UXBench Pro: Benchmarking Personalized User Experience in Multi-Turn Dialogue Interactions
Research
Research News
New papers, breakthroughs and academic AI research
Thinking Inertia: LLMs Keep Thinking When Told Not To
Research
Probing for Long-Horizon Deductive Reasoning Capabilities in Language Models with Prolog
Research
Large Language Model Turnover Undermines Screening for Artificial Intelligence-Assisted Scientific Writing
Research
Phonologically Informed Tokenization for German Speech Recognition: A Cross-Domain Study
Research
Efficient Multi-Granularity Knowledge Transfer for Radiology Report Generation
Research
Structured Sentiment Analysis Using Sequence Labeling as Dependency Graph Parsing
Research
What Output-Only Review Cannot Verify: Study Contracts for Research Agents
Research
RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing
Research
Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models
Research
Probability-Signature Dynamics: Unpacking Modular Addition Learning Within Two-Layer Networks
Research
MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation
Research