Postdoc @coastalcph and @MATSprogram fellow doing NLP things. Ex SWE @Google and student @dccuchile. I also like sports, photography, and reading.
Joined April 2010
- Tweets442
- Following867
- Followers619
- Likes2.4K
Constanza Fierro retweeted
New paper: you can make LLMs leak their hidden secrets by amplifying their reasoning weights beyond training through "overthinking." Here's how it works:
Constanza Fierro retweeted
How does visual information reach the final token in Vision-Language models?
We study information flow in different VLMs and find that they do not rely on a single mechanism.
Instead, VLMs dynamically switch between two different pathways. 🧵
I’m presenting this work today at #ICLR2026 at 3:15pm in Pavilion 4 #3914
Come say hi! ☺️
Constanza Fierro retweeted
At the #Neurips2025 mechanistic interpretability workshop I gave a brief talk about Venetian glassmaking, since I think we face a similar moment in AI research today.
Here is a blog post summarizing the talk:
davidbau.com/archives/2025/1…
Can we find weight directions to modify LLM's behaviors?
Our new paper proposes contrastive weight steering, an alternative to activation steering for modifying behaviors using small narrow distribution data 🕹️
🧵👇
Check out the paper and blogpost for more details:
Paper: arxiv.org/abs/2511.05408
