AI.info

Latest Research — Page 10

Browse Latest Research on AI.info.

• A Mixed Diet Makes DINO An Omnivorous Vision Encoder
• InnoText: A Unified Model for Visual Text Generation and Editing
• VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control
• What "Not" to Detect: Negation-Aware VLMs via Structured Reasoning and Token Merging
• Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones
• Optimization and Mobile Deployment for Anthropocene Neural Style Transfer
• Scalable Multi-Objective and Meta Reinforcement Learning via Gradient Estimation
• Merlin L48 Spectrogram Dataset
• Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption Models
• Causal Reinforcement Learning based Agent-Patient Interaction with Clinical Domain Knowledge
• Open Polymer Challenge: Post-Competition Report
• Text Annotation via Inductive Coding: Comparing Human Experts to LLMs in Qualitative Data Analysis
• A Causal Markov Condition for Value
• Prompt Estimation from Prototypes for Federated Prompt Tuning of Vision Transformers
• Expectations and Practices around AI Disclosure in CS Research
• Disentangling Shared and Private Neural Dynamics with SPIRE: A Latent Modeling Framework for Deep Brain Stimulation
• Optimal Meal Schedule for a Local Nonprofit Using LLM-Aided Data Extraction
• A Stochastic Differential Equation Framework for Multi-Objective LLM Interactions: Dynamical Systems Analysis with Code Generation Applications
• MuViT: Multi-Resolution Vision Transformers for Learning Across Scales in Microscopy
• Fast Weight Attention for Continual Learning
• How Far Can 5,500 Hours of Driving Take You? A Scaling Law Analysis of Video Diffusion Models
• DICE: Discrete Interpretable Comparative Evaluation with Probabilistic Scoring for Retrieval-Augmented Generation
• Graph homophily booster: Reimagining the role of discrete features in heterophilic graph learning
• KoSimpleQA: A Korean Factuality Benchmark with an Analysis of Reasoning LLMs
• Confidence Estimation for LLMs in Multi-turn Interactions
• Fast 3D Surrogate Modeling for Data Center Thermal Management
• FlowBind: Efficient Any-to-Any Generation with Bidirectional Flows
• FreeAskWorld: An Interactive and Closed-Loop Simulator for Human-Centric Embodied AI
• VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
• Private Zeroth-Order Optimization with Public Data
• EagleVision: A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence
• TOSC: Task-Oriented Shape Completion for Open-World Dexterous Grasp Generation from Partial Point Clouds
• OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects
• VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs
• Get RICH or Die Scaling: Profitably Trading Inference Compute for Robustness
• FaithLens: Detecting and Explaining Faithfulness Hallucination
• Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations
• Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Multi-View Performance Captures
• Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoning
• No One to Blame: A Framework of Constitutive AI Unaccountability