Yichen Sheng @Coding_Black
Research scientist in NVIDIA. Working in graphics and vision. Opinions are my own. shengcn.github.io West Lafayette, IN Joined July 2015-
Tweets129
-
Followers276
-
Following1K
-
Likes690
🚀🚀🚀
One of our roles in LLM/VLM research at NVIDIA is to explore effective data recipes for training large-scale models and share them to the public—an area where transparency has been limited, as seen with models like Gemini, GPT-4o, Qwen-VL models etc. The Eagle2 project aligns…
One of our roles in LLM/VLM research at NVIDIA is to explore effective data recipes for training large-scale models and share them to the public—an area where transparency has been limited, as seen with models like Gemini, GPT-4o, Qwen-VL models etc. The Eagle2 project aligns…
@CVPR2025 Wei Xiong and I will host a coffee chat session(11. 30~12. 30) in Room211 for Nvidia university hiring. Feel free to come and say hi if you are interested in DLSS and next generation generative rendering. linkedin.com/posts/nvidia-u…
Congrats to "VGGT" wins the best paper award at #CVPR2025 ! We are happy that #DL3DV benefits "VGGT" and the community. We will host the #DL3DV Demo session this afternoon from 4:00-6:00 pm. Come by and see what is the new in DL3DV!
🚀 We just open-sourced Cosmos DiffusionRenderer! This major upgrade brings significantly improved video de-lighting and re-lighting—powered by NVIDIA Cosmos and enhanced data curation. Released under Apache 2.0 and Open Model License. Try it out! 🔗 github.com/nv-tlabs/cosmo…
🚀 We just open-sourced Cosmos DiffusionRenderer! This major upgrade brings significantly improved video de-lighting and re-lighting—powered by NVIDIA Cosmos and enhanced data curation. Released under Apache 2.0 and Open Model License. Try it out! 🔗 github.com/nv-tlabs/cosmo… https://t.co/xInzadtz5T
Vision Language Models can be amazing at document understanding. Please check out our Nano sized model. More to come!
Vision Language Models can be amazing at document understanding. Please check out our Nano sized model. More to come!
Generative photography is our new physics-based camera-aware image generation tool. To appear @CVPR 2025 (Highlight paper 13.5%) arxiv.org/abs/2412.02168 - Respect camera controls - Photorealistic generation Credits to Yu Yuan @PurdueECE
Introducing AceMath-RL-Nemotron-7B, an open math model trained with reinforcement learning from the SFT-only checkpoint: Deepseek-R1-Distilled-Qwen-7B. It achieves: - AIME24: 69.0 (+13.5 gain by RL) - AIME25: 53.6 (+14.4) - LiveCodeBench: 44.4 (surprisingly, +6.8 gain after…
Eagle2.5 natively supports long-context without using any compression module. Eagle2.5-8B has: • got 6 out of 10 SOTA on long video benchmarks • beat GPT-4o (0806) on 3/5 video tasks • beat Gemini 1.5 Pro on 4/6 video tasks • got SOTA result on Hour-long video benchmark.
Eagle2.5 natively supports long-context without using any compression module. Eagle2.5-8B has: • got 6 out of 10 SOTA on long video benchmarks • beat GPT-4o (0806) on 3/5 video tasks • beat Gemini 1.5 Pro on 4/6 video tasks • got SOTA result on Hour-long video benchmark.
A friend's well-funded stealth photography-AI startup is hiring GenAI and multimodal engineers (full-stack welcome). They're a small, highly technical team of top-shelf AI researchers who are rethinking pro-quality photography. DM me if you're interested in talking to them.
A long time ago, back before DLSS was in many games (and when my hair was shorter and less gray), I went to Nintendo HQ to show them an early prototype of DLSS 2, in the hopes that a future Switch console would use DLSS. I'm so proud that the Switch 2 will be DLSS powered!…
Even though we haven't been publishing papers around DLSS, it takes a tremendous amount of hardcore research to bring AI models like DLSS4 into production. Super happy that we're sharing technical insights on DLSS4 in this report. So proud of the teams!
Even though we haven't been publishing papers around DLSS, it takes a tremendous amount of hardcore research to bring AI models like DLSS4 into production. Super happy that we're sharing technical insights on DLSS4 in this report. So proud of the teams!
