MMR1 Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources
@_akhaliq
-
Hunyuan3D-Omni: Unified Framework for Controllable 3D Asset Generation
By
–
Hunyuan3D-Omni A Unified Framework for Controllable Generation of 3D Assets
-
MetaEmbed: Scaling Multimodal Retrieval with Flexible Late Interaction
By
–
MetaEmbed Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction
-
VideoFrom3D: 3D Scene Video Generation with Diffusion Models
By
–
VideoFrom3D
— AK (@_akhaliq) 23 septembre 2025
3D Scene Video Generation via Complementary Image and Video Diffusion Models pic.twitter.com/zwVJRtf1g1From3D 3D Scene Generation via Complementary Image and Diffusion Models
-
DiffusionNFT: Online Diffusion Reinforcement with Forward Process
By
–
DiffusionNFT Online Diffusion Reinforcement with Forward Process
-
Apple EpiCache: Episodic KV Cache Management for Long Conversations
By
–
Apple presents EpiCache Episodic KV Cache Management for Long Conversational Question Answering
-
OnePiece: Context Engineering and Reasoning in Cascade Ranking
By
–
OnePiece Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System
-
Qwen-Image-Edit-2509 Release: Multi-Image Editing Support
By
–
Qwen-Image-Edit-2509 is out Multi-image Editing Support: It supports various combinations such as "person + person," "person + product," and "person + scene." Optimal performance is currently achieved with 1 to 3 input images. Improved Person Editing Consistency: Better
-
DeepSeek-V3.1-Terminus Released on Hugging Face with Improvements
By
–
DeepSeek-V3.1-Terminus is out on Hugging Face
— AK (@_akhaliq) 22 septembre 2025
This update maintains the model's original capabilities while addressing issues reported by users, including:
Language consistency: Reducing instances of mixed Chinese-English text and occasional abnormal characters
Agent… pic.twitter.com/bw9AtNHFUrDeepSeek-V3.1-Terminus is out on Hugging Face This update maintains the model's original capabilities while addressing issues reported by users, including: Language consistency: Reducing instances of mixed Chinese-English text and occasional abnormal characters Agent
-
Wan2.2-Animate-14B Now Available in Anycoder
By
–
Wan2.2-Animate-14B is now available in anycoder pic.twitter.com/El9G6JHJPl
— AK (@_akhaliq) 20 septembre 2025Wan2.2-Animate-14B is now available in anycoder