Whose Voice Survives the Summary? A Voice-Retention Audit of LLM Employee Listening
Research
Research News
New papers, breakthroughs and academic AI research
More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models
Research
CompOrca: Corpus-Scale Compliance Labelling of Instruction-Tuning Data
Research
When Reasoning Goes Astray: Attention Dynamics of Uncontrolled Reasoning
Research
Diversity Combining for Multi-Path LLM Reasoning
Research
NeurDuo-EEG: A Long-Sequence EEG Foundation Model with Persistent State and Explicit Memory
Research
Talk2Agent: Benchmarking Voice Interfaces for Text Agents
Research
Composing Task-specific Agent Harnesses at Test Time with Reusable Primitives
Research
Risk-Aware Adaptive Evaluation: Finding High-Impact Failures Under Limited Budgets
Research
ReLaG: A Scalable Framework Generalizing Random Splits to Data with Latent Relations
Research
When a Flatness Proxy Is Not a Function: Robustness Certificates and Training Interventions
Research
FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing
Research