Tired of slow diffusion models? Our new paper introduces f-distill, enabling arbitrary f-divergence for one-step diffusion distillation. JS divergence gives SOTA results on text-to-image! Choose the divergence that suits your needs. Joint work with @wn8_nie @ArashVahdat 1/N
github.com/NVIDIA/Cosmos Cosmos is a developer-first platform designed to help physical AI builders accelerate their development. It has pre-trained world foundation models (diffusion & autoregressive) in different sizes and video tokenizers. They are open models with permissive…
Big Congratulations to our team! We firmly believe AI will shape the future of the graphics. If you are also passionate and want to make a history, please join us!
Big Congratulations to our team! We firmly believe AI will shape the future of the graphics. If you are also passionate and want to make a history, please join us!
Our team at NVIDIA is continuously looking for highly motivated interns to work on intelligence in audio understanding and synthesis. Please reach out if you would like to collaborate with us!
We equip the diffusion model with a camera lens feature. You will feel safe when you *just* want to edit the focal length/shutter/bokeh/color temperature as the contents are preserved . Arxiv: arxiv.org/abs/2412.02168
We equip the diffusion model with a camera lens feature. You will feel safe when you *just* want to edit the focal length/shutter/bokeh/color temperature as the contents are preserved . Arxiv: arxiv.org/abs/2412.02168
📢Please check out our newest work on feed-forward reconstruction of dynamic monocular videos! With our bullet-time formulation, we reach great flexibility and state-of-the-art performance!
📢Please check out our newest work on feed-forward reconstruction of dynamic monocular videos! With our bullet-time formulation, we reach great flexibility and state-of-the-art performance!

Rhuiawbar @Rhuiawbar76596
13 Followers 2K Following
ElsieGarden @jj0rGL9B2B80u
10 Followers 694 Following
RockyParadox @RockyParadox44
130 Followers 7K Following
dadsfa @dadsfa344763
1 Followers 82 Following
HeddaWheeler @tArfzPC0d3IkchU
1 Followers 262 Following
Saber Darabi @SADarabi
308 Followers 8K Following
Avise @Avise655
29 Followers 1K Following
Lifan Wu @winmad4869
144 Followers 605 Following
Mary Zhao @MaryZ12358
1 Followers 6 Following
Rundi Wu @ChrisWu6080
682 Followers 305 Following Research Scientist @GoogleDeepMind | prev CS PhD @Columbia
Austen Johnston @JohnstonAu64082
33 Followers 2K Following
Emodor @Emodor703
28 Followers 2K Following
Longhui Yu @scut_longhui
988 Followers 1K Following Post-training in KIMI @Kimi_Moonshot | MS Peking University @PKU1898 Author of MetaMath, Easy2hard generalization, NuminaMath, Kimi k1.5, Kimi K2
JK @random_kida_92
2 Followers 123 Following
Unidentified Thinking... @whatiamlearning
56 Followers 232 Following Observing humans. Logging insights. Sharing what sticks—from books, thinkers, and this curious thing they call life.
Jaehoon Choi @jaehoon9301
43 Followers 229 Following CS Ph.D. student at University of Maryland, College Park
Xuanchi Ren @xuanchi13
756 Followers 413 Following PhD student @UofTCompSci. Research Scientist @NVIDIAAI. Working on computer vision and machine learning
McNasmue @McNasmue2IvPlY
73 Followers 3K Following
Antonio Villalon @agvillalons
96 Followers 330 Following
alexander @mcneiilly
5K Followers 577 Following
DoreenAndrew @893590U6A6iq88M
69 Followers 3K Following
Uipiugu @Uipiugu4668328
32 Followers 2K Following
Arash Vahdat @ArashVahdat
10K Followers 877 Following Research Director, leading fundamental generative AI research (GenAIR) @nvidia research, views are my own.
Phyllis Schoen @SchoenPhyl31472
26 Followers 2K Following
Edi Rumano @goeulers
80 Followers 366 Following That's me on the left. Founder, building @Corporare3D. Going from it to bit and back again.
Gpbhupinder @gpbhupinder
471 Followers 7K Following 👨💻 Full-Stack Developer & AI Integration Expert 🚀 From concept to launch, we bring your tech vision to life
Ariana Bermúdez @bermudezari
46 Followers 80 Following
Jieneng Chen @jieneng_chen
395 Followers 687 Following researcher #vision #ai #worldmodels PHD student @JohnsHopkins | selected @SiebelScholars 2025
Lucy @Lucy07286111291
409 Followers 6K Following
Yue Chen @faneggchen
286 Followers 236 Following PhD Student @Westlake_Uni. 3D/4D Reconstruction, Virtual Humans. Muggle dreaming of the Wizarding World
