Submitted by akhaliq 25 Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions · 25 authors 1
Submitted by akhaliq 17 OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch · 12 authors 1
Submitted by akhaliq 11 SlimPajama-DC: Understanding Data Combinations for LLM Training · 8 authors 1
Submitted by akhaliq 6 360^circ Reconstruction From a Single Image Using Space Carved Outpainting · 5 authors 1