Phu-Mon Htut (@phu_pmh) - Twitter Profili | Zamantika Mersobahis Locabet

Phu-Mon Htut retweetledi

Deli Chen@victor207755822·24 Nis

DeepSeek-V3: Dec 26, 2024 DeepSeek-V4: Apr 24, 2026 484 days later, we humbly share our labor of love. As always, we stay true to long-termism and open source for all. AGI belongs to everyone. ❤️🌍 #DeepSeekV4 #AGIforEveryone #OpenSource

DeepSeek@deepseek_ai

🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length. 🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models. 🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice. Try it now at chat.deepseek.com via Expert Mode / Instant Mode. API is updated & available today! 📄 Tech Report: huggingface.co/deepseek-ai/De… 🤗 Open Weights: huggingface.co/collections/de… 1/n

English

353

1.3K

13.1K

1M

Phu-Mon Htut retweetledi

Aishwarya Kamath@ashkamath20·8 Nis

We released Gemma 4 last week, and seeing the community's response has been amazing! 🚀 Honored to lead the vision efforts in which we made huge performance leaps from Gemma 3, I wanted to help you make the most of the new capabilities. Deep dive 🧵

English

26

107

904

47K

Phu-Mon Htut retweetledi

Junyang Lin@JustinLin610·26 Mar

x.com/i/article/2037…

ZXX

88

596

3.1K

876.1K

Phu-Mon Htut retweetledi

He He@hhexiy·25 Mar

x.com/i/article/2036…

ZXX

18

128

873

117.3K

Phu-Mon Htut retweetledi

Rheeya Uppaal@RUppaal·5 Oca

Journey Before Destination has been accepted to the main conference at #EACL! If you haven't already, read more about the paper here: uppaal.github.io/projects/visua… See you in Morocco! @eaclmeeting #EACL2026 #VLM #MultimodalAI #AIAlignment #ReasoningModels #Hallucinations

Rheeya Uppaal@RUppaal

How do you check your favourite VLM’s hallucination rate? Ask it questions about an image and verify the final answer - right? Wrong! Reasoning VLMs introduce a second dimension: the reasoning trace itself. If you only evaluate answers, your results can be deeply misleading. 🤔

English

0

1

7

449

Phu-Mon Htut retweetledi

Rheeya Uppaal@RUppaal·19 Ara

How do you check your favourite VLM’s hallucination rate? Ask it questions about an image and verify the final answer - right? Wrong! Reasoning VLMs introduce a second dimension: the reasoning trace itself. If you only evaluate answers, your results can be deeply misleading. 🤔

English

1

2

7

2.4K

Phu-Mon Htut retweetledi

Rheeya Uppaal@RUppaal·19 Ara

Joint work with @phu_pmh, Min Bai, Nikolaos Pappas, Zheng Qi, and Sandesh Swamy. Read more below! uppaal.github.io/projects/visua… #AI #ML #VLM #MultimodalAI #VisionLanguage #Interpretability #AIAlignment #ReasoningModels #Evaluation #Hallucinations #Multimodal #MachineLearning

English

0

1

2

136

Phu-Mon Htut retweetledi

Abhilasha Ravichander@lasha_nlp·1 Eki

It is PhD application season again 🍂 For those looking to do a PhD in AI, these are some useful resources 🤖: 1. Examples of statements of purpose (SOPs) for computer science PhD programs: cs-sop.org [1/4]

English

10

105

447

35.9K

Phu-Mon Htut retweetledi

Abhilasha Ravichander@lasha_nlp·22 Tem

Life update: I’m excited to share that I’ll be starting as faculty at the Max Planck Institute for Software Systems(@mpi_sws_) this Fall!🎉 I’ll be recruiting PhD students in the upcoming cycle, as well as research interns throughout the year: lasharavichander.github.io/contact.html

English

83

46

594

62.9K

Phu-Mon Htut retweetledi

Mimee @ PLSC 26’ // smart casual dark and academic@MimeeXu·19 Eyl

📣 The deadline for submitting a 4-page extended abstract has been extended to September 22, AoE. Emerging (+established) scholars are invited to our long-running NeurIPS workshop on Machine Learning for Systems, ft. a keynote by @JeffDean . mlforsystems.org #NeurIPS2024

Mimee @ PLSC 26’ // smart casual dark and academic tweet media

English

1

4

10

4.4K

Phu-Mon Htut@phu_pmh·10 Tem

I can’t make it to #ACL2023NLP but @najoungkim will be presenting our paper (QA)^2 today. Please check it out! 😇

Najoung Kim 🫠@najoungkim

I will be presenting (QA)^2 on Qs with questionable assumptions today (7/10) at the 14:00 poster session at #ACL2023NLP ! One important point that is less evident from the thread and the poster is that...

