#ChuYan
LightNews LightNews
kateinkharkiv.bsky.social
​😭🕯 Veronika Chuyan, a 29-year-old mother, was killed yesterday during the Russian attack on Kyiv. She was running to a bomb shelter, desperately trying to get her children to safety.

​She was trying to save her two little boys, aged 5 and nearly 3.
June 3, 2026 at 11:43 AM
meanwhileua.bsky.social
Veronika Chuyan, 29, was running to a bomb shelter with her two boys when a Russian missile killed her.

Son aged 5: emergency surgery. Son aged 3: bruises.
Two boys. No mother.

Support link is in our Bio
June 3, 2026 at 10:19 PM
united24media.com
🕯️ A massive Russian overnight missile strike on Kyiv on June 2 claimed the life of Veronika Chuyan, a young mother of two.

A Russian missile hit directly near Veronika while she was running to a shelter with her sons, aged 5 and 3.
June 3, 2026 at 9:43 AM
ukbastard.bsky.social
The mother who gave her life to save her sons from Russian missiles
Veronika Chuyan threw her body over her two boys as shrapnel from a double-tap strike flew towards them in Kyiv

archive.fo/F0AGX
June 14, 2026 at 2:14 PM
faredalmahlool.bsky.social
A massive Russian overnight missile strike on Kyiv on June 2 claimed the life of Veronika Chuyan, a young mother of two.

A Russian missile hit directly near Veronika while she was running to a shelter with her sons, aged 5 and 3.
June 5, 2026 at 4:56 PM
numcog.bsky.social
New review paper by the brilliant Dr. Chuyan Qu & myself on the development of place value understanding: doi.org/10.1177/0963...
Sage Journals: Discover world-class research
Subscription and open access journals from Sage, the world's leading independent academic publisher.
doi.org
March 18, 2026 at 7:13 PM
intelarchive.io
New addition

Journal article: International Law Analysis of Espionage at Sea and China's Response by Chuyan Liu (published 14-05-2025)

https://ijsspa.org/index.php/ojs/article/view/82
ijsspa.org
June 11, 2025 at 8:16 PM
regardcritique.bsky.social
L'un des plus importants cinéastes de la Shaw Brothers et un véritable maitre du film de sabre chinois.

Le test du coffret Bluray : regard-critique.fr/home-cinema/...

#Bluray #coffret #ChuYan #ShawBrothers #wuxiapian #ArtsMartiaux #TiLung #LoLieh #LiChing #DerekYee @SpectrumFilms
January 15, 2026 at 3:15 PM
dailymail.co.uk
Ukrainian mother, 28, dies after shielding her two sons as shrapnel from a Russian missile hurtled towards them trib.al/DcOef53
Ukrainian mother dies after shielding her sons from Russian missile
Veronika Chuyan, 28, died just yards from safety after a second missile hit a residential district of the Ukrainian capital during a wave of intensified Russian attacks.
www.dailymail.com
June 14, 2026 at 10:10 AM
optb0t.bsky.social
🔄 Updated Arxiv Paper

Title: Subspace Optimization for Large Language Models with Convergence Guarantees
Authors: Yutong He, Pengrui Li, Yipeng Hu, Chuyan Chen, Kun Yuan

Read more: https://arxiv.org/abs/2410.11289
June 5, 2025 at 8:15 AM
lmnash123.bsky.social
Condemn multiple things? You haven't condemned anything here.

You posted about Caolan's past, not about whether Irish alumina helped build the missile that killed Veronika Chuyan yesterday.

That speaks to your priorities
June 4, 2026 at 8:18 AM
paper.bsky.social
[11/30] 502 Likes, 60 Comments, 2 Posts
2609.03796, cs․CV | cs․AI, 03 Sep 2026

🆕LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

Chuyan Chen, Haoxing Chen, Kun Chen, Zhenglin Cheng, Long Cui, Ruishan Fang, Zhangxuan Gu, Zhicheng Huang, Zhenzhong Lan, Yuanting Le...
We introduce LLaDA-Image, a unified framework that pairs a 6B Diffusion Transformer (DiT) trained from scratch with a frozen vision-language understanding module built on the LLaDA2.0-Mini diffusion language model backbone. Instead of relying heavily on paired image-text data from the beginning, we first build a strong visual generative prior through image-only pre-training and mid-training. The generation pipeline comprises 220M samples, 98 of which are real images. For efficient and scalable optimization, we use parameter-free RMSNorm throughout the DiT together with the Muon optimizer. The resulting unified model produces highly photorealistic images while accurately following fine-grained editing instructions. We further distill LLaDA-Image into LLaDA-Image-Turbo, enabling fast inference in 2-4 sampling steps. On Qwen-Image-Bench, LLaDA-Image achieves overall scores of 53.53 and 53.38 on the English and Chinese tracks, respectively, setting a new state-of-the-art among open-source models on both tracks. To support further research on capable and efficient generative models, we release our model weights, training code, and detailed recipes.
September 8, 2026 at 12:10 AM
nanoatp.bsky.social
[28/30] 247 Upvotes, 3 Comments, 2 Posts, arXiv:2609.03796

