AI
LITERARYBIGFIVE: Author-Personalized Text Generation in a Unified Interpretable Space
Researchers have developed a framework called LiteraryBigFive that enables personalized text generat...
AI
Pointing-VLA: Typed Spatial Grounding Interfaces for Vision-Language-Action Manipulation
Researchers have developed Pointing-VLA, a new approach to vision-language-action models that improv...
AI
Language Chain in Alignment: Cross-Lingual Ranking Preference Optimization
Researchers propose Cross-Lingual Ranking Preference Optimization (CRPO), a framework that uses Engl...
AI
Counterfactual Transition Graphs: Evaluating Cross-Class Transition Quality
Researchers propose a new framework for evaluating how time-series classifiers connect their own cla...
AI
NetConfArena: An Executable Benchmark for LLM Agents in Closed-Loop Network Configuration
Researchers have created an executable benchmark called NetConfArena for evaluat...
AI
BenthicDINO: Physics-Informed Self-Distillation for View-Invariant Side-Scan Sonar Representations
Researchers have developed BenthicDINO, a new framework for processing side-scan...
AI
AI Surrogate Modeling for Real-Time Tokamak Equilibrium Prediction: Benchmarking Neural Architectures and Validation on EXL-50U
Researchers have developed an AI surrogate framework for predicting plasma equil...
AI
Think Only When Needed: Prompt-Authority Control for Selective Slow-Path Intervention in Vision-Language-Action Manipulation
Researchers have developed a system called TOWN-VLA (Think Only When Needed) to ...