always ready to learn something! professional: about to start my PhD, working in interpretability in NLP. personal: movies, languages, books, and historyabhinav271828.github.io Tübingen, DeutschlandJoined September 2021
New paper alert! 🧵👇
We show representations of concepts seen by a model during pretraining can be morphed to reflect novel semantics! We do this by building a task based on the conceptual role semantics "theory of meaning"--an idea I'd been wanting to pursue for SO long!
1/n
Check out our recent work on identifying the limitations and properties of SAEs!
We use formal languages as a synthetic testbed to evaluate the methodology and suggest further steps.
Check out our recent work on identifying the limitations and properties of SAEs!
We use formal languages as a synthetic testbed to evaluate the methodology and suggest further steps.
Can RL fine-tuning endow MLLMs with fine-grained visual understanding?
Using our training recipe, we outperform SOTA open-source MLLMs on fine-grained visual discrimination with ClipCap, a mere 200M param simplification of modern MLLMs!!!
🚨Introducing No Detail Left Behind:…
🚨 Introducing Detect, Describe, Discriminate: Moving Beyond VQA for MLLM Evaluation.
Given an image pair, it is easier for an MLLM to identify fine-grained visual differences during VQA evaluation than to independently detect and describe such differences 🧵(1/n):
162 Followers 257 FollowingIntern @GoogleDeepMind Toronto | PhD student at @MPI_IS + @uni_tue.
Researching generalization, robustness, and video (world) models.
613 Followers 437 FollowingPhD student at the University of Amsterdam / ILLC, interested in computational linguistics and (mechanistic) interpretability. Current Anthropic Fellow.
384 Followers 418 FollowingPhD Student at Max Planck Institute. Past @iiit_hyderabad @VectorInst. Interested in better evals, forecasting, and open-endedness.
9K Followers 1K FollowingAssistant Professor at NUS. Scaling cooperative intelligence & infrastructure for an automated future. PhD @ MIT ProbComp / CoCoSci. Pronouns: 祂/伊
267 Followers 836 FollowingPhD @Berkeley_EECS | Previous @MSFTResearch,@_FiveAI, @kasl_ai, @val_iisc, CS @IITBHU_Varanasi.
Interested in foundations of AI and AI Safety.
1K Followers 554 FollowingPhD student at the intersection of information theory and deep learning. Two master's degrees in maths and AI. Interested in AI existential safety
2K Followers 528 FollowingResearch Scientist @ Idiap Research Institute. @Idiap_ch
Adjunct lecturer @ Australian Institute for ML. @TheAIML
Occasionally cycling across continents.
2K Followers 1K FollowingMember of Technical Staff @GoodfireAI; Previously: Postdoc / PhD at Center for Brain Science, Harvard and University of Michigan
18K Followers 4K FollowingAI professor.
Deep Learning, AI alignment, ethics, policy, & safety.
Formerly Cambridge, Mila, Oxford, DeepMind, ElementAI, UK AISI.
AI is a really big deal.
1K Followers 700 FollowingEuropean Commission (AI Office). PhD student @CambridgeMLG. Here to discuss ideas and have fun. Posts are my personal opinions; I don't speak for my employer.
162 Followers 257 FollowingIntern @GoogleDeepMind Toronto | PhD student at @MPI_IS + @uni_tue.
Researching generalization, robustness, and video (world) models.
613 Followers 437 FollowingPhD student at the University of Amsterdam / ILLC, interested in computational linguistics and (mechanistic) interpretability. Current Anthropic Fellow.
5K Followers 668 FollowingIncoming Assistant Prof, Toyota Technical Institute at Chicago @TTIC_Connect
Recruiting PhD students (start 2026) 👀
Will irl - TC0 enthusiast
12K Followers 1K FollowingFounder of https://t.co/9KM4uFScMi, Associate Professor at Columbia. Making ai agent design and deployment easy and fast!
Forbes 30 under 30.
1.2M Followers 279 FollowingWe’re a team of scientists, engineers, ethicists and more, committed to solving intelligence, to advance science and benefit humanity.
9K Followers 52 FollowingThe official account of the Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics.
4K Followers 131 FollowingAI safety research @AnthropicAI. Prev postdoc in LLM interpretability with @davidbau, math PhD at @Harvard, director of technical programs at https://t.co/FxRv4QgERO
384 Followers 418 FollowingPhD Student at Max Planck Institute. Past @iiit_hyderabad @VectorInst. Interested in better evals, forecasting, and open-endedness.
6K Followers 1K FollowingGroup Leader,
Physics of Intelligence Program at Harvard University
Physics of Artificial Intelligence Group, NTT Research, Inc.
267 Followers 836 FollowingPhD @Berkeley_EECS | Previous @MSFTResearch,@_FiveAI, @kasl_ai, @val_iisc, CS @IITBHU_Varanasi.
Interested in foundations of AI and AI Safety.
1K Followers 554 FollowingPhD student at the intersection of information theory and deep learning. Two master's degrees in maths and AI. Interested in AI existential safety
10K Followers 1K FollowingWaiting on a robot body. All opinions are universal and held by both employers and family. Now a dedicated grok hate account.
Accepting ML/NLP PhD students.
25K Followers 89 FollowingA non-profit research lab focused on interpretability, alignment, and ethics of artificial intelligence.
Creators of GPT-J, GPT-NeoX, Pythia, and VQGAN-CLIP
No recent Favorites. New Favorites will appear here.