David Mortensen

5.4K posts

David Mortensen

David Mortensen

@dmort27

I make colorless green GPUs sleep brriously @LTIatCMU. phonology • morphology • language change • #NLProc data resources.

Pittsburgh, PA شامل ہوئے Haziran 2009
1.7K فالونگ2.1K فالوورز
David Mortensen ری ٹویٹ کیا
Neil Renic
Neil Renic@NC_Renic·
if academics are so smart why can't they connect to eduroam?
English
41
401
4K
187K
David Mortensen ری ٹویٹ کیا
Pranjal Aggarwal ✈️ ICLR'26
Pranjal Aggarwal ✈️ ICLR'26@PranjalAggarw16·
LLMs often generate incorrect code. Instead, what if they can generate provably correct code? Presenting AlphaVerus: A self-reinforcing method that automatically learns to generate mathematically correct code using inference-time search and verifier feedback. 🧵
English
1
19
84
18.8K
David Mortensen
David Mortensen@dmort27·
LLMs learn to generalize morphological derivation by analogy from exemplars rather than rules (which is probably also true of humans). However, their behavior is different from human morphological behavior in interesting ways. Read our paper to find out how.
Valentin Hofmann@vjhofmann

📢 New paper 📢 What generalization mechanisms shape the language skills of LLMs? Prior work has claimed that LLMs learn language via rules. We revisit the question and find that superficially rule-like behavior of LLMs can be traced to underlying analogical processes. 🧵

English
1
3
19
1K
David Mortensen ری ٹویٹ کیا
Valentin Hofmann
Valentin Hofmann@vjhofmann·
📢 New paper 📢 What generalization mechanisms shape the language skills of LLMs? Prior work has claimed that LLMs learn language via rules. We revisit the question and find that superficially rule-like behavior of LLMs can be traced to underlying analogical processes. 🧵
Valentin Hofmann tweet media
English
5
13
65
9.8K
David Mortensen ری ٹویٹ کیا
So Yeon (Tiffany) Min
So Yeon (Tiffany) Min@SoYeonTiffMin·
I am on the industry job market, and am planning to interview around next March. I am attending @NeurIPSConf, and I hope to meet you there if you are hiring! My website: soyeonm.github.io Short bio about me: I am a 5th year PhD student at CMU MLD, working with @rsalakhu and @ybisk. My current research focuses on the confidence of LLM agents - how LLM agents can assess their own limitations and determine when to leverage increased inference compute, larger models, or human intervention. I am a recipient of Apple AI/ML Scholars Fellowship for 2023. I have interned at Apple AI/ML and Meta FAIR. My research has been recognized through multiple features in CMU news. I hold B.S., M.Eng from MIT EECS. I am also presenting two of my recent works: Embodied-RAG/Situated Instruction Following in AFM and LangGame workshops. RT appreciated!
English
0
56
136
28.2K
David Mortensen ری ٹویٹ کیا
Kanishka Misra 🌊
Kanishka Misra 🌊@kanishkamisra·
🙏 really a lucky cherry on top because working with Kyle itself is an award!
Kyle Mahowald@kmahowald

Chuffed that @kanishkamisra on “controlled rearing” to learn the “a beautiful five days in Miami” arxiv.org/abs/2403.19827 construction won an EMNLP Outstanding Paper Award! And delighted that the ACL community saw fit to recognize a paper about an odd little ling construction.

English
10
3
73
4.3K
David Mortensen ری ٹویٹ کیا
Simran Khanuja
Simran Khanuja@simi_97k·
Thank you so much @emnlpmeeting for this wonderful recognition! I’m so honored and humbled 💕 Thanks @gneubig for your support throughout! We’ve been working on this for 1.5 years and everyone who has spoken with me in the recent past knows how passionately I feel about this work and this task in general 🥹 Thanks again to everyone who recognized and appreciated our efforts ✨
EMNLP 2026@emnlpmeeting

#EMNLP2024 Best Paper 1/5: An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevance

English
77
32
447
61.8K
David Mortensen ری ٹویٹ کیا
Shinji Watanabe
Shinji Watanabe@shinjiw_at_cmu·
Congratulations, @chenwanch1, for the EMNLP Best Paper Award!!! I'm super happy!
Shinji Watanabe tweet mediaShinji Watanabe tweet media
English
11
16
213
35.6K
David Mortensen ری ٹویٹ کیا
EMNLP 2026
EMNLP 2026@emnlpmeeting·
#EMNLP2024 Best Paper 2/5: Towards Robust Speech Representation Learning for Thousands of Languages
EMNLP 2026 tweet media
English
1
8
49
14.9K
David Mortensen ری ٹویٹ کیا
EMNLP 2026
EMNLP 2026@emnlpmeeting·
#EMNLP2024 Best Paper 1/5: An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevance
EMNLP 2026 tweet media
English
2
11
81
63.8K
David Mortensen ری ٹویٹ کیا
Jason Eisner
Jason Eisner@adveisner·
Who wants to come to JHU and do a postdoc with me?? I'm always enthusiastic about new modeling / inference / algorithmic ideas in NLP/ML. Also selected applications.
Johns Hopkins Data Science and AI Institute@HopkinsDSAI

We’re thrilled to announce the #HopkinsDSAI Postdoctoral Fellowship Program! We’re looking for candidates across all areas of data science and AI, including science, health, medicine, the humanities, engineering, policy, and ethics. Apply today! ai.jhu.edu/postdoctoral-f…

English
2
8
40
8.7K
David Mortensen ری ٹویٹ کیا
Terrible Maps
Terrible Maps@TerribleMaps·
Countries Featured in Poland's National Anthem
Terrible Maps tweet media
English
204
730
26.8K
2M
David Mortensen ری ٹویٹ کیا
Andreas Opedal
Andreas Opedal@OpedalAndreas·
💥 New #EMNLP2024 main paper 💥 It’s pretty established by now that the in-context log probability of a word, called surprisal, is predictive of the time the word takes to read. But how important is contextual information, really? Summary below 🧵 arxiv.org/abs/2409.08160
Andreas Opedal tweet media
English
2
5
39
7.5K
David Mortensen ری ٹویٹ کیا
Gravitational Lens
Gravitational Lens@cation_motion·
OMG, this is killing me 😂😂😂
Gravitational Lens tweet media
English
69
788
6.3K
651.2K
David Mortensen ری ٹویٹ کیا
Shinji Watanabe
Shinji Watanabe@shinjiw_at_cmu·
We are thrilled to announce the Interspeech 2025 URGENT Challenge, starting on 11/15! Join us in building universal speech enhancement models to tackle in-the-wild speech data using large-scale, multilingual data. Details: urgent-challenge.github.io/urgent2025/
Shinji Watanabe tweet media
English
1
43
113
11.9K
David Mortensen ری ٹویٹ کیا
Joel Mire
Joel Mire@Joel_Mire·
I’m thrilled to be at EMNLP this week presenting our paper, “The Empirical Variability of Narrative Perceptions of Social Media Texts” I’ll be giving an oral presentation during the CSS + Cultural Analytics Session 2 (Nov 14). Paper: aclanthology.org/2024.emnlp-mai… 🧵(1/12)
Joel Mire tweet media
English
1
11
33
4K