Direct Translation between Sign Languages
Research
Research News
New papers, breakthroughs and academic AI research
TomasuLLM: Out-of-Order Speculative Execution for LLM Agents
Research
Framing the Narrative: Ideological Mimicry in Large Language Models
Research
Evaluating Whether LLMs Can Reliably Connect the DOTs?
Research
DEdit: Iterative Draft Editing for Speculative Decoding
Research
Halluscoring 2026: The first shared task on llms hallucination detection and answer verification
Research
StreamDecisionBench: Evaluating Decisions in Force on Evolving Language Streams
Research
LLM Persona Unlearning
Research
Evaluating Language Model Safety Across Long Adversarial Conversations
Research
Marking Contour Tones in Yor\`{u}b\'{a}: A Typographic and Computational Proposal
Research
Security Properties of Neural Networks as Decision Problems
Research
Estimation of the Label-Noise Transition Matrix with Performance Guarantees via Selective Classification
Research