I will soon share more details about our accepted work at ICCV2023! See you all in Paris! 🗼🎉

#ICCV2023 Fri Oct 6 (PM) Going Beyond Nouns With Vision & Language Models Using Synthetic Data Cascante, Shehada, James Smith, Sivan Doveh, Kim, Rameswar Panda, Gül Varol, Aude Oliva, vislang.ai, Rogerio Feris, Leonid Karlinsky pdf: arxiv.org/abs/2303.17590 web: synthetic-vic.github.io

With Code+Data available, I'm happy to share one of my latest works to be presented at #ICCV2023! Going Beyond Nouns With Vision & Language Models Using Synthetic Data Project page: synthetic-vic.github.io Data & Code: github.com/uvavision/SyViC (1/6)

Rice CS PhD student Paola Cascante-Bonilla introduces a 1M-scale synthetic dataset at #iccv2023. It allows users to add synthetically generated objects like furniture & humans to an image & is the result of her collaboration with her vislang.ai advisor Vicente Ordónez. bit.ly/3QIqA1p

How do biases change before and after finetuning large scale visual recognition models? Our AFME 2024 @ NeurIPS paper incorporates sets of canonical images to highlight changes in biases for an array of off-the-shelf pretrained models. #NeurIPS2023 Link: arxiv.org/abs/2303.07615

Great news from #CVPR2024 🎉🎉🎉 Happy to share that our paper ElasticDiffusion: Training-free Arbitrary Size Image Generation was accepted #CVPR2025. Big thanks to my collaborators Vicente Ordóñez and Guha Balakrishnan. Checkout more details from here: elasticdiffusion.github.io

Chatted with Ruozhen Catherine He and Paola Cascante-Bonilla from vislang.ai at Rice University about the paper they had accepted to #CVPR2025 Their paper introduces Self-Consistency Equivalence Tuning (SelfEQ) to improve visual grounding in vision-and-language models using paraphrases. The Problem:

(1/4) Excited to share our latest work at #CVPR2024 #CVPR2025!🔥 Join us tomorrow, Thursday, June 20, from 10:30am to noon at Poster Session 3, # 334, to learn about "Improved Visual Grounding through Self-Consistent Explanations" with Paola Cascante-Bonilla, Ziyan, Alex Berg, vislang.ai.

Check out the work by Ruozhen Catherine He who is representing our group at #CVPR2024 at the poster session tomorrow morning. Poster #334. #CVPR.

Rice CS' Ruozhen Catherine He presented her paper, Improved Visual Grounding through Self-Consistent Explanations, at #CVPR2025 2024. SelfEQ helps computers ‘see’ more accurately and consistently. She is advised by faculty member Vicente Ordóñez-Román. bit.ly/4dfe9CS vislang.ai

GenAI has struggled to create consistent images, but research from Rice CS' vislang.ai lab could make weird AI images a thing of the past. Moayed Haji Ali and Vicente Ordónez-Román have developed a way to improve the performance of AI diffusion models. bit.ly/3BcIlQQ

Rice CS welcomes Zhengzhong Tu, Texas A&M assistant professor, next Tuesday, 9/24 at 4pm in Duncan Hall 3076. Dr. Tu will discuss Democratizing Diffusion Models for Controllable & Efficient Computational Imaging. PLEASE RSVP: bit.ly/4eraBh1 Zhengzhong Tu vislang.ai

I am excited to share that two of our research works will be presented at ECCV 2024. #ECCV2024 They focus on augmenting language models with fine-grained visual recognition ability. AutoVER made successful attempts at generative visual recognition. It was accepted to the ECCV

Rice is shaping the future of AI! Our researchers are working on groundbreaking methods to eliminate the "weird" or distorted images that AI sometimes generates. This innovation could lead to more accurate and realistic visuals created by artificial intelligence. The future of

Can pretrained diffusion models connect for cross-modal generation? 📢 Introducing AV-Link ♾ Bridging unimodal diffusion models in one framework to enable: 📽️ ➡️ 🔊 Video-to-Audio 🔊 ➡️ 📽️ Audio-to-Video 🌐: snap-research.github.io/AVLink/ 📄: hf.co/papers/2412.15… ⤵️ Results

Check our new work on cross-modal audio-video generation. Our work produces audio with the best alignment we have seen with respect to actions happening on video. Particularly useful in the era of astounding progress in generative video models.

Looking for a new (image) re-ranking paradigm? Check this out! LoCoRe (Long-Context Reranker) is trained with a long-context sequence model and token-level supervision to achieve **one-pass** re-ranking for all image candidates. Catch us at #CVPR Poster Session 2 #401 on Friday,