NiT Collection release all the pre-trained models for Native-resolution diffusion Transformer β’ 6 items β’ Updated Sep 16 β’ 1
π November 2025 - China Open Source Highlights Collection 13 items β’ Updated about 11 hours ago β’ 4
Instella β¨ Collection Announcing Instella, a series of 3 billion parameter language models developed by AMD, trained from scratch on 128 Instinct MI300X GPUs. β’ 13 items β’ Updated about 16 hours ago β’ 10
view article Article Weβre open-sourcing our text-to-image model and the process behind it 7 days ago β’ 60
Jan-v2-VL Collection Jan-v2-VL: an 8B VLM focused on reliable, many-step task execution. β’ 6 items β’ Updated 6 days ago β’ 27
MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE Paper β’ 2507.21802 β’ Published Jul 29 β’ 16
Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback Paper β’ 2510.16888 β’ Published about 1 month ago β’ 20
MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training Paper β’ 2311.17049 β’ Published Nov 28, 2023 β’ 4
SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions Paper β’ 2403.16627 β’ Published Mar 25, 2024 β’ 22
OlmoEarth Collection OlmoEarth pre-trained and fine-tuned foundation models for remote sensing β’ 10 items β’ Updated 15 days ago β’ 11
Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning Paper β’ 2510.25992 β’ Published 20 days ago β’ 42
MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency Paper β’ 2510.25897 β’ Published 20 days ago β’ 16
view article Article β‘ nano-vLLM: Lightweight, Low-Latency LLM Inference from Scratch Jun 28 β’ 24
Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion Paper β’ 2410.19324 β’ Published Oct 25, 2024 β’ 2
Emu3.5 Collection Native Multimodal Models are World Learners π β’ 4 items β’ Updated 6 days ago β’ 71
RAE Collection Collection for Diffusion Transformers with Representation Autoencoders β’ 1 item β’ Updated Oct 14 β’ 10