AI.info

Latest Research — Page 28

Browse Latest Research on AI.info.

• Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression
• Parallel Complex Diffusion for Scalable Time Series Generation
• LumiX: Structured and Coherent Text-to-Intrinsic Generation
• Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch
• Local Guidance for Configuration-Based Multi-Agent Pathfinding
• Segment, Embed, and Align: A Universal Recipe for Aligning Subtitles to Signing
• AnyTouch 2: General Optical Tactile Representation Learning For Dynamic Tactile Perception
• FCMBench: The First Large-scale Financial Credit Multimodal Benchmark for Real-world Applications
• Toward Reliable Sim-to-Real Predictability for MoE-based Robust Quadrupedal Locomotion
• Variance Matters: Improving Domain Adaptation via Stratified Sampling
• Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation
• Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning
• CreBench: Human-Aligned Creativity Evaluation from Idea to Process to Product
• 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
• CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
• 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
• 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
• Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs
• Difference Vector Equalization for Robust Fine-tuning of Vision-Language Models
• Causal Bayesian Optimization: Foundations, Methods, and Applications
• ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion
• When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluation
• Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks
• The Confidence Trap: Gender Bias and Predictive Certainty in LLMs
• How Many Experts Are Enough? Towards Optimal Semantic Specialization for Mixture-of-Experts
• A Mean-Field Framework for Inference-Time Distributional Control of Diffusion Models
• Importance-Aware Data Selection for Efficient LLM Instruction Tuning
• Diverse Preference Learning for Capabilities and Alignment
• Cite or Decline: A Strict Course-Grounded Chatbot for STEM Lecture Videos
• Continuous SUN (Stable, Unique, and Novel) Metric for Generative Modeling of Inorganic Crystals
• StreamingVLM: Real-Time Understanding for Infinite Video Streams
• Quality Diversity for Reliable Data Driven Time-Use Optimization
• Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization