@buair2

Boston University's AI Research (AIR) group led by @kate_saenko_ and Margrit Betke. We work on deep learning, computer vision, and NLP. Insta: @bu_air_labs.

 Boston, MA
bu.edu/hic/centers-initiatives-labs/air/
Joined January 2020
  • Tweets508
  • Following137
  • Followers270
44Media
Congratulations to @petsiuk on receiving the ECCV Best Paper Honorable Mention Award!
adn 👣@adn_twitts1 Oct 2024
And the award goes to... @eccvconf
2
4
26
1,851
Excited to be at NeurIPS! Presenting our poster on evaluating & adapting VLMs for multiple attribute-object relationships. Joint work with @AIatMeta- @kate_saenko_, @RanjayKrishna, Filip Radenovic, Abhimanyu Dubey, Bryan Plummer. cs-people.bu.edu/array/resea…
1
4
13
853
Introducing💥Lasagna: a layered diffusion model for image relighting. Lasagna adds realistic lighting to input images, even to vector art! Joint work with @drbashkirova @ARRay693 Rupayan Mallick, @SarahAdelBargal @RanjayKrishna @jianming_zhang_ arxiv.org/abs/2312.00833
7
1
27
3,772
wired.com/story/chatgpt-codi…

ChatGPT Isn't Coming for Your Coding Job

New technologies have long promised to make human software engineers redundant. But developers have only gotten more important over time.

wired.com
3
8
1,302
💪💪💪Two amazing PhD students defended within one week! @drbashkirova @AndreaDBurns Lucky to have had the privilege of working with both of you!
2
5
51
2,863
Excited to present this panel at @NeurIPSConf 23!
Sasha Rush
@srush_nlp27 Nov 2023
I'm moderating a plenary panel at #NeurIPS2023 entitled "LLMs: Beyond Scaling" with some amazing researchers. Please send or upvote any interesting questions: dory.app/events/2KZxWFPULUn9…
1
10
1,349
@llamagrp is attending @emnlpmeeting #EMNLP2023! We're presenting a couple of papers: on misinformation (by Jongin, poster Fri 2pm), on LLM editing (by Feyza, poster Sat 9am), and on code translation (by Peter, poster Sun at 11) . Do drop by and say hi!
1
2
7
826
We are 🔥super excited🔥 to release the Platypus family of finetuned LLMs 🥳🥳. Platypus achieves the top score in the Hugging Face Open LLM Leaderboard 🏆! The main focus of our work is to achieve cheap, fast and powerful refinement of base LLMs. page: platypus-llm.github.io/
14
76
8
296
81,856
Our data is now available at t.ly/3awQ. Evaluate how well your vision-langauge model can attach the correct attributes to the correct objects!
AK
@_akhaliq8 May 2023
COLA: How to adapt vision-language models to Compose Objects Localized with Attributes? abs: arxiv.org/abs/2305.03689 paper pages: huggingface.co/papers/2305.0…
1
12
50
26,048
Excited to announce I was one of the 232 outstanding reviewers for CVPR 2023!! See you all in Vancouver :)
2
1
1
25
2,851
VAST: Video-Audio Separation through Text, lets you separate sounds in video using natural language queries #CVPR2023 paper: arxiv.org/abs/2303.16342 website: cs-people.bu.edu/rxtan/proje… Led by @tan_rxtan w/@ARRay693 @AndreaDBurns B.A. Plummer @urinieto B. Russell @kate_saenko_
2
10
4
50
7,024
All the papers my group is presenting at @CVPR this week (videos ⬇️) ⭐ Prefix Conditioning for Pretraining ⭐ Bias Mimicking for Bias Mitigation ⭐ Pic2Word: Zero-Shot Composed Image Retrieval ⭐ Language-Guided Audio-Visual Source Separation ⭐ MaskSketch for Image Generation
1
2
29
3,799
Congratulations @natanielruizg on the award!! 💥💥💥
#CVPR2026@CVPR21 Jun 2023
#CVPR2023 paper awards
2
8
1,661
Excited 🥳🥳🥳to release my first senior author work, done while still a student at BU, with a start studded lineup of collaborators and an incredible student first-author @ArielNLee 🌻🙌- it's all about differences between Vision Transformers & CNNs arielnlee.github.io/PatchMix… 👇
4
31
4
127
38,786
We are running a #Neurips2023 @NeuripsConf workshop on machine learning for audio this year! Submissions on all aspects of ML for audio welcome. Website: mlforaudioworkshop.com/ Organizers: @sedielem @saddlepoint18 @rmanzelli @Aliceebaird @AlanCowen @KulisBrian Shri Narayanan
9
23
4,332
my student @AndreaDBurns and coauthors released a really cool dataset for multimodal webpage analysis called WikiWeb2M
WikiResearch@WikiResearch31 May 2023
"WikiWeb2M: A Page-Level Multimodal @Wikipedia Dataset" can be used for tasks like page description generation, section summarization, and contextual image captioning. (Burns et al, 2023) arxiv.org/pdf/2305.05432.pdf
1
15
1,342
Please volunteer to be a reviewer for #NeurIPS2023 ! otherwise we may be forced to use ChatGPT to write reviews LOL just kidding, that would be a terrible idea If you publish ML papers please do your part and review!
NeurIPS Conference
@NeurIPSConf5 Apr 2023
Our past conferences wouldn't have been possible without our many reviewers. If you have at least 2 papers in top peer-reviewed confs or journals, with at least one in an ML venue (eg NeurIPS ICML ICLR), we’d be v grateful if you reviewed for #NeurIPS2023 forms.gle/3bAjsYtD5FEpxJSq8

NeurIPS 2023 Reviewer Volunteering Form

The NeurIPS conference aims for a high-quality peer reviewing process by experts on a wide range of topics. Reviewers are expected to have at least two papers in top peer-reviewed conferences or...

docs.google.com
3
9
37
9,887
We present VAST: Video-Audio Separation through Text; a self-supervised method to learn to separate audio based on video/language. cs-people.bu.edu/rxtan/proje…
1
2
10
843
Congratulations Hariri Institute affiliates promoted to full professor: Kate Saenko, Jennifer Balakrishnan, Taylor Boas , Konstantinos Spiliopoulos, Theresa Ellis, and Paul Withers bit.ly/3JSydPa @BU_CAS @BUSargent @BU_Tweets @kate_saenko_ @JBalakrishnan @TaylorBoas
2
1
16
713
Pic2Word is our new model for searching for images based on a query image modified with words. For example, "🐈 in a tree" returns pictures of cats in trees. This is known as the "composed image retrieval" task.
AK
@_akhaliq8 Feb 2023
Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval abs: arxiv.org/abs/2302.03084 github: github.com/google-research/c…
1
8
1
60
16,395
Load more