Shruti Joshi @_shruti_joshi_

phd student in identifiable repl @Mila_Quebec. prev. research programmer @MPI_IS Tübingen, undergrad @IITKanpur '19. shrutij01.github.io Montreal, Canada Joined August 2018

Tweets

179
Followers

408
Following

828
Likes

2K

Sahil Verma @Sahil1V

3 months ago

🚨 New Paper! 🚨 Guard models slow, language-specific, and modality-limited? Meet OmniGuard that detects harmful prompts across multiple languages & modalities all using one approach with SOTA performance in all 3 modalities!! while being 120X faster 🚀 arxiv.org/abs/2505.23856

1 39 82 14K 23

Download Image

Soumye Singhal @soumyesinghal

5 months ago

⚡⚡ Llama-Nemotron-Ultra-253B just dropped: our most advanced open reasoning model 🧵👇

3 13 44 3K 5

Download Image

Arkil Patel @arkil_patel

5 months ago

𝐓𝐡𝐨𝐮𝐠𝐡𝐭𝐨𝐥𝐨𝐠𝐲 paper is out! 🔥🐋 We study the reasoning chains of DeepSeek-R1 across a variety of tasks and settings and find several surprising and interesting phenomena! Incredible effort by the entire team! 🌐: mcgill-nlp.github.io/thoughtology/

Sara Vera Marjanović @saraveramarjano

5 months ago

3 63 229 43K 146

Download Image

0 5 24 3K 6

Download Image

Arkil Patel @arkil_patel

7 months ago

Presenting ✨ 𝐂𝐇𝐀𝐒𝐄: 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐧𝐠 𝐜𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐢𝐧𝐠 𝐬𝐲𝐧𝐭𝐡𝐞𝐭𝐢𝐜 𝐝𝐚𝐭𝐚 𝐟𝐨𝐫 𝐞𝐯𝐚𝐥𝐮𝐚𝐭𝐢𝐨𝐧 ✨ Work w/ fantastic advisors @DBahdanau and @sivareddyg Thread 🧵:

1 18 41 7K 16

Download Image

Sahil Verma @Sahil1V

11 months ago

📣 📣 📣 Our new paper investigates the question of how many images 🖼️ of a concept are required by a diffusion model 🤖 to imitate it. This question is critical for understanding and mitigating the copyright and privacy infringements of these models! arxiv.org/abs/2410.15002

10 61 226 38K 109

Download Image

Tom Marty @Tom__Marty

11 months ago

🚨NEW PAPER OUT 🚨 Excited to share our latest research initiative on in-context learning and meta-learning through the lens of Information theory !🧠 🔗 arxiv.org/abs/2410.14086 Check out our insights and empirical experiments! 🔍

Eric Elmoznino @EricElmoznino

11 months ago

3 24 104 16K 65

0 3 7 672 2

Leena C Vankadara @leenaCvankadara

12 months ago

I am thrilled to announce that I will be joining the Gatsby Computational Neuroscience Unit at UCL as a Lecturer (Assistant Professor) in Feb 2025! Looking forward to working with the exceptional talent at @GatsbyUCL on cutting-edge problems in deep learning and causality.

Gatsby Computational Neuroscience Unit @GatsbyUCL

12 months ago

1 6 37 12K 3

Download Image

10 6 66 10K 3

Arkil Patel @arkil_patel

a year ago

Presenting tomorrow at #NAACL2024: 𝐶𝑎𝑛 𝐿𝐿𝑀𝑠 𝑖𝑛-𝑐𝑜𝑛𝑡𝑒𝑥𝑡 𝑙𝑒𝑎𝑟𝑛 𝑡𝑜 𝑢𝑠𝑒 𝑛𝑒𝑤 𝑝𝑟𝑜𝑔𝑟𝑎𝑚𝑚𝑖𝑛𝑔 𝑙𝑖𝑏𝑟𝑎𝑟𝑖𝑒𝑠 𝑎𝑛𝑑 𝑙𝑎𝑛𝑔𝑢𝑎𝑔𝑒𝑠? 𝑌𝑒𝑠. 𝐾𝑖𝑛𝑑 𝑜𝑓. Internship @allen_ai work with @pdasigi and my advisors @DBahdanau and @sivareddyg.

3 20 74 9K 22

Download Image

Nicholas Meade @ncmeade

a year ago

Adversarial Triggers For LLMs Are 𝗡𝗢𝗧 𝗨𝗻𝗶𝘃𝗲𝗿𝘀𝗮𝗹!😲 It is believed that adversarial triggers that jailbreak a model transfer universally to other models. But we show triggers don't reliably transfer, especially to RLHF/DPO models. Paper: arxiv.org/abs/2404.16020

3 32 99 33K 37

Download Image

Arkil Patel @arkil_patel

a year ago

📢 Exciting new work on AI safety! Do adversarial triggers transfer universally across models (as has been claimed)? 𝗡𝗼. Are models aligned by supervised fine-tuning safe against adversarial triggers? 𝗡𝗼. RLHF and DPO are far better!

Nicholas Meade @ncmeade

a year ago

3 32 99 33K 37

Download Image

0 6 20 2K 2

Arkil Patel @arkil_patel

2 years ago

Presenting tomorrow at #EMNLP2023: MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretations w/ amazing advisors and collaborators @DBahdanau, @sivareddyg, and @satwik1729

2 17 45 7K 5

Download Image

Sébastien Lachapelle @seblachap

2 years ago

1/ Excited for our oral presentation at #NeurIPS2023 on "Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation"! A theoretical paper about object-centric representation learning (OCRL), disentanglement & extrapolation arxiv.org/abs/2307.02598