iiinova — where your digital self keeps evolving

Reposted by Tomás Vergara Browne

Gaurav Kamath @grvkamath.bsky.social · 04/03/2026

🚨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)

35820

Reposted by Tomás Vergara Browne

Gaurav Kamath @grvkamath.bsky.social · 29/07/2025

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)

33317

Reposted by Tomás Vergara Browne

Benno Krojer @bennokrojer.bsky.social · 25/06/2025

Started a new podcast with @tomvergara.bsky.social ! Behind the Research of AI: We look behind the scenes, beyond the polished papers 🧐🧪 If this sounds fun, check out our first "official" episode with the awesome Gauthier Gidel from @mila-quebec.bsky.social : open.spotify.com/episode/7oTc...

open.spotify.com

02 | Gauthier Gidel: Bridging Theory and Deep Learning, Vibes at Mila, and the Effects of AI on Art

Behind the Research of AI · Episode

1176

Reposted by Tomás Vergara Browne

Benno Krojer @bennokrojer.bsky.social · 15/04/2025

Overall I loved the paper, got lots of inspiration from it and would love to be part of a similar project in the future: for example an empirical investigation of many AI papers to answer "To what extent is AI is a science?"

011

Reposted by Tomás Vergara Browne

Sara Vera Marjanovic @saravera.bsky.social · 01/04/2025

Models like DeepSeek-R1 🐋 mark a fundamental shift in how LLMs approach complex problems. In our preprint on R1 Thoughtology, we study R1’s reasoning chains across a variety of tasks; investigating its capabilities, limitations, and behaviour. 🔗: mcgill-nlp.github.io/thoughtology/

A circular diagram with a blue whale icon at the center. The diagram shows 8 interconnected research areas around LLM reasoning represented as colored rectangular boxes arranged in a circular pattern. The areas include: §3 Analysis of Reasoning Chains (central cloud), §4 Scaling of Thoughts (discussing thought length and performance metrics), §5 Long Context Evaluation (focusing on information recall), §6 Faithfulness to Context (examining question answering accuracy), §7 Safety Evaluation (assessing harmful content generation and jailbreak resistance), §8 Language & Culture (exploring moral reasoning and language effects), §9 Relation to Human Processing (comparing cognitive processes), §10 Visual Reasoning (covering ASCII generation capabilities), and §11 Following Token Budget (investigating direct prompting techniques). Arrows connect the sections in a clockwise flow, suggesting an iterative research methodology.

15116

Reposted by Tomás Vergara Browne

Parishad BehnamGhader @parishadbehnam.bsky.social · 12/03/2025

Instruction-following retrievers can efficiently and accurately search for harmful and sensitive information on the internet! 🌐💣 Retrievers need to be aligned too! 🚨🚨🚨 Work done with the wonderful Nick and @sivareddyg.bsky.social 🔗 mcgill-nlp.github.io/malicious-ir/ Thread: 🧵👇

mcgill-nlp.github.io

Exploiting Instruction-Following Retrievers for Malicious Information Retrieval

Parishad BehnamGhader, Nicholas Meade, Siva Reddy

1118

Reposted by Tomás Vergara Browne

Xing Han Lu @xhluca.bsky.social · 10/03/2025

Agents like OpenAI Operator can solve complex computer tasks, but what happens when users use them to cause harm, e.g. spread misinformation? To find out, we introduce SafeArena (safearena.github.io), a benchmark to assess the capabilities of web agents to complete harmful web tasks. A thread 👇

1167

Reposted by Tomás Vergara Browne

Vagrant Gautam @dippedrusk.com · 20/11/2024

After a fun and long #EMNLP2024 I'm now travelling AGAIN to Uppsala 🇸🇪, to speak at the Transdisciplinary Queer Futures of AI Conference! Any Sweden/Uppsala recs?

Me presenting my TACL paper with slides to a big room of people

Me at a poster about our work understanding "democratization" in AI research

Me, Mor Geva, Marius Mosbach and Tomás Vergara-Browne in front of our poster about the impact of interpretability and analysis work on NLP

Me and Julius Steuer presenting WinoPron, our new dataset that fixes issues with the original English Winogender Schemas dataset

1161