Similar User
@_Hao_Zhu
@jieyuzhao11
@WeijiaShi2
@shi_weiyan
@dan_fried
@vijaytarian
@hila_chefer
@nlpxuhui
@shuyanzhxyc
@claranahhh
@MaxMa1987
@JunjieHu12
@_emliu
@ZhuWanrong
@SoYeonTiffMin
Can a Transformer count inductively? ▶️ Yes, but different schema for positional embeddings are required for different forms of counting. Can we treat counting as a primitive operation of Transformer computation? ▶️ No, because it requires a non-trivial computation budget and…
OMG, this is killing me 😂😂😂
Just landed in Miami to attend #EMNLP2024 🐊 I’ll be presenting the poster of our “Tools fail” paper on Wednesday Nov 13th, 16:00-17:30 at Jasmine — come check out our poster for a chat!
Tools augment LLMs but can also introduce errors without explicit messages. Can LLMs detect these "silent" tool-based errors? We investigate this challenge and present an initial approach to failure recovery. Work w/ @SoYeonTiffMin @_Yingshan @ybisk 🗞️ arxiv.org/abs/2406.19228
Our method breaks down the Mutual Information into the Redundancy (R), Synergy (S), and Uniqueness (U) of the conditioning tokens. R is the redundant info from multiple tokens, S is the info from token interactions, and U is the unique information from each token. 4/n
Diffusion models have advanced significantly, but how well do we understand their workings? How do textual tokens impact output, and where do biases and failures occur? In our @NeurIPS 2024 paper, we introduce DiffusionPID to answer these questions and more. #neurips2024 1/n
We introduce Situated Instruction Following (SIF), to appear in ECCV 2024! There is inherent underspecification in instructions when humans act as they speak. SIF is addresses these dynamic, temporally evolving intent of instructions in the context of physical human actions.(1/7)
I’m thrilled to be joining @CarnegieMellon’s Machine Learning Department (@mldcmu) as an Assistant Professor this Fall! My lab will work at the intersection of neuroscience & AI to reverse-engineer animal intelligence and build the next generation of autonomous agents. Learn…
❓Are there any unique advantages of diffusion-based LMs over autoregressive LMs? ❓Can we scale and instruction-tune diffusion LMs? Presenting "David helps Goliath: Inference-Time Collaboration Between Small Specialized and Large General Diffusion LMs" at #NAACL2024! 📖…
Something to read for the weekend: link.springer.com/epdf/10.1007/s…
The average overworked PhD student
LLMs excel in math. Introducing a new benchmark, we observe: They struggle with creative and many-step questions (even with CoT), their performance varies widely even on similar topics, and they engage in genuine reasoning only in about half of cases. 1/n arxiv.org/abs/2406.05194
We should call models like Llama 3, Mixtral, etc. “open-weight models”, not “open-source models”. For a model to be open-source, the code and training data need to be public (good examples: GPT-J, OLMo, RedPajama, StarCoder, K2, etc.). Weights are like an exe file, which would be…
So excited to see this fascinating work by my labmate Artem🤩. This is an inspiration for everyone who loves animal 🤩. arxiv.org/abs/2404.18739
🎞 Prof. @radamihalcea appeared on @CBSDetroit to discuss a new #AI tool used to interpret the meaning behind a dog's bark. 🔽🔊 Hear what she has to say on this innovative way of connecting with our pets! youtube.com/watch?v=nToCDO…
1/We've nailed a framework to reliably detect if an LLM was trained on your dataset: LLM Dataset Inference. After over a year of thinking of writing about how hard this is, we had a breakthrough that made me quite literally jump from my seat! 📝: arxiv.org/abs/2406.06443 Long🧵
[LG] How Far Can Transformers Reason? The Locality Barrier and Inductive Scratchpad E Abbe, S Bengio, A Lotfi, C Sandon, O Saremi [Apple & EPFL] (2024) arxiv.org/abs/2406.06467 - Transformers can be Turing-complete in expressivity, but this does not address learnability. This…
Looking for the best color palette? 😔 Check the tool we just created with @joseph_barbier: 🎨 2500+ palettes 🐍 Python Library to get them 🔍 Easy-to-use application to find your perfect match python-graph-gallery.com/color-palette-… Feedback welcome, we're working hard on this right now!
We are looking for more reviewers for the Cognitive Modeling and Computational Linguistics Workshop (CMCL @ ACL 2024). The deadline for reviews is June 25. Please contact me or cmclorganizers2024@gmail.com if you would like to be a reviewer! cmclorg.github.io #nlproc
I'm thrilled to share that I will become the next Director of the Machine Learning Department at Carnegie Mellon. MLD is a true gem, a department dedicated entirely to ML. Faculty and past directors have been personal role models in my career. cs.cmu.edu/news/2024/kolt…
📌 This paper investigates the dramatic breakdown of state-of-the-art LLMs' reasoning capabilities when confronted with a simple common sense problem called the "Alice In Wonderland (AIW) problem". This is despite their strong performance on standardized reasoning benchmarks.…
Excited to share that our paper "Tables as Texts or Images: Evaluating the Table Reasoning Ability of LLMs and MLLMs" has been accepted to #acl2024 findings. We just released an updated version: arxiv.org/pdf/2402.12424
Wrote up some thoughts on a growing problem I see with HCI conference submissions: the influx of what can only be called LLM wrapper papers, and what we might do about it. Here is "LLM Wrapper Papers are Hurting HCI Research": ianarawjo.medium.com/llm-wrapper-pa…
United States Trends
- 1. Mike 1,79 Mn posts
- 2. Serrano 236 B posts
- 3. #NetflixFight 70,5 B posts
- 4. Canelo 16 B posts
- 5. #netflixcrash 15,4 B posts
- 6. Father Time 10,7 B posts
- 7. Logan 77 B posts
- 8. Rosie Perez 14,6 B posts
- 9. Boxing 290 B posts
- 10. He's 58 23,6 B posts
- 11. Shaq 15,8 B posts
- 12. ROBBED 101 B posts
- 13. #buffering 10,7 B posts
- 14. My Netflix 82,1 B posts
- 15. Tori Kelly 5.103 posts
- 16. Ramos 70,1 B posts
- 17. Roy Jones 7.092 posts
- 18. Cedric 21,5 B posts
- 19. Gronk 6.552 posts
- 20. Barrios 50,4 B posts
Who to follow
-
Hao Zhu 朱昊
@_Hao_Zhu -
Jieyu Zhao
@jieyuzhao11 -
Weijia Shi
@WeijiaShi2 -
Weiyan Shi@EMNLP
@shi_weiyan -
Daniel Fried
@dan_fried -
Vijay V.
@vijaytarian -
Hila Chefer
@hila_chefer -
Xuhui Zhou@EMNLP 2024
@nlpxuhui -
Shuyan Zhou🛶EMNLP
@shuyanzhxyc -
Clara Na @ EMNLP
@claranahhh -
Xuezhe Ma (Max)
@MaxMa1987 -
Junjie Hu
@JunjieHu12 -
Emmy Liu
@_emliu -
Wanrong Zhu
@ZhuWanrong -
So Yeon (Tiffany) Min
@SoYeonTiffMin
Something went wrong.
Something went wrong.