Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering
Research
Research News
New papers, breakthroughs and academic AI research
Learning Infinite-Horizon Average-Reward CMDPs via State Augmentation
Research
Learning Normal Diffusion Dynamics for Backdoor Defense in Text-to-Image Models
Research
Security-Enhanced Seed-Based Weight Quantization for Large Language Models
Research
Evidence-Guided Schema Normalization for Temporal Tabular Reasoning
Research
Evaluating Alignment of Behavioral Dispositions in LLMs
Research
Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization
Research
KlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy
Research
SiDiaC-v.2.0: Sinhala Diachronic Corpus Version 2.0
Research
Personalized State-Transition-Aware Memory for Clinical Agents
Research
Think Multilingual, Not Harder: A Data-Efficient Framework for Teaching Reasoning Models to Code-Switch
Research
CDMD: A Cross-Dataset Mixed-Type Diffusion Model for Tabular Data
Research