AI.info

Latest Research — Page 99

Browse Latest Research on AI.info.

• Locally Adaptive Multi-Objective Learning
• Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE
• In Situ Training of Implicit Neural Compressors for Scientific Simulations via Sketch-Based Regularization
• Multilingual Generative Retrieval via Cross-lingual Semantic Compression
• 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
• QuantumCanvas: A Multimodal Benchmark for Visual Learning of Atomic Interactions
• MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching
• HRoPE: Homography Relative Positional Encoding
• Unsupervised Evaluation of Multi-Turn Objective-Driven Interactions
• IM HERE: Interaction Model for Human Effort Based Robot Engagement
• TED++: Submanifold-Aware Backdoor Detection via Layerwise Tubular-Neighbourhood Screening
• CoordAR: One-Reference 6D Pose Estimation of Novel Objects via Autoregressive Coordinate Map Generation
• When AI Enters the Workplace, Who Faces Greater Risks? A Gendered Analysis
• Neural Symbollic Regression Using Deep Learning and Sparse Modelling
• T-DIG: Text-Conditioned Diversity for Image Generation
• Evolving Memory, Learning to Meta-Control: Test-Time Adaptation for Experience-augmented LLM Agents
• Parameter efficient hybrid spiking-quantum convolutional neural network with surrogate gradient and quantum data-reupload
• Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning
• S-Space: Exploring Spatial Workspace in Multimodal Language Models
• FedOnco-Bench: A Reproducible Benchmark for Privacy-Aware Federated Tumor Segmentation with Synthetic CT Data
• Wizard: Manipulate Any World in Real Time via Agentic Control
• Stop Jostling: Adaptive Negative Sampling Reduces the Marginalization of Low-Resource Language Tokens by Cross-Entropy Loss
• Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models
• A parameter-efficient three-branch architecture for multimodal misinformation detection with limited annotations
• Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs
• MaskOpt: A Large-Scale Mask Optimization Dataset to Advance AI in Integrated Circuit Manufacturing
• When Is Tracking Affordable? A Movement-Budget Feasibility Threshold for Dynamic Regret
• TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining
• The Prestige: Benchmarking Cognitive Visual Reasoning using Magic Tricks
• Training-free Online Video Step Grounding
• ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction
• Simplifying Outcomes of Language Model Component Analyses with ELIA
• Neurosymbolic Information Extraction from Transactional Documents
• HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs
• A Robust Task-Level Control Architecture for Learned Dynamical Systems
• DR.Experts: Differential Refinement of Distortion-Aware Experts for Blind Image Quality Assessment
• Rennala NSGD: Asynchronous Stochastic Optimization Beyond Euclidean Geometry
• Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay
• A Framework for the Systematic Evaluation of Obstacle Avoidance and Object-Aware Controllers