iiinova — where your digital self keeps evolving

Reposted by Shane Storks

Maria Leonor Pacheco @mlpacheco.bsky.social · 04/07/2026

I need *several* emergency reviewers on on mech interp for NLP. I also need emergency reviewers for papers on neuro-symbolic language reasoning, for a paper extracting symbolic structures from text, and for a paper on knowledge collapse in LLMs. Many missing reviews this cycle

174

Shane Storks @shanestorks.bsky.social · 04/07/2026

🚨 I’m still seeking an emergency reviewer for an ARR May 2026 submission on LLM-based image segmentation. Please DM me if you’re qualified to review for ARR (at least 2 ACL/AI conference pubs and 1 other pub), and could complete a review for it in the next couple days! 🙏

001

Reposted by Shane Storks

Queer in AI @queerinai.com · 01/07/2026

Pride month may be coming to an end, but the party isn’t! 🏳️‍🌈🏳️‍⚧️ Join Queer in AI and friends at aclmeeting.bsky.social / #ACL2026NLP on Sunday, July 5! 🍱 BYO Lunch Social — 12:30–14:00 🥂🍻🍹 Evening Social — 19:00–22:00 All welcome! More details & sign-up 👉 queerinai.com/acl-2026

012

Shane Storks @shanestorks.bsky.social · 05/05/2026

SAEs identify interpretable features in LLM layers, but what can we learn from how they activate together? 🤖📊 New #ACL2026NLP paper with Ruixuan Deng, Nick Hu, Miles Gilberti, and others reveals causal semantic modules composed of many co-activating features across LLM layers. 🧵

Screenshot of Figure 1 from the linked paper. (A) Our work extracts semantic modules from SAE features involves prompting an LLM, collecting SAE activations, constructing a network of coactivations, pruning it by feature activation density, identifying connected components, then performing causal analysis. (B) The resulting components represent concepts and relations in context-consistent ways, such as the country of China or the capital city of a country. (C) When we ablate features associated with these components, we can cause an LLM to output counterfactual information that defies prompt instructions in predictable and compositional ways.

161

Shane Storks @shanestorks.bsky.social · 06/04/2026

Happy news: I'll be joining Eastern Michigan University as an Assistant Professor of Computer Science in Fall 2026! If you're an EMU student interested in my research, let's connect 👋 Will be sharing some fun #ACL2026NLP papers from my postdoc soon!

381

Reposted by Shane Storks

Giuseppe Attanasio @gattanasio.cc · 10/02/2026

Hello #NLProc #ACL2026NLP people. I am looking for **two emergency reviewers** in the Safety and Alignment in LLMs track for ACL/ARR. Reviews are due Feb 15th. Please DM if interested and available. Happy to offer drinks/food if you live in/pass by Lisbon ☀️

0610

Reposted by Shane Storks

Jeremy Barnes @jeremy-nlp.bsky.social · 10/02/2026

Seems to be a common situation for ACs this round, but I'm also looking for two emergency reviewers for the January #ARR Evaluation and Resources track. I'd appreciate any help (reposts, encouragement, black magic...)

046

Reposted by Shane Storks

Martin Tutek @mtutek.bsky.social · 10/02/2026

I'm looking for two emergency reviewers 🧑‍🚒👩‍🚒 for the ARR January Generalizability and Transfer track. Please reach out if you have time & qualify for review or RT for visibility🙏🙏

026

Reposted by Shane Storks

Tom McCoy @rtommccoy.bsky.social · 10/02/2026

I could use an emergency reviewer for an ACL submission involving interpretability and syntax. Please DM me if you might be able to provide an emergency review before February 15!

144

Reposted by Shane Storks

Nils Feldhus @nfel.bsky.social · 09/02/2026

Looking for emergency reviewers for ARR Special Track "Explainability of NLP Models". Topics: Faithfulness, mechanistic interpretability, surveys and position papers. Deadline Feb 14 AoE. #ACL2026NLP

187

Reposted by Shane Storks

Stephanie Brandl @stephaniebrandl.bsky.social · 10/02/2026

I am looking for 2 emergency reviewers for the ARR Ethics, Bias & Fairness track. Please DM me if you are available 🙏

066

Shane Storks @shanestorks.bsky.social · 10/02/2026

Hello #NLProc #ACL2026NLP community, I'm looking for an emergency reviewer for an ARR submission on LLM interpretability. If you're available to complete a review before Feb 15, please reply or DM 🙏

026

Shane Storks @shanestorks.bsky.social · 20/08/2025

This work finally has a home! Looking forward to presenting “Transparent and Coherent Procedural Mistake Detection” at #EMNLP2025 🤩

000

Reposted by Shane Storks

Ai2 @ai2.bsky.social · 26/03/2025

Meet Ai2 Paper Finder, an LLM-powered literature search system. Searching for relevant work is a multi-step process that requires iteration. Paper Finder mimics this workflow — and helps researchers find more papers than ever 🔍

Screenshot of the Ai2 Paper Finder interface

611723

Reposted by Shane Storks

EMNLP @emnlpmeeting.bsky.social · 14/02/2025

The EMNLP 2025 conference website and CfP are now live! 2025.emnlp.org/calls/main-c... Conference dates: November 5-9 in Suzhou, China Submissions will be through ARR, and this year's theme is Interdisciplinary Recontextualization of NLP

2025.emnlp.org

Call for Main Conference Papers

Official website for the 2025 Conference on Empirical Methods in Natural Language Processing

0257

Reposted by Shane Storks

Queer in AI @queerinai.com · 03/02/2025

Our workshop has been extended till Feb 20. We are looking forward for your papers at NAACL's Queer in AI workshop.

01717

Reposted by Shane Storks

Alex Hanna @alexhanna.bsky.social · 24/01/2025

One of ways in which AI hype men are highly copacetic with Trump is that they think you can assert things with absolutely no care for truth or feasibility. Bullshitters par excellence

3507

Shane Storks @shanestorks.bsky.social · 21/01/2025

Some happy news: my dissertation on "Coherent Physical Commonsense Reasoning in Foundational Language Models" is finally available online! 🎓https://deepblue.lib.umich.edu/handle/2027.42/196025

deepblue.lib.umich.edu

Coherent Physical Commonsense Reasoning in Foundational Language Models

030

Shane Storks @shanestorks.bsky.social · 08/01/2025

📣 UMich undergraduate/master students: are you interested in research at the intersection of LLMs and cognitive science, but need guidance and computing resources? I want to work with you! If interested, DM/email me with your CV and a brief project proposal!

142

Shane Storks @shanestorks.bsky.social · 17/12/2024

How well can VLMs detect and explain humans' procedural mistakes, like in cooking or assembly? 🧑‍🍳🧑‍🔧 My new pre-print with Itamar Bar-Yossef, Yayuan Li, Zheyuan Zhang, Jason J. Corso, and Joyce Chai dives into this! arxiv.org/pdf/2412.11927

Dialog between a foundational VLM and itself to detect the incomplete state of the procedure "Unclip the pegs on the cloth" in an image showing a cloth pegged to a clothing line. The VLM generates the following questions and answers: 1. "Is there a cloth in the image? Yes", 2. "Are there pegs on the cloth? Yes", and 3. "Is there someone holding pegs? No". As the VLM asks these questions it becomes more confident that the procedure has not been successfully completed.

130