Wenjian Zhou @PIRATE2931
30 Followers 230 Following Rendering engineer at Booming Tech. Opinions are my own.
Wanhua Li @Wanhua_Ethan_Li
85 Followers 77 Following Computer Vision Researcher, Postdoc at Harvard. PhD @Tsinghua_Uni
Milos Hasan @MilosHasan
77 Followers 283 Following
Ali S @AliS1535131
0 Followers 47 Following
Lee @Li20201018
14 Followers 98 Following I don't log on to Twitter often, add my telegram if you need something: https://t.co/VdVOSuTsaW
Conference on Parsimo... @CPALconf
914 Followers 1K Following CPAL is a new annual research conference focused on the parsimonious, low dimensional structures that prevail in ML, signal processing, optimization, and beyond
Thijs Bergkamp @ThijsBergkamp
80 Followers 7K Following
Jie Fu @bigaidream
971 Followers 691 Following Working on autoformalization, building friendly AI to augment and flourish humanity; Prev. postdoc with Yoshua Bengio @Mila_Quebec | PhD @NUSingapore
Shao-Yuan Lo @shaoyuanlo
247 Followers 198 Following Assistant Professor @NTU_TW | PhD @JohnsHopkins | Trustworthy AI, Machine Learning, Multimodal Models
Bleseet @BleseetaSq
45 Followers 4K Following
Sam @samsenliu
25 Followers 290 Following
Daniel Sungho Jung @dqj5182
652 Followers 2K Following PhD in Artificial Intelligence @SeoulNatlUni • BS @PSUScience • Prev Intern @Sony & @kaistpr
Tongyi Lab @Ali_TongyiLab
9K Followers 20 Following We advance the development of AGI and foster open source collaboration towards a smarter future.
Jacob Effron @jacobeffron
3K Followers 629 Following Managing Director @redpoint supporting @AbridgeHQ @ideogram_ai @tryramp @poolsideai @AcuityMD @scribehow @wearelegora @getgarner / AI pod: Unsupervised Learning
Nicole Brichtova @nbrichtova
2K Followers 55 Following I lead product for image generation at Google DeepMind (Gemini / nano banana, Imagen). Opinions are my own.
Gengshan Yang @gengshanY
504 Followers 198 Following 3D computer vision, inverse rendering/physics/control, animals
Elizabeth Holmes @ElizabethHolmes
54K Followers 77 Following Building a better world for my two children. Inventor. Former Theranos Founder and CEO Mostly my words, posted by others
Jiantao Jiao @JiantaoJ
2K Followers 125 Following Director of Research & Distinguished Scientist at @NVIDIA, Professor at UC Berkeley EECS and Statistics. Building AGI/ASI
NVIDIA GeForce @NVIDIAGeForce
3.0M Followers 963 Following Introducing GeForce RTX 50 Series graphics cards & laptops, powered by NVIDIA Blackwell and AI.
Philipp Henzler @philipphenzler
1K Followers 713 Following Research Scientist @ Google | Generative video models (Veo) / 3D. PhD from UCL
Dynamics Lab @DynamicsLab_AI
5K Followers 166 Following An applied research company building at the frontier of AI
Black Myth @BlackMythGame
221K Followers 5 Following The only official account for the Black Myth series.
Katja Schwarz @K_S_Schwarz
2K Followers 422 Following Generative modeling in 2D and 3D @spAItial_AI. Ex-Meta AI Researcher. Previously PhD at Autonomous Vision Group in Tübingen.
Jacob Austin @jacobaustin132
7K Followers 920 Following Research at @GoogleDeepMind. Currently making LLMs go fast. I also play piano and climb. NYC. Opinions my own
clem 🤗 @ClementDelangue
157K Followers 5K Following Co-founder & CEO @HuggingFace 🤗, the open and collaborative platform for AI builders
Francisco Massa @fvsmassa
4K Followers 12 Following Research Engineer at Facebook AI Research working on PyTorch.
Yoko @stuffyokodraws
10K Followers 2K Following Cartoonist, Engineer, PM, Partner @a16z investing in infra & AI Prev Product lead @HashiCorp, Founding Eng/PM @Transposit. Eng @AppDynamics. Opinions = own.
Igor Babuschkin @ibab
103K Followers 856 Following Maybe the real ASI was the friends we made along the way. Co-founder @xAI, Research & Engineering
Federico Baldassarre @BaldassarreFe
1K Followers 452 Following Postdoctoral Researcher @AIatMeta: DINOv3 and world models. PhD @kth_rpl: deep learning explainability, concept-based visual representations and reasoning.
