Reposted by Diyi YangHao Zhu 朱昊 @zhuhao.me · 04/03/2025We are getting closer to have agents operating in the real physical world. However, can we trust frontier models to make embodied decisions 🎮 aligned with human norms 👩⚖️ ? With EgoNormia, a 1.8k ego-centric video 🥽 QA benchmark, we show that this is surprisingly challenging! 1239
Reposted by Diyi YangDirk Hovy @dirkhovy.bsky.social · 03/05/2025We (w/ @diyiyang.bsky.social, @zhuhao.me, & Bodhisattwa Prasad Majumder) are excited to present our #NAACL25 tutorial on Social Intelligence in the Age of LLMs! It will highlight long-standing and emerging challenges of AI interacting w humans, society & the world. ⏰ May 3, 2:00pm-5:30pm Room Pecos 0156
Reposted by Diyi YangYijia Shao @echoshao8899.bsky.social · 17/01/2025LM agents today primarily aim to automate tasks. Can we turn them into collaborative teammates? 🤖➕👤 Introducing Collaborative Gym (Co-Gym), a framework for enabling & evaluating human-agent collaboration! I now get used to agents proactively seeking confirmations or my deep thinking.(🧵 with video) 12210
Reposted by Diyi YangHao Zhu 朱昊 @zhuhao.me · 10/12/2024My first bluesky post will be for my first project as a postdoc at Stanford. Talk Arena is our first step towards building audio LMs into interactive agents. Try it out and let me know what you think. talkarena.orgtalkarena.orgTalk ArenaInteractive evaluation for audio models 2194
Reposted by Diyi YangWill Held @williamheld.com · 10/12/2024Want to add your model to the arena? Have an idea for a new feature for Talk Arena? We are open to collaboration in many forms! Co-led with @ellaminzhili.bsky.social in collaboration with @michaelryan207.bsky.social Kunat Pipatanakul Potsawee Manakul @zhuhao.me and @diyiyang.bsky.social (5/5)talkarena.orgTalk ArenaInteractive evaluation for audio models 031
Reposted by Diyi YangWill Held @williamheld.com · 10/12/2024With an increasing number of Large *Audio* Models 🔊, which one do users like the most? Introducing talkarena.org — an open platform where users speak to LAMs and receive text responses. Through open interaction, we focus on rankings based on user preferences rather than static benchmarks. 🧵 (1/5) 3318
Reposted by Diyi YangYijia Shao @echoshao8899.bsky.social · 06/12/2024Check out our paper, code, data to learn more! Paper: arxiv.org/abs/2409.00138 Website: salt-nlp.github.io/PrivacyLens/arxiv.orgPrivacyLens: Evaluating Privacy Norm Awareness of Language Models in ActionAs language models (LMs) are widely utilized in personalized communication scenarios (e.g., sending emails, writing social media posts) and endowed with a certain level of agency, ensuring they act in... 122
Reposted by Diyi YangYijia Shao @echoshao8899.bsky.social · 06/12/2024Excited to present our PrivacyLens paper at #NuerIPS next week! We explore LM agent privacy risks when deployed as personal assistants. (Details in thread) I am working on developing LM agents as collaborative research partners, learning aids, personal assistants, and more. Let's connect and chat!! 272
Reposted by Diyi YangAi2 @ai2.bsky.social · 21/11/2024Meet Tülu 3, a set of state-of-the-art instruct models with fully open data, eval code, and training algorithms. We invented new methods for fine-tuning language models with RL and built upon best practices to scale synthetic instruction and preference data. Demo, GitHub, paper, and models 👇 211131
Reposted by Diyi YangStanford NLP Group @stanfordnlp.bsky.social · 18/11/2024Missed some – or all – of our papers at #EMNLP2024? It's not too late to catch up using this handy list from the Stanford AI Lab blog: ai.stanford.edu/blog/emnlp-2... 0244
Reposted by Diyi YangGrace Lindsay @neurograce.bsky.social · 20/11/2024When I will respond to your email 382102354
Reposted by Diyi YangEdward Grefenstette @egrefen.bsky.social · 19/11/2024🌶️(?) take: Agents are somehow hot right because people realized that LLM output can be interpreted as a DSL which directs side effects in the world (e.g. tool calls) rather than just returning text in a chat/autocomplete sense. What are the open challenges? A 🧵... [1/11] 916531
Reposted by Diyi YangChristopher Manning @chrmanning.bsky.social · 18/11/2024I did an unscientific, uncontrolled experiment for #EMNLP2024—details in 🧵👇. I posted my conference & workshop papers to 5 socials. Clear results: Mastodon is near dead, Threads may have users but not my people, not giving up on X/Twitter yet, but Bluesky is worth investing in. 28710
Diyi Yang @diyiyang.bsky.social · 18/11/2024Had a great time doing the language agent tutorial (language-agent-tutorial.github.io) with Yu Su, Shunyu Yao and Tao Yu 😀 #EMNLP2024 Check out our slides here: tinyurl.com/language-age...language-agent-tutorial.github.ioEMNLP 2024 Tutorial: Language Agents: Foundations, Prospects, and RisksDeformable Neural Radiance Fields creates free-viewpoint portraits (nerfies) from casually captured videos. 0335
Reposted by Diyi YangWill Held @williamheld.com · 14/11/2024I'll be at the Google Theory and Practice of Foundation Models Workshop today and tomorrow! FOMO for EMNLP, but excited to chat more casually at a smaller non-archival workshop 😅 I am presenting at the Lightning Talks tomorrow at 1:30 PM on our Distilled Voice Assistant model if you're around! 081
Reposted by Diyi YangWill Held @williamheld.com · 07/11/2024Every semester, I drop into Georgia Tech's Deep Learning course to do a speed-through LLM lecture! I keep updating things to balance "history" and recent progress. Slides for this semester are here for folks who are teaching courses on NLP/DL/LLMs in the near future: docs.google.com/presentation...docs.google.comCS 4644 / 7643: Deep Learning - LLM Guest Lecture - Fall 2024Training Large Language Models CS 4644 / 7643: Deep Learning William Held School of Interactive Computing Georgia Institute of Technology 0102
Reposted by Diyi YangCaleb Ziems @calebziems.com · 15/11/2024I wanted to contribute to "Starter Pack Season" with one for Stanford NLP+HCI: go.bsky.app/VZBhuJ5 Here are some other great starter packs: - CSS: go.bsky.app/GoEyD7d + go.bsky.app/CYmRvcK - NLP: go.bsky.app/SngwGeS + go.bsky.app/JgneRQk - HCI: go.bsky.app/p3TLwt - Women in AI: go.bsky.app/LaGDpqg 22510