AI.info

Latest Research — Page 27

Browse Latest Research on AI.info.

• Improved Algorithms for Nash Welfare in Linear Bandits
• UNSEEN: Enhancing Dataset Pruning from a Generalization Perspective
• Energy and Memory-Efficient Federated Learning With Ordered Layer Freezing
• Sharp Monocular View Synthesis in Less Than a Second
• Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers
• Gaze as Evidence for Common Grounding: A Cross-Corpus Analysis of MapTask and MUNDEX
• Glance and Focus Reinforcement for Pan-cancer Screening
• Interlock: From Local Correctness to Task Completion in Long-Horizon Agents
• ActionSplice: In-Flight Action Editing for Interactive World Models
• Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologies
• CROCODIL: Cross-Model Code Editing with LLMs
• Enhancing Medical Large Vision-Language Models via Alignment Distillation
• RAVEN: Robust Advertisement Video Violation Temporal Grounding via Reinforcement Reasoning
• Computational Foundations for Strategic Coopetition: Formalizing Interdependence and Complementarity
• DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection
• FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning
• Removing Cost Volumes from Optical Flow Estimators
• Introducing Axlerod: An LLM-based Chatbot for Assisting Independent Insurance Agents
• Overcoming the Curvature Bottleneck in MeanFlow
• B-DENSE: Branching For Dense Ensemble Network Learning
• MobileMem: Learning from a Year of Mobile Experiences
• teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Data
• Trainable Vector Quantization for Large Language Models
• Generative World Simulation with DAO and JING
• OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models
• V-Zero: Self-Improving Multimodal Reasoning with Zero Annotation
• AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages
• Polar Coordinate-based Differential Evolution for Moving Target Search Using Vision Sensor on Unmanned Aerial Vehicles
• Causal Strengths and Leaky Beliefs: Interpreting LLM Reasoning via Noisy-OR Causal Bayes Nets
• Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction
• BudgetPix: Compute-Adaptive Tokenization for Pixel-Space Image Diffusion
• Generalized Spherical Neural Operators: Green's Function Formulation
• PROMISE: Prompt-Attentive Hierarchical Contrastive Learning for Robust Cross-Modal Representation with Missing Modalities
• Pre-trained Forecasting Models: Strong Zero-Shot Feature Extractors for Time Series Classification
• ESCA: Contextualizing Embodied Agents via Scene-Graph Generation
• StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos
• Agentic BAIM-LLM Evaluation (ABLE): Benchmarking LLM Use of Protein Design Tools
• Oxytrees: Model Trees for Bipartite Learning
• Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts
• FISCAL: Financial Synthetic Claim-document Augmented Learning for Efficient Fact-Checking