Center for Language and Speech Processing at @JohnsHopkins #NLProc #MachineLearning #AI https://teapaw.org/t.co/6IXR5OSQtw @jhuclsp@sigmoid.social
Baltimore, MD
Joined June 2016
- Tweets6K
- Following7.1K
- Followers8K
- Likes5.1K
JHU CLSP retweeted
An agent says “task complete.” How did it get there?
Did it test its changes, recover from errors, or revise its plan after human feedback?
We will be presenting our work on Act*ONOMY, a taxonomy for understanding and analyzing AI agent behavior, at NeurIPS 2026 in Sydney next month.
Developed through Grounded Theory, Act*ONOMY provides a shared vocabulary of 10 actions, 46 subactions, and 120 behavior categories. It links behavior labels to exact quotes in agent traces, helping researchers compare agents, inspect what agent does during runtime, and investigate potential failure patterns.
Explore the resources on our website（actonomy-agents.github.io/）:
🔎 A living and extensible taxonomy that can be expanded as AI agents evolve.
🧩 Annotated trajectories and reports. Follow agent runs and a human–agent coding session turn by turn, explore behavioral profiles, and inspect the evidence behind each annotation.
🛠️ Automated skills. Analyze your own agent traces and human–agent interactions, discover behaviors in new papers, and maintain or extend the taxonomy.
📄 Paper: arxiv.org/abs/2605.13625
🤗 Hugging Face dataset: huggingface.co/datasets/Soph…
💻 GitHub (code, datasets, and extension protocol): github.com/gaojie058/Act-ono…
We’re continuing to update the repository and taxonomy, and welcome feedback on the tools and codebook.
Many thanks to all my coauthors for their contributions to this work! @KaiserWhoLearns @JentseHuang @ktvank @SijieCesium @YuanCosette @shi_weiyan Zhuoran Lu @ZiangXiao @DanielKhashabi @mdredze
If you will be at NeurIPS in Sydney, I’d love to chat about how you study agent behavior and hear about your work!
JHU CLSP retweeted
Need different model weights? Just change them 🙃
Our new paper VFold does exactly that to enable low-overhead cross-layer value cache compression: half the value cache, >98% of full-cache performance 🧵
📄 arxiv.org/abs/2610.12338
JHU CLSP retweeted
Claude refuses to make an exact copy of The Landlord's Game, a game made in 1904 which has been in the public domain for decades.
JHU CLSP retweeted
Excited to share that I have reached 500 citations on Google Scholar! 🌟
This milestone doesn't just belong to me, but to all my amazing co-authors as well, without whom it would not have been possible.
JHU CLSP retweeted
Happy Halloween from Johns Hopkins Robotics!
Check out this cool demo of humanoid crawling created by my amazing colleagues
For Halloween, @geetachandra21 got our Unitree G1 to crawl like a spider!
Give Geeta (co-advised w/ @HaiminHu) a follow if you're interested in more humanoid demos.
We're doubling down on whole-body locomanipulation research at @HopkinsDSAI @HopkinsEngineer @JHUCompSci -- reach out if interested in working with us!
(credit to Addison Johnson, who helped design the mounts for the hands, and filmed this; and to Geeta who took a full-stack approach to ensuring that no humans or humanoids were harmed during the production of this video! and to @jloganolson for last year's humanoid crawling deo)
sciphylab.org/
JHU CLSP retweeted
Foundation models are trained in stages: pretraining, midtraining, and post-training. But is this separation fundamental?
We introduce unified training: a single algorithm for the full pipeline. This gives
⚙️ Simpler infrastructure
🔬 A framework for better science
(1/n)
JHU CLSP retweeted
Happy that Omnilingual MT got an Outstanding Paper Award at #EMNLP2026!
It's hopefully a step towards making omnilinguality normal rather than outstanding.
JHU CLSP retweeted
🎤✨ Our second keynote is LIVE!
We’re excited to have Prof. Berrak Sisman from @jhuclsp take the stage! 🚀
If you haven’t joined us yet, now’s the perfect time to tune in. Don’t miss out on this exciting session! 🌟
We’re live! 🎙️ The SALMA Workshop (@SALMAworkshop26) is now underway at #EMNLP2026 (@emnlpmeeting) in Room F9–F10. Stop by for an incredible slate of keynote speakers and cutting-edge papers on speech and audio language models!
Students who may not otherwise have access to application support are especially encouraged to apply.
Apply here: forms.gle/W2pXmman47CBoNZp9
Applications are due November 20. We hope to see yours!
JHU CLSP retweeted
I'd like to think there isn't a single neuron in my brain that would turn me into a psychopath if activated consistently. but who knows
if you have a qwen3.8 27b around, try steering L34 N3838 +0.75, now you have evil qwen 27b
for extra evil add L38 N17180 +0.75
same recipe as @_lyraaaa_: dose × median(‖resid‖ leaving layer L, tokens 1:) / ‖W_down[:, n]‖ at the down_proj input, every token
JHU CLSP retweeted
>its kimi
Today we announce the launch of the Giotto family of models. We are unveiling Giotto Alto and Giotto Solo, the smartest European sovereign AI models on the market.
Giotto Alto is our flagship model built for advanced reasoning capabilities, free for everyone and available on the App Store and Google Play. It is hosted on European cloud infrastructure, so your data stays in Europe. Giotto Solo is the smartest model that runs on a single GPU, so organisations can keep their AI on their own infrastructure.
We are a Swiss lab with a European heart and we built this so that Europe can run advanced AI on its own terms.
Use Giotto: cloud.giotto.ai/
Readers added context they thought people might want to know
Giotto's graphic shows self-reported benchmark scores comparing to specific variants of other models; independent leaderboards as of late Oct 2026 list no Giotto and different leading scores on AIME 2026, GPQA-Diamond and HLE.
giotto.ai
benchlm.ai/benchmarks/aim…
benchlm.ai/benchmarks/gpq…
benchlm.ai/benchmarks/hle
JHU CLSP retweeted
Wow! Congratulations @hanjie_chen !!!
Excited to share that we received two Outstanding Paper Awards at #EMNLP2026🔥
Congratulations to the student leads and the teams!🎉
Many thanks to the program chairs and committee for this recognition!💙
JHU CLSP retweeted
The first panel discussion, "When AI Chooses What You See, Who Chooses What You Do? AI, Information, and Human Agency," is happening now. #HopkinsDSAI
ALT Four panelists and one moderator sitting at the front of an auditorium. There are many people in the audience.
JHU CLSP retweeted
The Data Science and AI Institute Fall 2026 Symposium: Artificial Intelligence and Human Learning kicked off with remarks from Mark Dredze, director of DSAI. #HopkinsDSAI
ALT A man standing at a podium on the right, with a slide on the left. There are people in the audience.
JHU CLSP retweeted
Berrak is great! Would definitely recommend getting in touch with her if you're interested.
I am attending #EMNLP2026 and recruiting PhD students for Fall 2027 at JHU @jhuclsp. Research topics include speech and audio foundation models, expressive speech, healthcare, and mechanistic interpretability.
If you’re interested, I will be at our posters with my students.