Submitted by akhaliq 47 DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models · 17 authors 2
Submitted by akhaliq 27 Secrets of RLHF in Large Language Models Part II: Reward Modeling · 27 authors 4
Submitted by akhaliq 24 TRIPS: Trilinear Point Splatting for Real-Time Radiance Field Rendering · 4 authors
Submitted by akhaliq 24 Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation · 14 authors 1
Submitted by akhaliq 21 Patchscope: A Unifying Framework for Inspecting Hidden Representations of Language Models · 5 authors
Submitted by akhaliq 10 Diffusion Priors for Dynamic View Synthesis from Monocular Videos · 7 authors
Submitted by akhaliq 8 A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way Parallelism · 5 authors
Submitted by akhaliq 7 Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages · 2 authors