AI.info

Latest Research — Page 67

Browse Latest Research on AI.info.

• Variance Matters: Improving Domain Adaptation via Stratified Sampling
• Graphical model for factorization and completion of relatively high rank tensors by sparse sampling
• Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts
• Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Era
• Cortex: Consolidating Context into Parametric Memory
• Collaborative Personalized Preference Alignment for LLMs under Data Deficiency
• Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation
• SeMo3D: Unifying 3D Generation, Editing, and Completion via Selective Modeling
• TreemapMix: Dirichlet-Controlled Multi-Image Augmentation for Probability and Ordinal Supervision
• Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning
• CreBench: Human-Aligned Creativity Evaluation from Idea to Process to Product
• Avatar Intelligence: Amplifying Human Agency Through Persistent Personal Agents
• DataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration
• SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL
• SPEAR++: Scaling Gradient Inversion via Sparsely-Used Dictionary Learning
• Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments
• Primary-Fine Decoupling for Action Generation in Robotic Imitation
• CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
• Moving Beyond Diffusion: Hierarchy-to-Hierarchy Autoregression for fMRI-to-Image Reconstruction
• AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning
• Causal Structure Learning for Dynamical Systems with Theoretical Score Analysis
• DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation
• Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies
• QCell: Recombining and Aligning Cell Queries for Overlapping Instance Segmentation
• Steering Vectors as a Training Signal in LLM Post-Training
• Coherent Multi-Agent Trajectory Forecasting in Team Sports with CausalTraj
• Modularity is the Bedrock of Natural and Artificial Intelligence
• Deep (Predictive) Discounted Counterfactual Regret Minimization
• MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems
• TCAndon-Router: Adaptive Reasoning Router for Multi-Agent Collaboration
• Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs
• Surrogate Models for Stochastic Al-Cu Phase-Field Solidification
• Enabling Fine-Grained Operating Points for Black-Box LLMs
• RWKV-PCSSC: Exploring RWKV Model for Point Cloud Semantic Scene Completion
• Difference Vector Equalization for Robust Fine-tuning of Vision-Language Models
• Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective
• RINS-T: Robust Implicit Neural Solvers for Time Series Linear Inverse Problems
• Estimation and Optimization of Ship Fuel Consumption in Maritime: Review, Challenges and Future Directions
• Shaer: Controlled Arabic Poetry Generation with Meter Subform and Semantic Conditioning
• Enhancing Time Series Classification with Diversity-Driven Neural Network Ensembles