English

0

6

654

Phu-Mon Htut retweetledi

Gabriele Sarti@gsarti_·8 Tem

Heading to Toronto to attend ACL with the @GroNlp squad! 🍁 Will present: - Inseq, interpretability tool for generative LMs (arxiv.org/abs/2302.13942) - RAMP prompting for ACT (arxiv.org/abs/2305.17131) First ACL, or want to talk about LM interpretability? DMs open! 🤗

English

0

6

56

3.4K

Phu-Mon Htut retweetledi

Gabriele Sarti@gsarti_·29 May

Happy to share RAMP, a new prompting method to improve attribute-controlled MT capabilities of multilingual LLMs! 🌟 Work done at @AmazonScience w/ @phu_pmh, X. Niu, B. Hsu, A. Currey, @mnadejde and @gedinu, will appear in ACL 2023! Preprint: arxiv.org/abs/2305.17131

English

3

12

62

8.9K

Phu-Mon Htut retweetledi

Gabriele Sarti@gsarti_·16 May

Looking forward to presenting @InseqLib and my @AmazonScience internship paper in Toronto this summer! 🥳 Very thankful to all my amazing coauthors for this double #ACL2023NLP acceptance! 🤗

GroNLP@GroNlp

We're excited to share that our group members have 9 accepted papers at #ACL2023NLP Main/Findings/Demos! 🎉 Congrats to all authors and see you in Toronto! 🍁 #nlproc

English

3

49

7K

Phu-Mon Htut retweetledi

Najoung Kim 🫠@najoungkim·8 May

To be presented at ACL2023. The dataset's been up for a while but now sharing explicitly: github.com/najoungkim/qaqa

Najoung Kim 🫠@najoungkim

🦷 Another preprint 🦷 Information-seeking Qs often contain questionable assumptions that models should be robust to. "When did Marie Curie discover Uranium?" is an example. We propose (QA)^2, a test set evaluating the capacity to handle such Qs. (1/n) arxiv.org/abs/2212.10003

English

0

1

26

3.1K

Phu-Mon Htut retweetledi

NYU AI School '23@nyuaischool·16 Mar

After a very long time planning this, we're excited to announce applications are now open for the 4th NYU AI School *in-person* @NYUDataScience Rolling admits, so apply soon -- deadline April 6th! nyu-mll.github.io/nyu-ai-school-…

English

2

14

20

21.8K

Phu-Mon Htut@phu_pmh·21 Mar

@kchonyc incorrect but plausible :)

English

0

6

17.8K

Kyunghyun Cho@kchonyc·21 Mar

oh incorrect but plausible

English

3

0

2

4.1K

Kyunghyun Cho@kchonyc·21 Mar

#Bard makes a plausible mistake cc @geoffreyhinton

English

1

4

7.5K

Phu-Mon Htut@phu_pmh·22 Şub

@lasha_nlp @allen_ai @YejinChoinka @ai2_mosaic Congratulations, Lasha! :)

English

0

125

Abhilasha Ravichander@lasha_nlp·21 Şub

Exciting personal update!! I am thrilled to share that I defended my PhD #PHDone 🎉 Next steps: Young Investigator/Postdoc @allen_ai. I’m super excited to work with @YejinChoinka and the @ai2_mosaic team, as well as to join the vibrant NLP community in Seattle 🗻✨🧋☕️

English

41

11

369

25K

Phu-Mon Htut@phu_pmh·21 Ara

@najoungkim Preview 😛

English

0

1

70

Najoung Kim 🫠@najoungkim·21 Ara

Why no preview? arxiv.org/abs/2212.10003

English

1

0

2

798

Najoung Kim 🫠@najoungkim·21 Ara

🦷 Another preprint 🦷 Information-seeking Qs often contain questionable assumptions that models should be robust to. "When did Marie Curie discover Uranium?" is an example. We propose (QA)^2, a test set evaluating the capacity to handle such Qs. (1/n) arxiv.org/abs/2212.10003

English

4

9

55

27.3K

Phu-Mon Htut@phu_pmh·21 Ara

📢Check out our new paper arxiv.org/abs/2212.10003 w @najoungkim @sleepinyourhat @jowenpetty 😄🧵👇🏽

Najoung Kim 🫠@najoungkim

🦷 Another preprint 🦷 Information-seeking Qs often contain questionable assumptions that models should be robust to. "When did Marie Curie discover Uranium?" is an example. We propose (QA)^2, a test set evaluating the capacity to handle such Qs. (1/n) arxiv.org/abs/2212.10003

English

0

7

1.4K

Phu-Mon Htut

Keşfet