AI.info

Latest Research — Page 38

Browse Latest Research on AI.info.

• DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning
• Learner-Tailored Program Repair: A Solution Generator with Iterative Edit-Driven Retrieval Enhancement
• AUHead: Realistic Emotional Talking Head Generation via Action Units Control
• Decompose Radicals, Then Reward: Fine-Grained Inspection for Accurate Chinese Text Rendering
• Context and Symmetry in Auditing: A Case Study of Skeleton Inference in Motion Capture
• Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator
• SocialFusion: Addressing Social Degradation in Pre-trained Vision-Language Models
• Customizing Open Source LLMs for Quantitative Medication Attribute Extraction across Heterogeneous EHR Systems
• It Takes Two: A Dual Stage Approach for Terminology-Aware Translation
• Speculative Sampling with Reinforcement Learning
• WUSH: Near-Optimal Adaptive Transforms for LLM Quantization
• Can LLMs Help You at Work? A Sandbox for Evaluating LLM Agents in Enterprise Environments
• A physics-aware deep learning model for shear band formation around collapsing pores in shocked reactive materials
• Detecting Generated Images by Fitting Natural Image Distributions
• CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models
• Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos
• Human-in-the-Loop Testing of AI Agents for Air Traffic Control with a Regulated Assessment Framework
• Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation
• Recoverability Has a Law: The ERR Measure for Tool-Augmented Agents
• NRGPT: An Energy-based Alternative for GPT
• Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Models
• Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping
• Introducing Echo Networks for Computational Neuroevolution
• DUALFloodGNN: Physics-informed Graph Neural Network for Operational Flood Modeling
• Information-Theoretic Quality Metric of Low-Dimensional Embeddings
• Quantum Machine Learning for Image Classification: A Hybrid Model of Residual Network with Quantum Support Vector Machine
• RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory
• SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs Quantization
• Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion Models
• LLM-based Few-Shot Early Rumor Detection with Imitation Agent
• AgentXRay: White-Boxing Agentic Systems via Workflow Reconstruction
• LociArt: A Unified Paradigm for Free-Style Local Video Stylization
• Textual Equilibrium Propagation for Deep Compound AI Systems
• Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight
• tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction
• Adaptive Partitioning Schemes for Optimistic Optimization
• Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation
• MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
• Higher-order Linear Attention
• Few-Shot Adaptation Benchmark for Remote Sensing Vision-Language Models