Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAGResearchSep 30, 2026
K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversationsResearchSep 30, 2026
Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt RewritingResearchSep 30, 2026
AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-DistillationResearchSep 30, 2026