AdinaY (Adina Yakefu)

posted an update 1 day ago

Post

399

LongWriter-Zero 🔥 A Purely RL trained LLM handles 10K+ token coherent passages by Tsinghua University

Model:
THU-KEG/LongWriter-Zero-32B
Dataset:
THU-KEG/LongWriter-Zero-RLData
Paper:
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning (2506.18841)

✨ 32B
✨ Multi-reward GRPO: length, fluency, structure, non-redundancy
✨ Enforces <think><answer> format via Format RM
✨ Build on Qwen2.5-32B-base

posted an update 1 day ago

Post

163

MOSS-TTSD 🔊 Bilingual text-to-spoken dialogue model by Fudan University - Open MOSS team.

Model:
fnlp/MOSS-TTSD-v0
Demo:
fnlp/MOSS-TTSD

✨ Supports Chinese & English
✨ Zero-shot 2-speaker voice cloning
✨ Long-form generation (up to 960s)
✨ Built on Qwen 3

posted an update 2 days ago

Post

199

Skywork-SWE 🔥 New code agent model by Skywork 天工

Skywork/Skywork-SWE-32B

✨ 32B - Apache 2.0
✨ 38.0% pass@1 on SWE-bench Verified
✨ Up to 47.0% with test-time scaling
✨ Shows clear data scaling law (8K+ demos)
✨ Built on Qwen2.5-Coder-32B + OpenHands

reacted to merve's post with 🚀🔥 3 days ago

Post

4903

fav open-source multimodal reasoning model just got an update 🔥

moonshotai/Kimi-VL-A3B-Thinking-2506 has
> smarter with less tokens, small size (only 3B active params!!!)
> better accuracy
> video reasoning
> higher resolution 🤯
Read their blog https://huggingface.co/blog/moonshotai/kimi-vl-a3b-thinking-2506

reacted to merve's post with ❤️ 7 days ago

Post

3558

Releases of the past week are here merve/releases-june-13-6852c3c1eaf1e0c24c958860

Here's our picks 🤓
So many interesting models released past week in open AI! 🤖

🖼️ Computer Vision/VLMs
> nanonets/Nanonets-OCR-s is the new state-of-the-art OCR model that can handle checkboxes, watermarks, tables (OS)
> Meta released facebook/v-jepa-2-6841bad8413014e185b497a6, new sota video embeddings with two new classification models (OS)
> ByteDance-Seed/SeedVR2-3B is a new 3B video restoration model (OS)

Audio
> Stepfun released stepfun-ai/Step-Audio-AQAA, new large (137B 🤯) audio language model that takes in audio and generates audio (OS)

🤖 Robotics
> nvidia released nvidia/GR00T-N1.5-3B, new open foundation vision language action model

3D
> tencent/Hunyuan3D-2.1 is the new version of Hunyuan by Tencent that can generate 3D assets from text and image prompts

posted an update 8 days ago

Post

1257

SongGeneration 🎵 A model by Tencent for vocal + accompaniment music generation.

Model:
tencent/SongGeneration
Demo:
https://huggingface.co/spaces/waytan22/SongGeneration-LeVo

✨ Mixed & dual-track token modeling
✨ Hi-fi music with custom codec
✨ Currently supports Chinese, English version coming soon!

posted an update 9 days ago

Post

4004

Kimi-Dev 💻 New coding model by Moonshot AI

moonshotai/Kimi-Dev-72B

✨ 72B - MIT license
✨ 60.4% on SWE-bench Verified
✨ RL-trained to patch real repos in Docker
✨ Only rewarded if full test suite passes

posted an update 9 days ago

Post

633

MiniMax-M1 🔥 The First reasoning model by MiniMax.

MiniMaxAI/minimax-m1-68502ad9634ec0eeac8cf094

✨ 40k/80k thinking budget
✨ Powered by Hybrid MoE + Lightning Attention 👀
✨ 1M context length 🤯
✨ Apache 2.0
✨ RL-trained for math, coding & real-world software

posted an update 10 days ago

Post

425

Hunyuan 3D 2.1 🔥 Industrial-grade 3D model just released by Tencent Hunyuan

tencent/Hunyuan3D-2.1
tencent/Hunyuan3D-2.1

✨ PBR materials: leather, bronze & more, breathtaking realism under any light
✨ Consumer GPU-ready: good for developers and small teams

reacted to yukiarimo's post with 🔥 14 days ago

Post

1342

Introducing Mizu UI (水). New UI elements, redesigned from the ground up across the entire Yuna Ai WebUI, will make your day better and your UX experience smoother! The beta has already arrived; the final version will be released this week!

