LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression Paper • 2403.12968 • Published Mar 19, 2024 • 26
LEMMA: Learning from Errors for MatheMatical Advancement in LLMs Paper • 2503.17439 • Published Mar 21 • 15
On Memory Construction and Retrieval for Personalized Conversational Agents Paper • 2502.05589 • Published Feb 8
REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once Paper • 2507.10541 • Published 18 days ago • 28
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models Paper • 2311.02373 • Published Nov 4, 2023