Search papers, labs, and topics across Lattice.
7
0
12
4
Kimi K3's innovative architecture achieves a 2.5x scaling efficiency improvement, enabling robust performance across diverse long-horizon tasks.
SelPE achieves high-fidelity structured text synthesis under strict privacy constraints, outperforming traditional methods in low-data environments.
LaST-HD achieves over 90% accuracy in robot manipulation tasks using just 20 minutes of low-cost human demonstration data, revolutionizing how robots learn from human actions.
Decomposing complex reasoning problems into verifiable subproblems unlocks significant performance gains in LLM reasoning, especially on hard problems previously stuck in gradient dead zones.
Train a text-to-image model that rivals the state-of-the-art with 1/5th the compute by using GPT-4 to generate better captions.
Ditch the pixel-perfect edits: letting multimodal models fully *reimagine* images based on semantic understanding yields massive quality gains in refinement tasks.
LLMs struggle with long-horizon reasoning in software engineering because they retrieve irrelevant memories, but aligning memory with subtasks boosts performance by 4.7 points on SWE-bench.
