Tessera
Folgen

Sweta Karlekar

@swetakar.bsky.social

Machine learning PhD student @ Blei Lab in Columbia University Working in mechanistic interpretability, nlp, causal inference, and probabilistic modeling! Previously at Meta for ~3 years on the Bayesian Modeling & Generative AI teams. 🔗 www.sweta.dev

33 Posts2699 Follower1196 Folgt
Sweta Karlekar@swetakar.bsky.social · 6mo ago

For those in NYC working in AI, ML-NYC is a free monthly speaker series co-organized by the Flatiron Institute, Columbia, and NYU. Past speakers include Bin Yu, Christos Papadimitriou, Léon Bottou (and many more). Talks are followed by a catered reception. Join us Feb 11th @ 4pm for Romain Lopez!

Blei Lab@bleilab.bsky.social · 6mo ago

The ML in NYC Speaker Series + Happy Hour is excited to host Professor Romain Lopez as our February speaker as he discusses deep generative models and their applications to the field of cellular and molecular biology! www.eventbrite.com/e/ml-nyc-spe...

Blei Lab@bleilab.bsky.social · 8mo ago

Excited to highlight recent work from the lab at NeurIPS! If you’re interested in understanding why uncertainty estimates often break under distribution shift — and how we can do better — check out Yuli’s poster tomorrow.

Yuli Slavutsky@yulislavutsky.bsky.social · 8mo ago

Uncertainty estimation fails under distribution shifts. Why? Partly because in stats, even Bayesian stats, we treat x as given. But intuitively data makes different models plausible. For reliable uncertainty, we need to account for it explicitly. Come chat with me about it tomorrow at my poster

Andrew Jesson@anndvision.bsky.social · 2y ago

fun @bleilab.bsky.social x oatml collab come chat with Nicolas , @swetakar.bsky.social , Quentin , Jannik , and i today

Nicolas Beltran-Velez@velezbeltran.bsky.social · 2y ago

Hello! We will be presenting Estimating the Hallucination Rate of Generative AI at NeurIPS. Come if you'd like to chat about epistemic uncertainty for In-Context Learning, or uncertainty more generally. :) Location: East Exhibit Hall A-C #2703 Time: Friday @ 4:30 Paper: arxiv.org/abs/2406.07457

Blei Lab@bleilab.bsky.social · 2y ago

Check out our new paper from the Blei Lab on probabilistic predictions with conditional diffusions and gradient boosted trees! #Neurips2024

Nicolas Beltran-Velez@velezbeltran.bsky.social · 2y ago

I am very excited to share our new Neurips 2024 paper + package, Treeffuser! 🌳 We combine gradient-boosted trees with diffusion models for fast, flexible probabilistic predictions and well-calibrated uncertainty. paper: arxiv.org/abs/2406.07658 repo: github.com/blei-lab/tre... 🧵(1/8)

Samples y | x from Treeffuser vs. true densities, for multiple values of x under three different scenarios. Treeffuser captures arbitrarily complex conditional distributions that vary with x.
Blei Lab@bleilab.bsky.social · 2y ago

Check out our new paper about hypothesis testing the circuit hypothesis in LLMs! This work previously won a top paper award at the ICML mechanistic interpretability workshop, and we’re excited to share it at #Neurips2024

claudia shi@claudiashi.bsky.social · 2y ago

The circuit hypothesis proposes that LLM capabilities emerge from small subnetworks within the model. But how can we actually test this? 🤔 joint work with @velezbeltran.bsky.social @maggiemakar.bsky.social @anndvision.bsky.social @bleilab.bsky.social Adria @far.ai Achille and Caro

Sweta Karlekar@swetakar.bsky.social · 2y ago

Very happy to share some recent work by my colleagues @velezbeltran.bsky.social, @aagrande.bsky.social and @anazaret.bsky.social! Check out their work on tree-based diffusion models (especially the website—it’s quite superb 😊)!

Nicolas Beltran-Velez@velezbeltran.bsky.social · 2y ago

I am very excited to share our new Neurips 2024 paper + package, Treeffuser! 🌳 We combine gradient-boosted trees with diffusion models for fast, flexible probabilistic predictions and well-calibrated uncertainty. paper: arxiv.org/abs/2406.07658 repo: github.com/blei-lab/tre... 🧵(1/8)

Samples y | x from Treeffuser vs. true densities, for multiple values of x under three different scenarios. Treeffuser captures arbitrarily complex conditional distributions that vary with x.
Sweta Karlekar@swetakar.bsky.social · 2y ago

Just learned about @andrewyng.bsky.social's new tool, aisuite (github.com/andrewyng/ai...) and wanted to share! It's a standardized wrapper around chat completions that lets you easily switch between querying different LLM providers, including OpenAI, Anthropic, Mistral, HuggingFace, Ollama, etc.

GitHub - andrewyng/aisuite: Simple, unified interface to multiple Generative AI providers

Simple, unified interface to multiple Generative AI providers - GitHub - andrewyng/aisuite: Simple, unified interface to multiple Generative AI providers

github.com

Sweta Karlekar@swetakar.bsky.social · 2y ago

(Shameless) plug for David Blei's lab at Columbia University! People in the lab currently work on a variety of topics, including probabilistic machine learning, Bayesian stats, mechanistic interpretability, causal inference and NLP. Please give us a follow! @bleilab.bsky.social

Carlos E. Perez (IntuitMachine)@ceperez.bsky.social · 2y ago

Almost 3x faster than FlashAttentiion2 github.com/thu-ml/SageA...

GitHub - thu-ml/SageAttention: Quantized Attention that achieves speedups of 2.1x and 2.7x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various mod...

Quantized Attention that achieves speedups of 2.1x and 2.7x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models. - thu-ml/SageAttention

github.com

Sweta Karlekar@swetakar.bsky.social · 2y ago

For anyone looking for climate-related data for ML projects, I recently learned about www.saildrone.com/technology/d.... Saildrone builds ocean drones that collect a ton of oceanic and climate data. And they have some publicly-available datasets on their website for researchers :) 🌊 #mlsky

Browse Sample Data Sets – Saildrone

Browse publicly available sample data sets from completed Saildrone missions, available for download in NetCDF format.

saildrone.com