Search papers, labs, and topics across Lattice.
5
0
8
0
Value Flattening is identified as an important yet overlooked failure mode of critic learning in standard PPO and a simple sparse supervision strategy can mitigate it; SParse Proximal Policy Optimization is introduced, which applies the value loss to only a few well-separated states in each response to mitigate both effects.
Short-context models can achieve superior reasoning performance by leveraging long-context teacher models through innovative token alignment and training strategies.
Action-Grounded Representation Alignment (AGRA) transforms how robots interpret visual data, enabling them to focus on crucial interaction regions and significantly enhancing manipulation performance.
Even the best LLMs struggle with Olympiad-level combinatorics, achieving only 65.4% on a benchmark designed to expose their reasoning limitations.
