Search papers, labs, and topics across Lattice.
8 papers published across 1 lab.
Omni-modal foundation models achieve self-improvement via RL compute scaled to 1M context, leveraging asynchronous training and agentic grading for enhanced intelligence.
Activations, not just descriptions, unlock the prediction of how LLM alignment generalizes to unseen values, revealing a structured value space.
KL regularization's failure in group policy optimization stems from subtle reward interactions, but a new calibration method unlocks performance gains.
Discarding just a few high-advantage rollouts during GRPO updates dramatically boosts LLM reasoning and exploration.
Aggressively scaling exploration in RLVR without sacrificing model quality is now possible by distilling novel strategies from dedicated explorer policies.
Activations, not just descriptions, unlock the prediction of how LLM alignment generalizes to unseen values, revealing a structured value space.
KL regularization's failure in group policy optimization stems from subtle reward interactions, but a new calibration method unlocks performance gains.
Discarding just a few high-advantage rollouts during GRPO updates dramatically boosts LLM reasoning and exploration.
Omni-modal foundation models achieve self-improvement via RL compute scaled to 1M context, leveraging asynchronous training and agentic grading for enhanced intelligence.
Aggressively scaling exploration in RLVR without sacrificing model quality is now possible by distilling novel strategies from dedicated explorer policies.
Distilling teacher-relative logit shifts, not just final policies, unlocks substantial gains in multi-teacher on-policy distillation by preventing inherited base biases from dominating learned preferences.
Stated-preference economics offers a robust framework for evaluating LLM responses to subjective questions, revealing that even advanced models can fail basic economic validity tests.
Reward modeling inference costs plummet by up to 7x by performing judgments entirely in a compressed latent space, bypassing token-by-token generation.
