Search papers, labs, and topics across Lattice.
Tencent Hunyuan ,
3
1
4
5
RL gains in LLMs are surprisingly localized to a low-dimensional, non-infinitely compressible manifold, with control directions orthogonal to principal activation components.
Merging existing expert capabilities can yield significant performance boosts, but choosing the right fusion method can make all the difference in multi-domain reinforcement learning.
