Search papers, labs, and topics across Lattice.
5
0
9
5
Qwen-UI-Agent outperforms leading models in mobile and cross-platform tasks, achieving up to 97.5% accuracy on key benchmarks.
Multimodal context learning remains critically underdeveloped, with top models barely scratching the surface of effective performance.
Weak policies can achieve up to 18.6% better performance with PATS, a training framework that dynamically adapts guidance based on evolving policy needs.
Distilled RL achieves a breakthrough in LLM post-training by effectively transferring previously inaccessible knowledge, outperforming traditional methods in both accuracy and adaptability.
LLMs can now optimize GPU kernels more effectively by learning from a structured memory of optimization strategies at different levels of abstraction.
