Search papers, labs, and topics across Lattice.
7 papers from Google DeepMind on Reasoning & Chain-of-Thought
Training LLMs to optimize for conflicting objectives between the final output and the reasoning process can significantly degrade the monitorability of Chain-of-Thought, making oversight more difficult.
LLMs get *more* honest when they have time to reason, defying human tendencies and revealing surprising insights about their internal representational geometry.
Mixture-of-Experts models might be hiding more of their reasoning than we thought, thanks to a newly quantified "opaque serial depth" metric.
Achieve significantly better code generation and mathematical problem solving from diffusion language models with a simple, training-free sampling tweak that encourages diversity.
Gemini 3 Deep Think can now autonomously solve a majority of problems in a challenging math competition, signaling a leap in AI's mathematical reasoning capabilities.
Forget full-cache rollouts: this parameter-efficient fine-tuning method lets large reasoning models maintain accuracy while slashing memory usage during RL training.
Reasoning-based safety guardrails, once thought to be a strong defense against jailbreaks, crumble with just a few strategically placed tokens.
