Aligned but Not Partner-Specific: How Multimodal LLM Agents Succeed in Reference Games Without Forming Conceptual Pacts
Research
Research News
New papers, breakthroughs and academic AI research
ReNikud: Audio-Supervised Hebrew Grapheme-to-Phoneme Conversion
Research
GS-PQM: A Parameter-Domain Quality Metric for Compressed Gaussian Splatting
Research
Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning
Research
Why Your Deep Research Agent Fails? On Hallucination Evaluation in Full Research Trajectory
Research
Credal Large Language Models for Semantic Commitment under Uncertainty
Research
Text-Preserving Lossy Text Compression: A Study of Strategic Deletion and LLM Reconstruction
Research
DECK: A Consistency x Confidence Taxonomy of LLM Hallucinations
Research
FedFit: Federated Fine-Tuning of LLMs via Vector-Bank Parameterization and Quantization
Research
Towards Optimal Policy Improvement
Research
Generalization in Neural Networks Through the Lens of Magnitude Potential
Research
A Comprehensive Review of One-Pixel Attack: Research Status, Taxonomy, Applications, Regulation Policy and Future Directions
Research