Search papers, labs, and topics across Lattice.
7
8
11
4
Learned routers can outperform fixed-model baselines by 14.6%, revealing a new frontier in efficient LLM deployment.
Constraint-First Reasoning reveals that explicitly managing answer-space constraints can dramatically enhance the accuracy of mathematical problem-solving in language models.
Self-evolving rubric rewards can dramatically enhance audio reasoning in models, outperforming traditional methods by adapting to the model's evolving capabilities.
Subsampling MSAs based on energetic frustration can dramatically enhance the recovery of alternative protein conformations, outperforming traditional sequence-based methods.
LLMs can now rank millions of candidates with significant accuracy gains thanks to a novel K-means clustering and graph-based ensemble approach that overcomes context length limitations.
LLMs can now tap into arbitrarily long-term memories by retrieving "thoughts" – their own past reasoning steps – rather than just raw data, leading to significant performance gains.
Continuous diffusion can finally rival discrete methods in language modeling, thanks to LangFlow's novel architecture and training techniques.
