Sample-efficient Integration of New Modalities into Large Language Models Paper • 2509.04606 • Published 4 days ago • 6
Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them Paper • 2507.10616 • Published Jul 13 • 1
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering Paper • 2410.15999 • Published Oct 21, 2024 • 20