🆕LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

Chuyan Chen, Haoxing Chen, Kun Chen, Zhenglin Cheng, Long Cui, Ruishan Fang
We introduce LLaDA-Image, a unified framework that pairs a 6B Diffusion Transformer (DiT) trained from scratch with a frozen vision-language understanding module built on the LLaDA2.0-Mini diffusion language model backbone. Instead of relying heavily on paired image-text data from the beginning, we first build a strong visual generative prior through image-only pre-training and mid-training. The generation pipeline comprises 220M samples, 98 of which are real images. For efficient and scalable optimization, we use parameter-free RMSNorm throughout the DiT together with the Muon optimizer. The resulting unified model produces highly photorealistic images while accurately following fine-grained editing instructions. We further distill LLaDA-Image into LLaDA-Image-Turbo, enabling fast inference in 2-4 sampling steps. On Qwen-Image-Bench, LLaDA-Image achieves overall scores of 53.53 and 53.38 on the English and Chinese tracks, respectively, setting a new state-of-the-art among open-source models on both tracks. To support further research on capable and efficient generative models, we release our model weights, training code, and detailed recipes.
September 7, 2026 at 12:04 AM
nanoatp.bsky.social
[29/30] 236 Upvotes, 3 Comments, 2 Posts, arXiv:2609.03796

🆕LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

Chuyan Chen, Haoxing Chen, Kun Chen, Zhenglin Cheng, Long Cui, Ruishan Fang
We introduce LLaDA-Image, a unified framework that pairs a 6B Diffusion Transformer (DiT) trained from scratch with a frozen vision-language understanding module built on the LLaDA2.0-Mini diffusion language model backbone. Instead of relying heavily on paired image-text data from the beginning, we first build a strong visual generative prior through image-only pre-training and mid-training. The generation pipeline comprises 220M samples, 98 of which are real images. For efficient and scalable optimization, we use parameter-free RMSNorm throughout the DiT together with the Muon optimizer. The resulting unified model produces highly photorealistic images while accurately following fine-grained editing instructions. We further distill LLaDA-Image into LLaDA-Image-Turbo, enabling fast inference in 2-4 sampling steps. On Qwen-Image-Bench, LLaDA-Image achieves overall scores of 53.53 and 53.38 on the English and Chinese tracks, respectively, setting a new state-of-the-art among open-source models on both tracks. To support further research on capable and efficient generative models, we release our model weights, training code, and detailed recipes.
September 6, 2026 at 12:05 AM
arxiv-cs-cv.bsky.social
Chuyan Chen, Haoxing Chen, Kun Chen, Zhenglin Cheng, Long Cui, Ruishan Fang, Zhangxuan Gu, Zhicheng Huang, Zhenzhong Lan, Yuanting Lei, Haoquan Li, Jianguo Li, ...
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes
https://arxiv.org/abs/2609.03796
September 4, 2026 at 7:29 PM
cscv-bot.bsky.social
Chuyan Chen, et al.: LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes https://arxiv.org/abs/2609.03796 https://arxiv.org/pdf/2609.03796 https://arxiv.org/html/2609.03796
September 4, 2026 at 6:40 AM
csai-bot.bsky.social
Chuyan Chen, Peng Sun, Kun Yuan: CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum Orthogonalization https://arxiv.org/abs/2608.02502 https://arxiv.org/pdf/2608.02502 https://arxiv.org/html/2608.02502
August 5, 2026 at 6:42 AM
csai-bot.bsky.social
Chuyan Chen, Peng Sun, Kun Yuan: CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum Orthogonalization https://arxiv.org/abs/2608.02502 https://arxiv.org/pdf/2608.02502 https://arxiv.org/html/2608.02502
August 4, 2026 at 6:42 AM
arxiv-cs-cv.bsky.social
Tianren Ma, Lin Long, Chuyan Chen, Mu Zhang, Junbo Zhao, Tong Zhang, Qixiang Ye
dRAE: Representation Autoencoder with Hyper-Spherical Codes
https://arxiv.org/abs/2607.22148
July 28, 2026 at 2:09 AM
cscv-bot.bsky.social
Tianren Ma, Lin Long, Chuyan Chen, Mu Zhang, Junbo Zhao, Tong Zhang, Qixiang Ye: dRAE: Representation Autoencoder with Hyper-Spherical Codes https://arxiv.org/abs/2607.22148 https://arxiv.org/pdf/2607.22148 https://arxiv.org/html/2607.22148
July 27, 2026 at 6:40 AM
terpsichorecmlos.bsky.social
x.com/telegraph/st...
The Telegraph (@Telegraph) on X
Veronika Chuyan threw her body over her two boys as shrapnel from a double-tap strike flew towards them in Kyiv.⁠ ⁠ Veronika is one of thousands of Ukrainian civilians killed in Russia’s relentless bo...
x.com
June 14, 2026 at 5:36 PM
timmyfromtheblock.bsky.social
chuyan liu, marizabeth perez, emmanuel antwe-adjei, and ryan sangston present short blast talks. go see their posters tonight! #dros19
December 4, 2024 at 9:21 PM
arxiv-cs-ro.bsky.social
Hongyu Wang, Chuyan Xiong, Ruiping Wang, Xilin Chen
BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation
https://arxiv.org/abs/2506.07530
June 10, 2025 at 5:37 AM
arxiv-cs-ro.bsky.social
Mingxu Zhang, Xiaoqi Li, Jiahui Xu, Kaichen Zhou, Hojin Bae, Yan Shen, Chuyan Xiong, Jiaming Liu, Hao Dong
SR3D: Unleashing Single-view 3D Reconstruction for Transparent and Specular Object Grasping
https://arxiv.org/abs/2505.24305
June 2, 2025 at 5:56 AM
arxiv-cs-ro.bsky.social
Chuyan Xiong, Chengyu Shen, Xiaoqi Li, Kaichen Zhou, Jiaming Liu, Ruiping Wang, Hao Dong
AIC MLLM: Autonomous Interactive Correction MLLM for Robust Robotic Manipulation
https://arxiv.org/abs/2406.11548
October 16, 2024 at 8:30 AM