Spoiler: Mizu UI will also come to the Yuki Story from next month!

Additionally:

- Circular import issue was fixed. Not sure if anything is working, but it can
- Hanasu suppport added, GPT-SoVITS-V2 removed from AiFlow

For more details check the git log or official community.

For you:

- Yuna Ai V4 Miru support is coming this week (yes, fr this time).
- Himitsu V1 Miru can arrive, but we need more support!

Thanks for being with us!

posted an update 15 days ago

Post

1588

Lingshu 🩺📖 medical MLLM released by DAMO Alibaba

lingshu-medical-mllm/lingshu-mllms-6847974ca5b5df750f017dad

✨ 7B/32B
✨ 12+ imaging modalities supported: X-Ray, CT, MRI, Microscopy +more
✨ Great performance on medical benchmark

posted an update 17 days ago

Post

3176

RoboBrain 2.0🔥 OPEN embedded brain model by BAAIBeijing

BAAI/RoboBrain2.0-7B

✨ 7B - Apache 2.0 / 32B coming soon
✨ Supports multiple images, long videos, and high-resolution visuals
✨ Spatial + temporal reasoning
✨ Real-time memory & scene graphs

posted an update 19 days ago

Post

2681

RedNote 小红书 just released their first LLM 🔥

dots.llm1.base 🪐 a 142B MoE model with only 14B active params.

rednote-hilab/dotsllm1-68246aaaaba3363374a8aa7c
✨ Base & Instruct - MIT license
✨ Trained on 11.2T non-synthetic high-quality data
✨ Competitive with Qwen2.5/3 on reasoning, code, alignment

posted an update 19 days ago

Post

450

MiniCPM4🔥 efficient LLMs built for end-side devices, by OpenBMB

openbmb/minicpm4-6841ab29d180257e940baa9b

✨ Apache 2.0
✨ 5–7× Faster Inference (Jetson Orin & RTX 4090)
✨ 8B trained on 8T clean, non-synthetic tokens
✨ 32K Native Context -> 128K+ with InfLLM v2 + LongRoPE
✨ Runs on 🤗Transformers , http://CPM.cu, vLLM, and SGLang

posted an update 20 days ago

Post

2024

New models from Qwen 🔥

Qwen3-Embedding and Qwen3-Reranker Series just released on the hub by
Alibaba Qwen team.

✨ 0.6B/ 4B/ 8B with Apache2.0
✨ Supports 119 languages 🤯
✨ Top-tier performance: Leading the MTEB multilingual leaderboard！

Reranker:
Qwen/qwen3-reranker-6841b22d0192d7ade9cdefea
Embedding:
Qwen/qwen3-embedding-6841b2055b99c44d9a4c371f

posted an update 21 days ago

Post

1613

OpenAudio S1-mini 🔊 a new OPEN multilingual TTS model trained on 2M+ hours of data, by FishAudio

fishaudio/openaudio-s1-mini

✨ Supports 14 languages
✨ 50+ emotions & tones
✨ RLHF-optimized
✨ Special effects: laughing, crying, shouting, etc.

1 reply

·

posted an update 22 days ago

Post

1020

AReaL-boba² 🔥 A fully async RL system by Ant Research & Tsinghua.

Paper: AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning (2505.24298)
Model:
inclusionAI/areal-boba-2-683f0e819ccb7bb2e1b2f2d5

✨ 8B/14B/32B models, datasets & paper – all on the hub
✨ 2.77× faster training
✨ Native Agentic RL support

reacted to merve's post with 🚀 22 days ago

Post

1404

Yesterday was the day of vision language action models (VLAs)!

> SmolVLA: open-source small VLA for robotics by Hugging Face LeRobot team 🤖
Blog: https://huggingface.co/blog/smolvla
Model: lerobot/smolvla_base

> Holo-1: 3B & 7B web/computer use agentic VLAs by H Company 💻
Model family: Hcompany/holo1-683dd1eece7eb077b96d0cbd
Demo: https://huggingface.co/spaces/multimodalart/Holo1
Blog: https://huggingface.co/blog/Hcompany/holo1
super exciting times!!

reacted to danaaubakirova's post with ❤️ 22 days ago

Post

2109

We just dropped SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics!

check out the blog: https://huggingface.co/blog/smolvla
read the technical report: SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics (2506.01844)
access the model weights: lerobot/smolvla_base

Adina Yakefu PRO

AI & ML interests

Recent Activity

Organizations

Adina Yakefu PRO

AI & ML interests

Recent Activity

Organizations

AdinaY's activity