Submitted by akhaliq 52 Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing · 7 authors 3
Submitted by akhaliq 16 TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding · 5 authors 1
Submitted by akhaliq 14 Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment · 5 authors 1
Submitted by akhaliq 14 MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation · 6 authors 1