When to Call an LLM: A Confidence-Gated Hybrid for Cost-Effective Emotion Recognition in Conversational AI
Research
Research News
New papers, breakthroughs and academic AI research
Anchoring What Matters: A Dual-Level Learning Framework for Visually-Grounded Multimodal Reasoning
Research
Do Frontier Models Seek Safety Evidence Before Acting?
Research
RideWay: Benchmarking Efficient Task Completion for Tool-Using Language Agents
Research
Memory Has Geometry: Non-Uniform Geometric Memory for Long-Horizon Personalized AI
Research
TuiML: Machine Learning for AI Agents
Research
Missing Bridges: Composition-Aware Active Imitation Learning
Research
Is Trump's Vocabulary Poor? Vocabulary Richness Across Texts of Different Lenghts
Research
Disentangling Algorithmic Bias from Archival Artifacts: A Controlled Audit of Vision-Language Model Valuation in Metropolitan Museum Archives
Research
Enhancing Extubation Failure Prediction with LLM-Derived Features from Respiratory Therapy Clinical Notes
Research
Where Grokking Happens: Distributed Utility and Fourier Recoding Without a Module Switch
Research
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents
Research