AI.info

Latest Research — Page 41

Browse Latest Research on AI.info.

• Buy versus Build an LLM: A Decision Framework for Governments
• HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding
• ACE-Brain-0: Spatial Intelligence as a Shared Scaffold for Universal Embodiments
• E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memory
• CADO: From Imitation to Cost Minimization for Heatmap-based Solvers in Combinatorial Optimization
• Approximating Shapley Explanations in Reinforcement Learning
• RARF: Region-Aware Rectified Flows for 3D Brain MRI Inpainting
• FactGuard: Event-Centric and Commonsense-Guided Fake News Detection
• AI Should Facilitate Democratic Deliberation at Scale
• Low-Rank Ternary Adaptation for Fine-Tuning Transformers
• SimBA: Simplifying Benchmark Analysis Using Performance Matrices Alone
• OAD-Promoter: Enhancing Zero-shot VQA using Large Language Models with Object Attribute Description
• Family Matters: A Systematic Study of Spatial vs. Frequency Masking for Continual Test-Time Adaptation
• ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents
• CHAMMI-75: Pre-training multi-channel models with heterogeneous microscopy images
• PixPerfect: Seamless Latent Diffusion Local Editing with Discriminative Pixel-Space Refinement
• COCO-Tree: Compositional Hierarchical Concept Trees for Enhanced Reasoning in Vision Language Models
• SPADE: Self-Play in Adaptive Synthetic Executable Environments
• MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping
• Reinforced Linear Genetic Programming
• Text-Only Training for Image Captioning with Retrieval Augmentation and Modality Gap Correction
• SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration
• Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention
• Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation
• Unsupervised Evaluation of Multi-Turn Objective-Driven Interactions
• When AI Enters the Workplace, Who Faces Greater Risks? A Gendered Analysis
• Neural Symbollic Regression Using Deep Learning and Sparse Modelling
• Parameter efficient hybrid spiking-quantum convolutional neural network with surrogate gradient and quantum data-reupload
• Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models
• A parameter-efficient three-branch architecture for multimodal misinformation detection with limited annotations
• ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction
• DR.Experts: Differential Refinement of Distortion-Aware Experts for Blind Image Quality Assessment
• STAGE: STyle-controllable Action GEneration for personalized autonomous driving
• The Denario project: Deep knowledge AI agents for scientific discovery
• CASTLE: A Comprehensive Benchmark for Evaluating Student-Tailored Personalized Safety in Large Language Models
• BADiff: Bandwidth Adaptive Diffusion Model
• Last Translation Benchmark
• Animus3D: Text-driven 3D Animation via Motion Score Distillation
• CLIP-FTI: Fine-Grained Face Template Inversion via CLIP-Driven Attribute Conditioning
• Spatiotemporal-Untrammelled Mixture of Experts for Multi-Person Motion Prediction