Search papers, labs, and topics across Lattice.
School of Electronics Engineering and Computer Science, Peking University
3
0
9
0
Unlocking the potential of compute-in-memory accelerators for LLMs requires carefully navigating a complex dataflow design space, and AccelCIM provides the first systematic framework to do so.
Finally, a video generation model that lets you puppeteer the camera independently of the scene, unlocking creative control previously impossible.
LLMs can escape the trap of converging on popular but incorrect answers in unsupervised RLVR by temporarily "unlearning" and exploring diverse response options.
