Rattana Pukdee Profile
Rattana Pukdee

@rpukdeee

Followers
55
Following
268
Media
1
Statuses
104

PhD student at @mldcmu 🐕‍🦺

Pittsburgh
Joined April 2014
Don't wanna be here? Send us removal request.
@dylanjsam
Dylan Sam
1 month
🚨Excited to introduce a major development in building safer language models: Safety Pretraining! Instead of post-hoc alignment, we take a step back and embed safety directly into pretraining. 🧵(1/n)
7
90
342
@jen_hsia
Jennifer Hsia
3 months
1/6 Retrieval is supposed to improve generation in RAG systems. But in practice, adding more documents can hurt performance, even when relevant ones are retrieved. We introduce RAGGED, a framework to measure and diagnose when retrieval helps and when it hurts.
1
22
106
@rpukdeee
Rattana Pukdee
6 months
In our #AISTATS2025 paper, we ask: when it is possible to recover a consistent joint distribution from conditionals? We propose path consistency and autoregressive path consistency—necessary and easily verifiable conditions. See you at Poster session 3, Monday 5th May.
1
7
15
@dylanjsam
Dylan Sam
8 months
Excited to share new work from my internship @GoogleAI ! Curious as to how we should measure the similarity between examples in pretraining datasets? We study the role of similarity in pretraining 1.7B parameter language models on the Pile. arxiv: https://t.co/iyS3Fxtx9a 1/🧵
5
42
170
@dylanjsam
Dylan Sam
9 months
To trust LLMs in deployment (e.g., agentic frameworks or for generating synthetic data), we should predict how well they will perform. Our paper shows that we can do this by simply asking black-box models multiple follow-up questions! w/ @m_finzi and @zicokolter 1/ 🧵
4
42
118
@dylanjsam
Dylan Sam
11 months
Contrastive VLMs (CLIP) lack the structure of text embeddings, like satisfying analogies via arithmetic (king - man = queen). We enhance CLIP’s *reasoning abilities* on such tasks by finetuning w/ text descriptions of image differences! w/ D. Willmott, J.Semedo, @zicokolter 1/🧵
2
46
173
@danielpjeong
Daniel P Jeong
1 year
🧵 Are "medical" LLMs/VLMs *adapted* from general-domain models, always better at answering medical questions than the original models? In our oral presentation at #EMNLP2024 today (2:30pm in Tuttle), we'll show that surprisingly, the answer is "no". https://t.co/3259JyNU44
Tweet card summary image
arxiv.org
Several recent works seek to develop foundation models specifically for medical applications, adapting general-purpose large language models (LLMs) and vision-language models (VLMs) via continued...
2
36
104
@danielpjeong
Daniel P Jeong
1 year
(1/N) Can LLMs tell you what features to use for predicting an outcome? In our work, we demonstrate that LLMs such as GPT-4 are capable of identifying predictive features for supervised learning tasks, even without access to the training data. w/ @zacharylipton @RavikumarPrad 🧵
3
11
31
@RuntianZhai
Runtian Zhai
1 year
One week away from @iclr_conf in Vienna 🤩 I will be presenting two spotlights: why big foundation models generalize so well under the self-supervised setting, and how to leverage massive unlabeled data using a base kernel that encodes inter-sample similarity. Details 👇 (1/3)
1
10
48
@yewonbyun_
Emily Byun
1 year
Estimating notions of unfairness/inequity is hard as it requires that data captures all features that influenced decision-making. But what if it doesn't? In our work ( https://t.co/YXXLlkbRRS), we answer this question w/ @dylanjsam @MichaelOberst @zacharylipton @brwilder
3
28
71
@RuntianZhai
Runtian Zhai
2 years
Unlabeled data is crucial for modern ML. It provides info about data distribution P, but how to exploit such info? Given a kernel K, our #ICLR2024 spotlight gives a general & principled way: Spectrally Transformed Kernel Regression (STKR). Camera-ready 👇 https://t.co/0IQZz1NiGn
Tweet card summary image
arxiv.org
Unlabeled data is a key component of modern machine learning. In general, the role of unlabeled data is to impose a form of smoothness, usually from the similarity information encoded in a base...
1
13
59
@RuntianZhai
Runtian Zhai
2 years
What'd you do with an inter-sample similarity kernel, lots of unlabeled and little labeled data? Some might say kernel ridge regression (KRR), but KRR can't use unlabeled data by representer theorem. Our #ICLR2024 spotlight STKR gives an answer. A 🧵 (1/3) https://t.co/op78hiL61v
openreview.net
Unlabeled data is a key component of modern machine learning. In general, the role of unlabeled data is to impose a form of smoothness, usually from the similarity information encoded in a base...
1
4
13
@brandontrabucco
Brandon Trabucco
2 years
Stable Diffusion is an effective data augmentation. Website: https://t.co/GJLFbOmGiX Watch Here: https://t.co/2lbPuysK4j I'm excited to share my NeurIPS talk about DA-Fusion from the Synthetic Data workshop, where we build an augmentation that semantically modifies images, and
1
24
62
@dylanjsam
Dylan Sam
2 years
Check out our #NeurIPS2023 paper "Learning with Explanation Constraints" with my co-author @rpukdeee, which explains how explanations of model behavior can help us from a learning-theoretic perspective! ( https://t.co/EKknX9EMzT) 🧵 (1/n)
2
16
58
@AlexTamkin
Alex Tamkin
3 years
DALL-E meets WALL-E: An Art History 1) Mona Lisa, Leonardo da Vinci
7
124
1K
@_onionesque
Shubhendu Trivedi
4 years
"A Theory of PAC Learnability under Transformation Invariances" https://t.co/E5n5EQFpfS by Hao Shao, @montasser_omar and Avrim Blum; seems like one of the first papers studying optimal algorithms in terms of sample complexity under (group) transformation invariances.
Tweet card summary image
arxiv.org
Transformation invariances are present in many real-world problems. For example, image classification is usually invariant to rotation and color transformation: a rotated car in a different color...
1
5
32
@rpukdeee
Rattana Pukdee
4 years
I am excited to share that I joined @mldcmu , @SCSatCMU as a PhD student and I will be working on interpretability/ robustness in ML with my advisors Nina Balcan and Pradeep Ravikumar. 🤓
0
0
1
@iScienceLuvr
Tanishq Mathew Abraham, Ph.D.
4 years
Materials for a comprehensive course on Geometric Deep Learning are available here: https://t.co/TS5q8fQwQF • 12 lectures • Taught by pioneers in the field (@mmbronstein, @TacoCohen, @joanbruna, @PetarV_93) • 100% free Check it out! 🚀
5
158
566
@jbhuang0604
Jia-Bin Huang @ICCV2025
4 years
How to come up with research ideas? Excited about starting doing research but have no clue?🤷‍♂️🤷🏻‍♀️ Here are some simple methods that I found useful in identifying initial directions. Check out the thread below 👇
39
503
2K