Hugging Face @huggingface
567K Followers 210 Following The AI community building the future. https://t.co/VkRPD0Vclr
Rundi Wu @ChrisWu6080
682 Followers 305 Following Research Scientist @GoogleDeepMind | prev CS PhD @Columbia
Joe Ortiz @joeaortiz
968 Followers 812 Following @GoogleDeepMind researching robot perception | Ex @AIatMeta (FAIR), PhD @imperialcollege
Zhuohan Li @zhuohan123
9K Followers 866 Following mts @ openai | cs phd @ 🌁 uc berkeley | building @vllm_project | machine learning system | the real agi is the friends we made along the way
Paul Millerd @p_millerd
34K Followers 4K Following Good Work: https://t.co/U8LTNPklcl Pathless Path: https://t.co/b4ARw5qd8H Community: https://t.co/vaLzoFYrMq 👉 https://t.co/WYFNJogPkF
Ken Liu @kyliu99
35K Followers 111 Following SFF author, speaker, lawyer, programmer; Hugo, Nebula, World Fantasy; rep by Russ Galen; The Dandelion Dynasty & “The Paper Menagerie"
Richard Sutton @RichardSSutton
52K Followers 64 Following Student of mind and nature, libertarian, chess player, cancer survivor. @ Keen, UAlberta, Amii, https://t.co/u8za2Kod54, The Royal Society, Turing Award
Shuangfei Zhai @zhaisf
2K Followers 97 Following Research Scientist & Manager, Machine Learning Research @ Apple
Prem Qu Nair @premqnair
5K Followers 932 Following @cognition, previously @nuro @princeton. Pursuing 70mm, 225lb, and $0.10/piece
Ethan He @EthanHe_42
17K Followers 841 Following AI @xai | prev @nvidia @AIatMeta @CarnegieMellon | 8k citations 5k GitHub stars | views are my own
Ludwig Schmidt @lschmidt3
6K Followers 424 Following Assistant professor at @Stanford and member of the technical staff at @AnthropicAI.
Yejin Choi @YejinChoinka
25K Followers 404 Following professor at Stanford, researcher at NVIDIA, adventurer at heart
Mira Murati @miramurati
371K Followers 574 Following Now building @thinkymachines. Previously CTO @OpenAI
Longhui Yu @scut_longhui
988 Followers 1K Following Post-training in KIMI @Kimi_Moonshot | MS Peking University @PKU1898 Author of MetaMath, Easy2hard generalization, NuminaMath, Kimi k1.5, Kimi K2
Yulun Du @Yulun_Du
2K Followers 757 Following Scaling @Kimi_Moonshot prev @LTIatCMU Opinions are my own.
Tianfan Xue @tianfanx
119 Followers 86 Following
Ali Hassani @AliHassaniJr
455 Followers 57 Following Computer Science PhD Student at Georgia Tech. I like fast computers. I like AI. I love the combination.
Banghua Zhu @BanghuaZ
7K Followers 1K Following Assistant Professor @UW, Principal Research Scientist @Nvidia. Prior Cofounder @NexusflowX, @Berkeley_EECS @Google @Microsoft. I work on LLMs.
Alexandr Wang @alexandr_wang
333K Followers 838 Following chief ai officer @meta, founder @scale_ai. rational in the fullness of time
Trapit Bansal @TrapitBansal
32K Followers 250 Following AI Research @Meta | Co-Creator of OpenAI o1 | Previously @OpenAI, @MSFTResearch, @GoogleAI, @facebook, @iiscbangalore, and undergrad @IITKanpur
Manling Li @ManlingLi_
8K Followers 760 Following Assistant Professor@NU, Amazon Scholar, Postdoc@Stanford, PhD@UIUC #NLP #CV Language+Vision/EmbodiedAI, Reasoning, Planning, Compositionality, Trustworthiness
Starlink @Starlink
1.4M Followers 29 Following Internet from space for humans on Earth. Engineered by @SpaceX
Michelle Qin @michelleqin_
13K Followers 639 Following Engineer, Multimodal @OpenAI. CS @Stanford. I care about people, AI, & design for play 🤸♀️
Xiaohua Zhai @XiaohuaZhai
11K Followers 311 Following Researcher at Meta (previously at OpenAI Zürich, Google DeepMind)
Google Research @GoogleResearch
23K Followers 6 Following Impossible? Let’s see. From algorithms to neuroscience to AI, Google Research strives to progress science, advance society & improve billions of people’s lives.