
Min-Hung (Steve) Chen
@CMHungSteven
Followers
2K
Following
31K
Media
56
Statuses
725
Senior Research Scientist, NVR TW @NVIDIAAI @NVIDIA (Project Lead: DoRA, EoRA | Ph.D. @GeorgiaTech | Multimodal AI | https://t.co/dKaEzVoTfZ
Taipei City, Taiwan
Joined July 2011
(1/N).Are you looking for #Vision #Transformer papers in various areas? .Check out this list of papers including a broad range of different tasks!.Feel free to share with others😀.@Montreal_AI @machinelearnflx @hardmaru @ak92501 @arankomatsuzaki @omarsar0.
github.com
An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites - cmhungsteve/Awesome-Transformer-Attention
3
31
166
Super excited to share HERMES @ICCVConference — our video understanding framework that can boost accuracy, speed, and reduce memory! . Please check the original post from @JosmyFaure1 for more details!. website: #ICCV2025 #NVIDIA #LLM #Video #multimodal.
🚀 New at #ICCV2025: HERMES — a Video Understanding framework that’s both ⚡ efficient and 🎯 accurate. No more trade-off between speed and performance.
0
10
58
RT @JosmyFaure1: 🚀 New at #ICCV2025: HERMES — a Video Understanding framework that’s both ⚡ efficient and 🎯 accurate. No more trade-off bet….
0
2
0
RT @chen_yiting_TW: 📣 Call for Submissions - X-Sense Workshop #ICCV2025!. Let's accelerate Ego-Exo Sensing for cleaner, safer, and more eff….
0
6
0
Thanks @_akhaliq for sharing our latest VLA Reasoning work!. Please see more details here: @NVIDIAAIDev @NVIDIAAI @nvidia .#NVIDIA #NVIDIAResearch #VLA #reasoning #RL.
0
17
70
RT @FuEnYang1: 🤖 How can we teach embodied agents to think before they act?. 🚀 Introducing ThinkAct — a hierarchical Reasoning VLA framewor….
0
26
0
RT @_akhaliq: Nvidia presents ThinkAct. Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
0
120
0
RT @NVIDIAAIDev: Compressing LLMs but worried about accuracy? 🎯. New from #NVIDIAResearch: EoRA uses eigenspace low-rank approximation to c….
0
21
0
📣 Call for Submissions - X-Sense Workshop @ICCVConference ! .📅 Deadline: August 31, 2025 09:59 AM GMT .📝 Submission Portal: 🌐 More info: #ICCV2025 #ICCV #ICCV25.
openreview.net
Welcome to the OpenReview homepage for ICCV 2025 Workshop X-Sense
📢 Excited to share the first X-Sense Workshop: Ego-Exo Sensing for Smart Mobility at @ICCVConference with outstanding speakers!! .Please stay tuned for the Call for Papers.#ICCV2025 #ICCV #ICCV25
0
3
14
RT @chen_yiting_TW: 📣 Call for Submissions - X-Sense Workshop #ICCV2025!. Let's accelerate Ego-Exo Sensing for cleaner, safer, and more eff….
lnkd.in
This link will take you to a page that’s not on LinkedIn
0
7
0
RT @thammadou: NVIDIA’s EoRA Makes LLM Compression Lightning Fast⚡. The AI community just got a major breakthrough! NVIDIA Research has unv….
0
2
0
RT @PavloMolchanov: 🚨 Announcing data filtering challenge with $28,000 in prizes!. Announcing the Data Filtering Challenge for Finetuning E….
0
7
0
Please come visit our #AuraFusion360 poster @CVPR tomorrow!!. 📅 Date: Saturday, June 14 | 🕣 Time: 17:00 - 19:00 (Poster Session 4). 📍 Location: ExHall D, Poster #50. @NVIDIAAIDev @NVIDIAAI.#CVPR2025 #CVPR #Nvidia #nvidiaresearch #AI #CV #GenerativeAI #3D #diffusion #NYCU.
Thanks @janusch_patas for sharing!.🎉 AuraFusion got accepted to @CVPR 2025! 🎉 .Huge congrats to the team! . [🌐 Website] [📝 Paper] #CVPR2025 #CVPR #Nvidia #nvidiaresearch #AI #CV #GenerativeAI #3D #diffusion.
0
0
4
RT @ZhidingYu: Come to the T4V Workshop this Thursday (June 12th) and check the latest development in Transformers!.
0
2
0
RT @gberta227: Join us for the 4th iteration of Transformers for Vision (T4V) workshop on Thursday!.
0
4
0
RT @CMHungSteven: @CVPR is around the corner!!.Join us at the Workshop on T4V at #CVPR2025 with a great speaker lineup (@MikeShou1, @jw2yan….
0
19
0
Kudos to our great organization team: @gberta227, @_rohitgirdhar_, @ZhidingYu, @giffmana, @gulvarol, @mohitban47, @ALVAREZ_JOSEM, @tyleryzhu, @alaa_nouby, @mmiemon, and others!.#NVIDIAResearch #NVIDIA #UNC #MetaAI #GoogleDeepMind #ParisTech #AppleResearch.#AI #CV #MachineLearning.
0
0
3