Search papers, labs, and topics across Lattice.
3 papers from Apple ML Research on Reasoning & Chain-of-Thought
Just 20% of a strong model's chain-of-thought can unlock a weaker model's reasoning abilities, revealing the surprising transferability of CoT mechanics.
Key contribution not extracted.
RL fine-tuning can make vision-language models *less* reliable reasoners, as gains in benchmark accuracy come at the cost of faithfulness to the underlying visual grounding and chain-of-thought.
