Rohit Gupta
@rohitgUCF
Followers
197
Following
12K
Media
68
Statuses
678
Graduate student @ Center for Research in Computer Vision, University of Central Florida. Applied Science Intern at Amazon Stores Foundational AI.
Joined January 2021
If you work on Video LLMs or Reasoning for VLMs, try ImplicitQA, our new benchmark that requires models to fuse information from many frames using reasoning based on implicit facts about the world. Available on huggingface, GPT-O3 baseline gets around 64%, test your approach !.
0
0
2
RT @gabriberton: HalLoc is a cool paper from CVPR, afaik the only dataset with token-level annotation of hallucinations, with 150K token-le….
0
3
0
RT @charles_irl: You can read the whole article, and find the code, on the Modal blog here:.
modal.com
Price, performance, and control: pick three.
0
1
0
RT @svlevine: I always found it puzzling how language models learn so much from next-token prediction, while video models learn so little f….
0
178
0
RT @vidllms: VideoLLMs are one of the fastest growing areas in computer vision . Presented at the ongoing VideoLLMs workshop at CVPR. Venue….
0
2
0
RT @vidllms: Remarks from our chair Prof @ucfmshah kicking off the VideoLLMs workshop @CVPR . #CVPR #CVPR2025 #ComputerVision #AI
https://t….
0
7
0
I am already in Nashville, if anyone is around today let me know !.
1
0
1
RT @KhanSalmanH: Attendees of the VidLLMs workshop at #CVPR2025 can apply for travel grants of $1,000 - courtesy of Amazon and Apple. If yo….
0
1
0
RT @ucfmshah: Travel grants sponsored by Amazon and Apple are available for participants at CVPR-2025 VidLLMs workshop. Fill out this form….
0
13
0
Prizes worth $3,000 to be had !.
🚀 Join the Multilingual Video Reasoning Challenge! 🌍.🎥 879 real videos, 8,025 QA, 15 domains, 14 languages .🧠 Prove your VLM’s cultural IQ in open‑ended & MCQ tracks. 💰 Prizes + global glory!.Register & rules: #AI #MultilingualAI #CVPR2025
1
0
0
If you work on VideoLLMs and are looking for funding for your CVPR Trip, we have some grants courtesy of Apple and Amazon !.
0
0
0
really enjoying the thorough layerwise experiments in the new Perception Encoder series of papers from Meta
0
0
5
Participate in our new Complex Video Reasoning and Robustness Challenge !.
0
0
2
Submissions for VideoLLMs workshop now extended till Friday !.
🚨 Submission deadline for papers to 1st Video LLMs Workshop at #CVPR2025 has been extended by 5 days to April 20 !. 📌 Non-archival | 📷 Both Novel and published work welcome 📷.🎯CFP: Submit at:
0
0
1
RT @KhanSalmanH: 🚨 Submit to 1st Video LLMs Workshop at #CVPR2025 by April 15!. 📌 Non-archival | 💡 Novel work welcome.🎯 Topics: training, d….
0
12
0
RT @vidllms: 🚨 🚨 🚨 News 🚨 🚨 🚨. Paper Submission for the Video LLMs Workshop at @CVPR is open now !. Call for papers: .
openreview.net
Welcome to the OpenReview homepage for CVPR 2025 Workshop VideoLLMs
0
16
0
RT @charles_irl: I think programming GPUs is too hard. Part of the problem is sprawling, scattered documentation & best practices. Over th….
0
367
0
