Mohit Bansal
@mohitban47
Parker Professor at UNC Chapel Hill (@unccs @unc). Director: https://t.co/5qlPVgnrlN (@uncnlp). Previous: @Berkeley_AI, @TTIC_Connect @IITKanpur #NLP, #CV, #AI, #ML
ID:830355049
http://www.cs.unc.edu/~mbansal/ 18-09-2012 04:25:22
3,8K Tweets
8,1K Followers
629 Following
Today 5-7pm at #NeurIPS2023 , I’ll present VPGen & VPEval, the first interpretable/explainable visual programming framework for T2I generation & evaluation.
See you at poster #331!🤗
Project: vp-t2i.github.io
Talk: youtube.com/watch?v=8iuCZX…
Abhay Zala @ NeurIPS2023 Mohit Bansal UNC NLP
An excerpt from the session 'Building Scalable Large Language Models' at GPAI Summit 2023 by Prof Mohit Bansal, John R. & Louise S. Parker Professor, University of North Carolina.
Ministry of Electronics & IT Amitabh Nag Mohit Bansal
Meet the Speakers at #GPAISummit2023 's Session on Building Scalable Large Language Models (LLMs). The aim is to deepen understanding through research and industry insights while encouraging networking and professional growth in the LLM and NLP sectors. Visit…
Happening right now!
Session on Building Scalable Large Language Models at GPAI Summit.
Ministry of Electronics & IT Amitabh Nag
At #NeurIPS2023 , I’ll present SeViLA, a SoTA framework that self-chained image-LM to tackle video 1) localization & 2) QA!
Great Hall & Hall B1+B2 (level 1) # 317 Wed 5-7pm
paper: arxiv.org/abs/2305.06988
talk: youtube.com/watch?v=AIdXfZ…
Jaemin Cho @ NeurIPS2023 Prateek Yadav not @NeurIPS'23 Mohit Bansal @ EMNLP 2023 UNC NLP
Tuesday 10:45am-12:45pm
(Spotlight) #1526: Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
With Peter Hase, Mohit Bansal @ EMNLP 2023 , and Been Kim
I'll be at #NeurIPS2023 from Mon-Thurs. Happy to talk about LLMs, Reasoning, Interpretability, or anything else 😃
On Wed (10.45-12.45pm CST), I'll also present a paper on how personalization enables LLMs to efficiently teach weaker agents 👇
Cmr-ready: arxiv.org/abs/2306.09299
The FOMO of missing #NeurIPS2023 despite having two papers (TIES-Merging and SeViLA) is real.
However, If you want to chat or are looking for interns to work on MoE models, Instruction Tuning, Continuously updating LLMs, PEFT methods, or Model Merging then do reach out!
🧵
I attend #NeurIPS2023 to present 3 papers, and would love to have a coffee chat!🤗
1. VPGen&VPEval
vp-t2i.github.io
nips.cc/virtual/2023/p…
2. SeViLA
arxiv.org/abs/2305.06988
nips.cc/virtual/2023/p…
3. Paxion (Spotlight)
arxiv.org/abs/2305.10683
nips.cc/virtual/2023/p…
I'll be at #NeurIPS2023 from Mon-Fri😀. Happy to talk about VLN, image generation, or anything else.
On Wed (5 - 7pm CST), I'll present PanoGen--creating diverse 360-degree panoramic environment via recursive outpainting for VLN.
pano-gen.github.io
recorder-v3.slideslive.com/?share=87305&s…
Thanks for the invitation, Digital India -- looking forward to speaking on 'Building Scalable LLMs' at the Global Partnership on Artificial Intelligence GPAI 🙂
gpaidelhi2023.in
#GPAISummit2023 #GPAI2023