Log inSign up
Harit Vishwakarma
282 posts
user avatar
Harit Vishwakarma
@harit_v
Postdoc@Oxford, AI for Science, LLM Reliability and Data-centric AI, prev. @WisconsinCS, @iiscbangalore, @IBMResearch.
Oxford, UK
harit7.github.io
Joined December 2012
1,874
Following
586
Followers
  • user avatar
    Harit Vishwakarma
    @harit_v
    Sep 25, 2024
    📢Excited to share that our work on improving confidence functions for auto-labeling has been accepted to #NeurIPS24🎉. More updates coming soon. Meanwhile, check out the full paper on Arxiv and catch up with our previous thread! 👇 Arxiv: arxiv.org/pdf/2404.16188
    user avatar
    Harit Vishwakarma
    @harit_v
    Jul 27, 2024
    1/9 Care to cut your data labeling costs? 💰💰💰 Join us at the #ICML2024 #DMLR workshop to learn about auto-labeling and how we push it to the next level by improving the confidence functions! 🧵 Paper: arxiv.org/pdf/2404.16188
    Image
    Image
    2.5K
  • user avatar
    Harit Vishwakarma
    @harit_v
    Dec 9, 2023
    Excited to present 3 papers at #NeurIPS2023 ! Come and let's chat ☕️ 1. Wed 5p. Promises and Pitfalls of Threshold-based Auto-Labeling (Spotlight) 2. Tue 5p. Train 'n Trade: Foundations of Parameter Markets 3. Sat 11a. Human in the Loop OOD Detection with FPR Control ⬇️
    11K
  • user avatar
    Harit Vishwakarma
    @harit_v
    Sep 15, 2022
    Super excited to share that our work with @nick11roberts and my advisor @fredsala, "Lifting Weak Supervision to Structured Prediction" has been accepted at #NeurIPS2022. Preprint coming soon!
  • user avatar
    Harit Vishwakarma
    @harit_v
    Dec 14, 2024
    1/ Thrilled to present our work on Monty Hall inspired re-prompting and score optimization in conformal prediction (CP) to improve uncertainty quantification and accuracy of LLMs at inference time. Catch me, Alan, and Nic at #NeurIPS2024 1. Stats for LLM w/s, Sat., 2. Open
    Image
    3.2K
  • user avatar
    Harit Vishwakarma
    @harit_v
    Jul 5, 2023
    📢 A fun blog post 📢 with my advisor @fredsala Checkout our blog post on improving the reliability of LLMs via aggregation using super cool classical tools🔧🔨. BlogPost: sprocketlab.github.io/posts/2023/06/… Paper: proceedings.neurips.cc/paper_files/pa… Code: github.com/SprocketLab/Ma…
    Image
    10K
  • user avatar
    Harit Vishwakarma
    @harit_v
    Jul 29, 2023
    Excited to present our poster on “Promises and Pitfalls of Threshold-based Auto-Labeling” at the DMLR workshop at @icmlconf. This is a work with my colleague Heguang Lin and my advisors Fred Sala (@fredsala) and Ramya Vinayak. 📅 Sat. 3:30 - 4:30 pm, in Ballroom C. 1/n
    Image
    9.4K
  • user avatar
    Harit Vishwakarma
    @harit_v
    Jul 27, 2024
    1/9 Care to cut your data labeling costs? 💰💰💰 Join us at the #ICML2024 #DMLR workshop to learn about auto-labeling and how we push it to the next level by improving the confidence functions! 🧵 Paper: arxiv.org/pdf/2404.16188
    Image
    Image
    4.2K
  • user avatar
    Harit Vishwakarma
    @harit_v
    Dec 15, 2024
    Replying to @thaoshibe
    I fancy a day when the poster boards will have a huge display. We can do poster, slides, demo whatever. Given the amount of money is spent on posters, it might be worth to have these.
    7.2K
  • user avatar
    Harit Vishwakarma
    @harit_v
    Nov 29, 2022
    Excited to present our work on 💪🏋️ Lifting Weak Supervision to Structured Prediction 💪🏋️ @NeurIPSConf this week! We’ll be in Hall J, #334 at 4pm on Wednesday– drop by and chat with us! arxiv.org/abs/2211.13375 #NeurIPS2022 [1/n]
    Image
  • user avatar
    Harit Vishwakarma
    @harit_v
    Jul 29, 2023
    Excited to present our poster on “Human in the Loop Out-of-Distribution (OOD) Detection with False Positive Rate (FPR) Control” at the AI & HCI w/s at @icmlconf. It's a work with my colleague Heguang Lin and my advisor Ramya Vinayak. 📅 Sat. 10:50 -11:50 am, Room 311. 1/n
    3.1K
  • user avatar
    Harit Vishwakarma
    @harit_v
    Dec 11, 2024
    Excited to present Colander at #NeurIPS24, our new framework for optimizing confidence functions to make auto-labeling more efficient and reliable. Check out our poster #1906 at today's evening poster session. Wed, Dec 11, 4:30–7:30 PM Poster #1906 Project Page:
    Image
    1.8K
  • user avatar
    Harit Vishwakarma
    @harit_v
    Jul 27, 2024
    1/9 Want to up your Semi-Supervised Learning (SSL) game? Join us at the #ICML2024 #DMLR workshop to discuss our improvements to pseudolabeling-based SSL via learnable confidence functions and pseudolabeling accumulation! 🧵 Paper: bit.ly/pablo-dmlr
    Image
    Image
    1.7K
  • user avatar
    Harit Vishwakarma
    @harit_v
    May 1, 2024
    Excited to be at #AISTATS2024 👋 . Join us for the poster presentation on "Taming False Positives in Out-of-Distribution Detection with Human Feedback" with @CrossEntropi @ramyavinayak 🗓️ Date: Thu. 2nd May 🕔 Time: 5-7 pm CEST Paper URL: bit.ly/4a0Nw26 1/n
    3.1K
  • user avatar
    Harit Vishwakarma
    @harit_v
    Dec 12, 2023
    Curious to know how to trade model weights? Come to our poster tomorrow at 5p !
    user avatar
    Tzu-Heng (Brian) Huang
    @zihengh1
    Dec 12, 2023
    Can we treat model weights as market commodities? Just as manufacturers use purchased parts to cut production costs, ML could gain from trading well-trained parameters in market, instead of isolated development! We build a market to trade parameter sets in our #NeurIPS2023 paper!
    Image
    675

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
Advertisement
Advertisement