97

Browse Latest Research on AI.info.

• Parametric Knowledge is Not All You Need: Toward Honest Large Language Models via Retrieval of Pretraining Data
• Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs
• Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer
• Transfer Learning in Nonparametric Regression with Deep ReLU Networks
• FaNe: Towards Fine-Grained Cross-Modal Contrast with False-Negative Reduction and Text-Conditioned Sparse Attention
• TINNs: Time-Induced Neural Networks for Solving Time-Dependent PDEs
• qa-FLoRA: Data-free query-adaptive Fusion of LoRAs for LLMs
• RecalibrateGPT: AI Fatigue Resilient Conversational Interfaces
• Variational Autoencoder for Calibration: A New Approach
• VIS-Ground: Video Interactive Storytelling with Contextual Grounding
• SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search
• Cross-modal Consistency Guidance for Robust Emotion Control in Auto-Regressive TTS Models
• Robust Ego-Exo Correspondence with Long-Term Memory
• SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment
• ProxyFL: A Proxy-Guided Framework for Federated Semi-Supervised Learning
• PnP-Transformer: A Neural Pose Solver for 6D Object Pose Estimation
• MeSH: Memory-as-State-Highways for Recursive Transformers
• Life, Machine Learning, and the Search for Habitability: Predicting Biosignature Fluxes for the Habitable Worlds Observatory
• Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation
• Scalable Deep Subspace Clustering Network
• LISTEN to Your Preferences: An LLM Framework for Multi-Objective Selection
• Improved Dimension Dependence for Bandit Convex Optimization with Gradient Variations
• OLR-WAA: Adaptive and Drift-Resilient Online Regression with Dynamic Weighted Averaging
• MADS: Multi-Agent Dialog Simulation for Robust Conversational Agents
• Variance Driven Exploration: A Provable and Efficient Methodology for Pure Exploration in Highly Stochastic Environments
• CycliST: A Video Language Model Benchmark for Reasoning on Cyclical State Transitions
• Assessing nnU-Net Generalization across Brain Tumor Populations in BraTS-GoAT 2026
• OpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectories
• DaCe-DT: Data-Centric Offline Multi-Task Reinforcement Learning via Adaptive Prompts and Trajectory Correction for Heterogeneous Tasks
• CoMViT: An Efficient Vision Backbone for Supervised Classification in Medical Imaging
• Buy versus Build an LLM: A Decision Framework for Governments
• HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding
• ALIVE: Interaction-Aligned Object Insertion for First-Frame-Guided Video Editing
• Mostly Reading: What Open-Book Scores Measure in Document-Level LoRA Adapters
• Improving Synthetic Data Generation for Argument Mining via Adversarial Reinforcement Learning
• RLSLM: A Hybrid Reinforcement Learning Framework Aligning Rule-Based Social Locomotion Model with Human Social Norms
• ChanSFormer: A Channel Agnostic Vision Transformer for Multi-Channel Cell Painting Images
• Simple and Efficient Heterogeneous Temporal Graph Neural Network
• ACE-Brain-0: Spatial Intelligence as a Shared Scaffold for Universal Embodiments
• E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memory