Passing false-belief tests = model HAS theory of mind Passing false-belief tests ≠ model USES theory of mind to perform tasks Our #ACL2023 paper: t.ly/IXLLr formulates 𝑻𝒂𝒔𝒌-𝑶𝒓𝒊𝒆𝒏𝒕𝒆𝒅 cognitive capabilities, which are used to perform tasks.

Check out our project website with dataset&code released! lingjunzhao.github.io/coop_instructi…

Excited to give an oral presentation in person at the ICML ToM workshop today! ToM Workshop

When a language model guides a human, giving false instructions can frustrate them or even put them in danger. We propose a cost-effective method for detecting hallucinations in navigation instructions. More about our #EMNLP2023 findings paper⬇️ (1/n)

Excited to present our work at EMNLP tomorrow 12:15-12:30pm at Human-centered NLP oral session (Monroe)! Excited to meet new people and chat on topics including multimodal learning, trustworthy in generative AI, human-AI collaboration

I’m super grateful for Khanh Nguyen for all the help! Khanh is on academic job market now, he is very passionate and knowledgeable about his research, and is patient and offers great suggestions to help students succeed. Consider be his student before he gets too popular 😆

I am recruiting PhD students to join my lab at Harvard in Fall 2025! (deadline Dec 15) If you are interested in solving problems at the intersection of reinforcement learning, imitation learning, and NLP, pls consider applying (bit.ly/4fnficx)! Harvard SEAS Kempner Institute at Harvard University

📢 I am on the JOB market this year 📢 I am looking for both faculty and research scientist positions. My research makes AI agents useful and safe for humans. I enable them to effectively convey uncertainty, ask for help, learn from human feedback, and pursue goals that benefit

Unbelievable. This quote is blatantly false and unnecessary for the argument. And she surely had expected the backlash with the patronizing NOTE. This is racism, not "cultural generalization". NeurIPS Conference

My X profile is locked, so if you are lucky enough to see this post, please help me promote the post from Diyi.

Excited to introduce Gr00T-N1! Setting itself apart from existing VLA models, Gr00T-N1 pioneers a novel synthetic data generation strategy, leveraging a diverse suite of simulation environments & demonstration, and action-free trajectories from video generation model. Try it out!

1/ How can a monolingual English speaker 🇺🇸 decide if a French translation 🇫🇷 is good enough to be shared? Introducing ❓AskQE❓, an #LLM-based Question Generation + Answering framework that detects critical MT errors and provides actionable feedback 🗣️ #ACL2025

Representation also matters for VLA models! Introducing FLARE: Robot Learning with Implicit World Modeling. With future latent alignment objective, FLARE significantly improves policy performance on multitask imitation learning & unlocks learning from egocentric human videos.

I’ll be presenting this work in Room 1.62 today! If you're curious about how calibration errors in LLMs can be measured through human calibration, come find me and Eve Fleisig @ ACL 2025! 📍Oral Session 3 - HC: Human-centered NLP 📅Monday, July 28@ 2PM