Submitted by akhaliq 67 Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation · 7 authors 3
Submitted by akhaliq 25 Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning · 4 authors 2
Submitted by akhaliq 20 Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis · 7 authors 5
Submitted by akhaliq 16 VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers · 9 authors
Submitted by akhaliq 13 Margin-aware Preference Optimization for Aligning Diffusion Models without Reference · 6 authors 1
Submitted by akhaliq 13 ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization · 9 authors
Submitted by akhaliq 10 MLCM: Multistep Consistency Distillation of Latent Diffusion Model · 6 authors
Submitted by akhaliq 9 ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models · 6 authors
Submitted by akhaliq 9 GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement · 10 authors