(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! https://t.co/kMThHeO7Gg Feel free to share with others😀 @Montreal_AI @machinelearnflx @hardmaru @ak92501 @arankomatsuzaki @omarsar0

🎬 ICCV'25 just wrapped and we're rolling into EMNLP'25! Our paper "MovieCORE: Cognitive Reasoning in Movies" was accepted as an Oral presentation 🚀 #EMNLP2025 #NLP #ComputerVision #VideoUnderstanding #VisionLanguageModels #AI #MachineLearning #DeepLearning #VLM #LLM

We, at NVIDIA, presents - Length Penalty Done Right - Cut CoT length by 3/4 without sacrificing accuracy using only RL - This makes DeepSeek-R1-7B running ~8 times faster on AIME-24 while maintaining the same accuracy.

Welcome to the workshop at ICCV. In the afternoon session, I will give a talk of our effort towards learning physical AI for sidewalk autonomy.

📣 Join us for the ICCV’25 X-Sense Workshop at Hawai'i Convention Center @ Room 323C on Monday, Oct. 20!! Link: https://t.co/FV7wCU92sY

If you're at #ICCV2025, Hawaii, make sure to drop by the X-Sense workshop at Hawai'i Convention Center @ Room 323C on Monday, Oct. 20. Join us for a discussion on the future of x-modal sensing! 📸📍 Link:

#ICCV2025 is around the corner! Don't hesitate to visit @HsukuangChiu's V2V-GoT poster @ X-Sense Workshop to learn our latest LLM-based Cooperative Driving work! Workshop: https://t.co/WaIl0uuJij V2V-GoT: https://t.co/u9tFpmoxuB @ICCVConference #V2V #LLM #iccv25 #NVIDIA #CMU

Excited to have a poster presentation for our latest research V2V-GoT at #ICCV2025 X-Sense Workshop! 🗓 Date & Time: Oct 20th, Monday, 11:40am ~ 12:30pm 📍 Location: Exhibition Hall II (No 188 ~ 210) 🌐 Paper, code, and dataset: https://t.co/GTnWrShw80 #NVIDIA #CMU

#ICCV2025 is around the corner! Don't hesitate to visit @JosmyFaure1's HERMES poster to learn our latest efficient video understanding work! 🌐 Website: https://t.co/LFQgh9mbfC

🎉 Excited for #ICCV2025! We’ll present HERMES, our cognitive-inspired framework that makes video models both faster and smarter. 📍 Poster Session: 🗓️ Thu. 23 Oct. 🕓 11:15 AM - 1:15 PM local time 📌 Honolulu Convention Center, Exhibit Hall I #2114

(1/6) I built KohakuHub — a fully self-hosted HF alternative, with HF compatibility and a familiar experience 🧠Host your own data, Keep your workflow Check more information in the repository and our community! 🔗 https://t.co/7ZBOkDK5FJ 💬 https://t.co/HVjx3Rg9XA

Tina proved that LoRA can match or surpass full-parameter RL. Tora builds directly on that result, turning it into a full framework. Built on torchtune, it extends RL post-training to LoRA, QLoRA, DoRA, and QDoRA under one interface with GRPO, FSDP, and compile support. QLoRA

[#hiring] I'm seeking PhD #Interns for 2026 at #NVIDIAResearch Taiwan! If interested, please send your CV and cover letter to minhungc [at] nvidia [dot] com 🔎Research topics: Efficient Video/4D Understanding & Reasoning. 📍Location: Taiwan / Remote (mainly APAC) #internships

Apply link: https://t.co/XuVnfPFM0g NVR Taiwan Website: https://t.co/C8mxyxeJMS @NVIDIAAI @NVIDIAAIDev @nvidia #NVIDIA #intern #researchinternship #research #multimodal #SpatialUnderstanding #4D #EfficientAI #VLM #LLM

[#hiring] I'm seeking PhD #Interns for 2026 at #NVIDIAResearch Taiwan! If interested, please send your CV and cover letter to minhungc [at] nvidia [dot] com 🔎Research topics: Efficient Video/4D Understanding & Reasoning. 📍Location: Taiwan / Remote (mainly APAC) #internships

[#EMNLP2025] Super excited to share MovieCORE @emnlpmeeting (Oral) — New #VideoUnderstanding Benchmark on System-2 Reasoning! 👉Check the original post from @JosmyFaure1 for more details! 📷 Project: https://t.co/pmR8WCunyW #VLM #LLM #Video #multimodal #AI #NVIDIA #NTU #NTHU

🚀 New Benchmark Alert! Our paper MovieCORE: COgnitive REasoning in Movies is accepted at #EMNLP2025 (Oral) 🎉 Movies aren’t just “what happened”, they’re why it happened, how characters feel, and what it means. MovieCORE tests Vision-Language Models on System-2 reasoning.

📣 Still Open for Submissions - X-Sense Workshop @ICCVConference! 📅 Deadline: September 8, 2025, 09:59 AM GMT 📝 Submission Portal: https://t.co/l2y89nLVx4 🌐 More info: https://t.co/3LRd386Bkm #ICCV2025 #ICCV #ICCV25 #CFP #NYCU #Cornell #NVIDIA #USYD #MIT #UCSD #TUDelft #UCLA

Thanks @_akhaliq for sharing our work! Check out more details:

We connect the autoregressive pipeline of LLMs with streaming video perception. Introducing AUSM: Autoregressive Universal Video Segmentation Model. A step toward unified, scalable video perception — inspired by how LLMs unified NLP. 📝

Ego-exo sensing is definitely the future and has a lot of potentials. Join us and explore this together!