Juan Diego Rodríguez (he/him)
@juand_r_nlp
CS PhD student at UT Austin in #NLP Interested in language, reasoning, semantics and cognitive science. You can also find me over at the other site 🦋
Bunları beğenebilirsin
If you're 13 right now here's what you should do: Spend all your time reading philosophy, sci fi, poetry, and history. Go to museums and look at every damn thing in there. Watch all the classic films and maybe every single movie made in the 90s. Learn how to write prose,…
When we sat down with @alexandr_wang at Meta Connect 2025, he shared his advice for young people: “If you’re 13 right now, you should spend all your time vibe coding. This is the Bill Gates, Mark Zuckerberg moment. The people who grow up with these tools will have an immense…
🤣
If you are interested in winning an ACL paper award, it's a very smart move is to write something with @kmahowald. Historically, he has won at least one each year for as long as I can remember.
Delighted Sasha's work using mech interp to study complex syntax constructions won an Outstanding Paper Award at EMNLP! And delighted the ACL community continues to recognize unabashedly linguistic topics like filler-gaps, and the huge potential for LMs to inform such topics!
🚨 Announcing a new LLM calibration method, DINCO, which enforces confidence coherence (that probs must sum to 1) by having the LLM verbalize its confidence independently on self-generated distractors, and normalizing by the total confidence. Major gains on long + short-form QA!
🚨 Introducing DINCO, a zero-resource calibration method for verbalized LLM confidence. We normalize over self-generated distractors to enforce coherence ➡️ better-calibrated and less saturated (more usable) confidence! ⚠️ Problem: Standard verbalized confidence is overconfident…
COLM Keynote: Nicholas Carlini Are LLMs worth it? youtube.com/watch?v=PngHcm…
youtube.com
YouTube
Nicholas Carlini - Are LLMs worth it?
I’ll be in Boston attending BUCLD this week — I won’t be presenting but I’ll be cheering on @najoungkim who will present at the prestigious SLD symposium about the awesome work by her group, including our work on LMs as hypotheses generators for language acquisition! 🤠👻
Dear “15-18 yo founder”s sending me DMs, don’t. Go and hug your parents, fall in love, eat chocolate cereal for breakfast, read poetry. Nobody will give you back these years. And sure, do your homework and learn math and code if that feels fun. But stop building SaaS and…
“For a glorious decade in the 2010s, we all worked on better neural network architectures, but after that we just worked on scaling transformers and making them more efficient”
The Computer Science section of @arxiv is now requiring prior peer review for Literature Surveys and Position Papers. Details in a new blog post
236 direct/indirect PhD students!! Based on OpenReview data, an interactive webpage: prakashkagitha.github.io/manningphdtree/ Your course, NLP with Deep learning - Winter 2017, on YouTube, was my introduction to building deep learning models. This is the least I could do to say Thank You!!
Thanks! 😊 But it’d be really good to generate an updated version of those graphs!
I'm super excited to update that "Lost in Automatic Translation" is now available as an audiobook! 🔊📖 It's currently on Audible: audible.ca/pd/B0FXY8VQX5 Stay tuned (lostinautomatictranslation.com) for more retailers, including Amazon, iTunes, etc., and public libraries! 📚
A thread on the equilibria of pendulums and their connection to topology. 1/n
We’re drowning in language models — there are over 2 mil. of them on Huggingface! Can we use some of them to understand which computational ingredients — architecture, scale, post-training, etc. – help us build models that align with human representations? Read on to find out 🧵
one thing that really became clear to me (which admittedly makes me publish much less) is that, especially as academics, "beating the state of the art" is a crap target to aim for. the objective should be to replace the state of the art. (of course, this is unfortunately super…
𝑵𝒆𝒘 𝒃𝒍𝒐𝒈𝒑𝒐𝒔𝒕! In which I give some brief reflections on #COLM2025 and give a rundown of a few great papers I checked out!
I will be giving a short talk on this work at the COLM Interplay workshop on Friday (also to appear at EMNLP)! Will be in Montreal all week and excited to chat about LM interpretability + it’s interaction with human cognition and ling theory.
A key hypothesis in the history of linguistics is that different constructions share underlying structure. We take advantage of recent advances in mechanistic interpretability to test this hypothesis in Language Models. New work with @kmahowald and @ChrisGPotts! 🧵👇
Happy to announce the first workshop on Pragmatic Reasoning in Language Models — PragLM @ COLM 2025! 🧠🎉 How do LLMs engage in pragmatic reasoning, and what core pragmatic capacities remain beyond their reach? 🌐 sites.google.com/berkeley.edu/p… 📅 Submit by June 23rd
Interested in language models, brains, and concepts? Check out our COLM 2025 🔦 Spotlight paper! (And if you’re at COLM, come hear about it on Tuesday – sessions Spotlight 2 & Poster 2)!
Our paper "ChartMuseum 🖼️" is now accepted to #NeurIPS2025 Datasets and Benchmarks Track! Even the latest models, such as GPT-5 and Gemini-2.5-Pro, still cannot do well on challenging 📉chart understanding questions , especially on those that involve visual reasoning 👀!
Introducing ChartMuseum🖼️, testing visual reasoning with diverse real-world charts! ✍🏻Entirely human-written questions by 13 CS researchers 👀Emphasis on visual reasoning – hard to be verbalized via text CoTs 📉Humans reach 93% but 63% from Gemini-2.5-Pro & 38% from Qwen2.5-72B
Accepted at #NeurIPS2025 -- super proud of Yulu and Dheeraj for leading this! Be on the lookout for more "nuanced yes/no" work from them in the future 👀
![yulu_qin's tweet image. Does vision training change how language is represented and used in meaningful ways?🤔 The answer is a nuanced yes! Comparing VLM-LM minimal pairs, we find that while the taxonomic organization of the lexicon is similar, VLMs are better at _deploying_ this knowledge. [1/9]](https://pbs.twimg.com/media/GwZPQE5WUAUeZkZ.jpg)
United States Trendler
- 1. Cheney 66.3K posts
- 2. Sedition 125K posts
- 3. First Take 45K posts
- 4. Treason 76.4K posts
- 5. Mark Walter N/A
- 6. Cam Newton 3,528 posts
- 7. Buss 7,682 posts
- 8. #WeekndTourLeaks 1,433 posts
- 9. Jeanie N/A
- 10. Trump and Vance 34.3K posts
- 11. SEDITIOUS BEHAVIOR 25.4K posts
- 12. #ExpediaChat 1,151 posts
- 13. Constitution 97.3K posts
- 14. Nano Banana Pro 19.9K posts
- 15. Stephen A 41.1K posts
- 16. Commander in Chief 43.2K posts
- 17. #Geeksgiving25 N/A
- 18. Shayy 10.1K posts
- 19. Coast Guard 14.1K posts
- 20. Bush 62K posts
Bunları beğenebilirsin
-
Tanya Goyal
@tanyaagoyal -
Puyuan Peng
@PuyuanPeng -
Jessy Li
@jessyjli -
Prasann Singhal
@prasann_singhal -
Greg Durrett
@gregd_nlp -
Yasumasa Onoe
@yasumasa_onoe -
Xi Ye
@xiye_nlp -
Freda Shi @EMNLP 2025
@fredahshi -
Nathan Schneider
@complingy -
Shiyue Zhang
@byryuer -
Fangyuan Xu
@brunchavecmoi -
Isabel Papadimitriou
@isabelpapad -
Eunsol Choi
@eunsolc -
Hung-Ting Chen
@hungting_chen -
Kaj Bostrom
@alephic2
Something went wrong.
Something went wrong.