Search papers, labs, and topics across Lattice.
5
0
7
0
FP4 RL for MoE LLMs can now match BF16 rollout quality with 5.4x speedup by directly aligning train-rollout quantization.
Expert design guidance nearly doubles LLM agent speedups for GPU kernel generation, yet agents still miss critical low-level optimizations.
Rather than treating agent trajectories as dead post-training demonstrations, researchers can now resurrect thousands of fully executable, verifiable terminal environments directly from tool-execution logs.
