HuggingFace Trending Models & Daily Papers

HuggingFace Trending Models (May 25-26, 2026)

• tencent/Hy-MT2-1.8B | ⭐964 | translation | Downloads: 7471
• bytedance-research/Lance | ⭐836 | any-to-any | Downloads: 1908
• tencent/Hy-MT2-30B-A3B | ⭐385 | translation | Downloads: 2091
• NemoStation/Marlin-2B | ⭐352 | video-text-to-text | Downloads: 9144
• sapientinc/HRM-Text-1B | ⭐353 | text-generation | Downloads: 103033
• meituan-longcat/LongCat-Video-Avatar-1.5 | ⭐253 | ? | Downloads: 0
• Supertone/supertonic-3 | ⭐681 | text-to-speech | Downloads: 48112
• openbmb/MiniCPM5-1B | ⭐265 | text-generation | Downloads: 2409
• CohereLabs/command-a-plus-05-2026-w4a4 | ⭐203 | image-text-to-text | Downloads: 7769
• HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive | ⭐882 | image-text-to-text | Downloads: 1598473
• SulphurAI/Sulphur-2-base | ⭐1358 | text-to-video | Downloads: 1376847
• openbmb/MiniCPM-V-4.6 | ⭐978 | image-text-to-text | Downloads: 314347

Notable Releases

• tencent/Hy-MT2-1.8B - Tencent's latest translation model, trending #1
• bytedance-research/Lance - ByteDance's any-to-any multimodal model
• Supertone/supertonic-3 - Text-to-speech model with 48K downloads
• openbmb/MiniCPM-V-4.6 - Latest MiniCPM multimodal model with 314K downloads
• SulphurAI/Sulphur-2-base - Text-to-video model, 1.3M downloads
• CohereLabs/command-a-plus-05-2026-w4a4 - Cohere's quantized Command-A+

HF Daily Papers (May 25)

• SkillOpt: Executive Strategy for Self-Evolving Agent Skills -
• Rethinking Cross-Layer Information Routing in Diffusion Transformers -
• Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models -
• SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research -
• StepAudio 2.5 Technical Report -
• See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding -
• PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion -
• From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills -