Freda Shi
@fredahshi
Assistant Professor @UWCheritonCS, @CIFAR_News AI Chair @VectorInst, @ReviewAcl Co-CTO | PhD @TTIC_Connect | Excited about "grounding" in any form
I'll be at #ACL2025NLP from next Monday to Wednesday! Here's a snapshot of my first batch of papers as the last author, plus helping the amazing lab member @xLuo_CompLing to present her TACL work after being in the audience for 3 times. DM me if you'd like to catch up in person!
🛬The City Airport Train (CAT) 🚆 offers the fastest connection from Vienna Airport to the city. Purchase your tickets online in advance and get 20% off with code ACL2025. 👉 cityairporttrain.com/en/
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]
Awesome-LLM-Papers-by-Tom ^ Another example that parsing is helpful to resolve syntactic ambiguity.
So much research is being done about LLMs that it's hard to stay on top of the literature. To help with this, I've made a list of all the most important papers from the past 8 years: rtmccoy.com/pubs/ I hope you enjoy!
I also forgot to mention that we're organizing a workshop that particularly focused on space, a highly interesting and interdisciplinary field with an amazing lineup of speakers (see poster!) You are all invited to submit & participate!
📣 Excited to announce SpaVLE: #NeurIPS2025 Workshop on Space in Vision, Language, and Embodied AI! 👉 …vision-language-embodied-ai.github.io 🦾Co-organized with an incredible team → @fredahshi · @maojiayuan · @DJiafei · @ManlingLi_ · David Hsu · @Kordjamshidi 🌌 Why Space & SpaVLE? We…
Otw to Vancouver for #ICML25! Shuo Xie and I will be presenting our joint work with Kunhe Yang(@KunheYang): “Should Decision-Makers Reveal Classifiers in Online Strategic Classification?” We ask: can hiding the model help reduce errors caused by human strategic manipulation?
The Austrian Academy of Sciences is offering a pretty generous package to researchers in the US who would like to come to Austria for a postdoc. stipendien.oeaw.ac.at/en/fellowships…. Please email me if you're interested in applying for this by Jul 25 🧑🔬
committed to doing my part in decreasing reviewer workload by writing fewer papers
Our study on pragmatic generation is accepted to #COLM2025! Missed the first COLM last year (no suitable ongoing project at the time😅). Heard it’s a great place to connect with LM folks, excited to join for round two finally.
Vision-Language Models (VLMs) can describe the environment, but can they refer within it? Our findings reveal a critical gap: VLMs fall short of pragmatic optimality. We identify 3 key failures of pragmatic competence in referring expression generation with VLMs: (1) cannot…
how much does the last layer of a VLM retain the original image? i trained a linear probe on the output features of several CLIP/SigLIP models on image reconstruction, and found that *only* with SigLIP, if you multiply the input by 10-100, pixels get reconstructed perfectly??
#ICML #cognition #GrowAI We spent 2 years carefully curated every single experiment (i.e. object permanence, A-not-B task, visual cliff task) in this dataset (total: 1503 classic experiments spanning 12 core cognitive concepts). We spent another year to get 230 MLLMs evaluated…
This year, there have been various pieces of evidence that AI agents are starting to be able to conduct scientific research and produce papers end-to-end, at a level where some of these generated papers were already accepted by top-tier conferences/workshops. Intology’s…
Dear PhD students now regretting taking offers at US schools: If you turned down PhD offers in Canada, but want to rethink that, email the professors who were trying to recruit you. They might be able to pull some strings. Your sane neighbor to the north, Canada