Tessera

Gaurav Kamath

@grvkamath.bsky.social

PhD-ing at McGill Linguistics + Mila, working under Prof. Siva Reddy. Mostly computational linguistics, with some NLP; habitually disappointed Arsenal fan

43 Posts74 Follower 52 Folgt

Gaurav Kamath @grvkamath.bsky.social · 2mo ago

Super cool project that I really enjoyed being part of! tl;dr - when a human or model encounters new visual stimuli, how closely is it mapped to other, previously encountered concepts? (Come for weird dog-monster, stay for the science 🙂 )

Ada@adadtur.bsky.social · 2mo ago

Super excited to finally announce my latest research “Would you still call this Dax? Novel Visual References in VLMs and Humans”! We studied how vision-language models (VLMs) adopt new visual concepts and map them to language compared to humans, and found that…

Gaurav Kamath @grvkamath.bsky.social · 5mo ago

🚨New Paper!🚨 How do reasoning LLMs handle inferences that have no deterministic answer? We find that they diverge from humans in some significant ways, and fail to reflect human uncertainty… 🧵(1/10)

Gaurav Kamath @grvkamath.bsky.social · 6mo ago

Super cool interpretability work from @bennokrojer.bsky.social , that I think is also relevant to anyone interested in how word meanings are represented in LLMs!

Benno Krojer@bennokrojer.bsky.social · 6mo ago

🚨New paper Are visual tokens going into an LLM interpretable 🤔 Existing methods (e.g. logit lens) and assumptions would lead you to think “not much”... We propose LatentLens and show that most visual tokens are interpretable across *all* layers 💡 Details 🧵

Tom McCoy @rtommccoy.bsky.social · 12mo ago

🤖 🧠 NEW PAPER ON COGSCI & AI 🧠 🤖 Recent neural networks capture properties long thought to require symbols: compositionality, productivity, rapid learning So what role should symbols play in theories of the mind? For our answer...read on! Paper: arxiv.org/abs/2508.05776 1/n

The top shows the title and authors of the paper: "Whither symbols in the era of advanced neural networks?" by Tom Griffiths, Brenden Lake, Tom McCoy, Ellie Pavlick, and Taylor Webb.

At the bottom is text saying "Modern neural networks display capacities traditionally believed to require symbolic systems. This motivates a re-assessment of the role of symbols in cognitive theories."

In the middle is a graphic illustrating this text by showing three capacities: compositionality, productivity, and inductive biases. For each one, there is an illustration of a neural network displaying it. For compositionality, the illustration is DALL-E 3 creating an image of a teddy bear skateboarding in Times Square. For productivity, the illustration is novel words produced by GPT-2: "IKEA-ness", "nonneotropical", "Brazilianisms", "quackdom", "Smurfverse". For inductive biases, the illustration is a graph showing that a meta-learned neural network can learn formal languages from a small number of examples.

Proceedings of the National Academy of Sciences @pnas.org · 12mo ago

Using congressional speeches as a corpus, researchers quantify how younger and older adults adopt new meanings for words as language changes. Older people may be a bit slower to change, but can show considerable linguistic flexibility. In PNAS: www.pnas.org/doi/10.1073/...

Examples of word sense probability over the time range of the corpus.

Philip Ball @philipcball.bsky.social · last yr.

My latest column for @thenewworldmag.bsky.social looks at the question of how new meanings for words spread in the population. www.thenewworld.co.uk/philip-ball-...

Why we need to be more chill about language change

It appears that our vocabulary is entrained with the Zeitgeist, whether we like it or not

thenewworld.co.uk

Gaurav Kamath @grvkamath.bsky.social · last yr.

Our new paper in #PNAS (bit.ly/4fcWfma) presents a surprising finding—when words change meaning, older speakers rapidly adopt the new usage; inter-generational differences are often minor. w/ Michelle Yang, ‪@sivareddyg.bsky.social‬ , @msonderegger.bsky.social‬ and @dallascard.bsky.social‬👇(1/12)