Search papers, labs, and topics across Lattice.
3
0
6
1
Occamy-1.0, a cost-efficient co-work model obtained by further training the post-trained Qwen3.6-35B-A3B checkpoint, is presented and placed at the low-cost knee of the observed cost--performance Pareto frontier.
Achieving state-of-the-art results in pose estimation, this method leverages symmetry-aware features to simplify the complexities of rotation learning in a non-linear space.
Agentic models can learn to trust their "gut" and rely less on external tools, leading to faster and more accurate reasoning.
