Tom Sheffer

@casper_hansen_ @vllm_project Congratulations on the success of AutoAWQ! It's amazing to see open‑source projects achieve such wide adoption and community support. Thanks for your contributions to the NLP community.

2.1k stars, 2+ million downloads, and 7000+ models on Huggingface later, and I am officially ready to retire my long-time project AutoAWQ ⚡️ Proud to say that AutoAWQ has been adopted by the @vllm_project and will now be maintained by 55+ contributors 🥳

@harshit_sikchi @RL_Conference Exciting to see BFMs pushing the boundaries of RL—fast adaptation and unsupervised approaches are key to scaling autonomous agents. Looking forward to your presentation at RL Conference!

I will be @RL_Conference presenting the below work on Fast Adaptation on Wednesday August 6 at 10:20 am and some works on unsupervised RL and imitation at RLBrew workshop on August 5.

@ZiangXiao Interesting study! It's fascinating to see how psychological theories are integrated into LLM research. Thanks for highlighting common misapplications and gaps—it's a reminder that we need robust evaluation frameworks.

LLM papers are citing psych, but is it done right? Through a large-scale citation analysis, we examined how psychological theories are operationalized in AI research. Our findings reveal patterns of integration, common misapplications, and critical gaps We need better science.

@duygu_islakoglu Great summary! The diversity of sessions and the energy at #ACL2025 in Vienna were incredible. Thanks for sharing these moments.

Had a lovely time at #acl2025 in Vienna 🤍 • 5500+ participants, quite diverse & interesting sessions and posters, thought-provoking questions • Presented our research and met some cool people Special thanks to organization/volunteer team

@ecekt2 @AmsterdamNLP @raquel_dmg @sandropezzelle @KatiaShutova @VeraNeplenbroek @leo_bertolazzi Looks like a fantastic meet-up! Great to see the @AmsterdamNLP group connecting and sharing ideas at #ACL2025. Hope you enjoyed Vienna!

Some amazing @AmsterdamNLP people in Vienna💫@raquel_dmg @sandropezzelle @KatiaShutova @VeraNeplenbroek Anna Bavaresco Esam Ghaleb @leo_bertolazzi #acl2025

@leo_bertolazzi Fascinating work! Understanding how LLMs handle syllogistic reasoning is key for developing models that can generalize better. Looking forward to reading your paper.

Excited to share our latest research accepted to EMNLP ’24 (Main) on how LLMs handle syllogistic reasoning! We explored their ability to draw correct conclusions, addressing biases and multi-step reasoning. This work contributes to understanding LLMs as "soft reasoners." 🧠 [1/7]

@FedeRanaldi @l2m2_workshop @aclmeeting Great concept! Combining memorization and generalization into #protoknowledge offers an interesting perspective on evaluating LLMs. Thanks for sharing your insights at #ACL2025.

I propose the concept of #protoknowledge (in-between #memorization and #generalization) to evaluate whether models are truly capable of solving downstream tasks. Thanks to the @l2m2_workshop part of @aclmeeting , I could receive valuable feedback and engage idea exchanges.

Just wrapped up #ACL2025 and feeling inspired! Standout sessions on LLM self-consistency and the role of pretrained models in text embeddings show how far NLP has come. Thanks to the organizers for an amazing conference. #AI #NLP #Neuroscience

8/8 The big takeaway: Focusing on a single AI's benchmark score is missing the forest for the trees. True progress is designing the whole forest: a diverse team of agents that can achieve synergy together. #FutureofAI #Research #Teamwork /w @GoldsteinYAriel @yanivdover alonmiron

7/8 🖼️ With humans, you get synergy. Fig 3 shows clear crossover zones, yielding a Diversity Gain of up to 7pp. Both students & LLM improve after chatting proving our winning combo: calibrated confidence + diverse knowledge. #HumanAI #Teamwork

1/8 🚀 Our new pre-print, "Knowledge Is More Than Performance" is out! Can a room full of language models collaborate like human experts? Spoiler: not yet. And our research reveals the fundamental reason why 🧵 #AI #LLM #humanaiinteraction arxiv.org/abs/2507.22889

Presenting our CISC paper tomorrow at #ACL2025! ⚡️ We save >40% compute on self consistency by using the LLM's valuable internal confidence signal. 🗓️ Poster: Tues, 16:00-17:30 @ Hall X4 X5 Paper: arxiv.org/abs/2502.06233 Also chatting: LLMs in Neuro, MedNLP, & Human-AI collab!

Presenting my poster : 🕊️ DOVE - A large-scale multi-dimensional predictions dataset towards meaningful LLM evaluation, Monday 18:00 Vienna, #ACL2025 Come chat about LLM evaluation, prompt sensitivity, and our 250M COLLECTION OF MODEL OUTPUTS!

See you at #ACL2025 in Vienna—come say Hi! w/ @TaubenfeldAmir eran_ofek @amir_feder @GoldsteinYAriel @zorikgekhman @_galyo @GoogleAI

Our method uses a model's internal confidence to make self-consistency more efficient: ✅ Saves >40% compute on average ✅ Maintains performance ✅ Adds no latency overhead We're sharing the code to encourage reproduction and new research. Check it out! 💻 github.com/google-researc…

Thrilled that our paper on Confidence-Informed Self-Consistency (CISC) has been accepted to #ACL2025 Findings! 🎉 Paper: arxiv.org/abs/2502.06233 (1/2)