Xing Han Lu
@xhluca
Vibe agents @Mila_Quebec @McGill_NLP
"Build the web for agents, not agents for the web" This position paper argues that rather than forcing web agents to adapt to UIs designed for humans, we should develop a new interface optimized for web agents, which we call Agentic Web Interface (AWI).
Today I learned a student of mine from China gave up waiting for his Canadian visa after over a year without updates: 1. He was a Vector Scholarship awardee. 2. He had to set aside $20K under the Direct Stream (for faster visa processing), despite being my funded student. 3. He…
I’ll be at ACL, hit me up if you’re interested in research scientist / senior dev positions at Mila! (Or just chat that’s fine too) #ACL2025 #ACL2025NLP #NLProc
We’re hiring senior devs and applied research scientists! (yes Mila has a dedicated applied research team, and yes it’s a great place to work) apply.workable.com/mila-2/j/0EF0A… apply.workable.com/mila-2/j/1C327…
Our #ACL2025NLP workshop REALM on LLM agents is happening July 31 in Vienna 🎶🎼 🗓️ Schedule & accepted papers are live! realm-workshop.github.io 🚀Join us for a day of invited talks, paper presentations and a panel discussion with an amazing line-up!
Interested in knowing more about LLMs agents and in contributing to this topic?🚀 📢We're thrilled to announce REALM: The first Workshop for Research on Agent Language Models 🤖 #ACL2025NLP in Vienna 🎻 We have an exciting lineup of speakers 🗓️ Submit your work by *March 1st*
Countless times of iterations for cooking it, but the process is satisfying. I still believe we can pour more data in each stage if we have more hands so the potential is unlimited and scaling law hasn’t hit the wall yet! Towards Digital Agents🤖 We are already on the way.
>>> Qwen3-Coder is here! ✅ We’re releasing Qwen3-Coder-480B-A35B-Instruct, our most powerful open agentic code model to date. This 480B-parameter Mixture-of-Experts model (35B active) natively supports 256K context and scales to 1M context with extrapolation. It achieves…
Nice work! We observed a similar trend on certain math tasks in our work: arxiv.org/abs/2504.07128 Section 4.1 has a discussion of our findings. You might want to consider citing it :) cc @saraveramarjano @arkil_patel @sivareddyg
Super excited that our work on SafeArena is in great hands with @ncmeade at #ICML2025! Go say hi and talk to Nick about all things web agent safety! 🤖
I'll be at #ICML2025 this week presenting SafeArena (Wednesday 11AM - 1:30PM in East Exhibition Hall E-701). Come by to chat with me about web agent safety (or anything else safety-related)!
8 research papers of 2025 that you should read, pt. 2 ▪️ Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies Ahead ▪️ Continuous Thought Machines by @SakanaAILabs ▪️ Scalable Chain of Thoughts via Elastic Reasoning ▪️ Parallel Scaling Law for LMs ▪️ Soft…
Attending #ICML2025 🇨🇦 this week! I’ll be co-organizing the Computer Use Agent Workshop @workshopcua on July 19th! Happy to chat about anything related to language agents — especially world modeling, scaling RL for agents, and multi-turn RL. Excited to meet old friends and…
I am speaking at 10 am PT on a slightly different topic than I usually talk about 🙂: "Simple Ideas Can Have Mighty Effects: Don't Take LLM Fundamentals for Granted" Check out if you're around. #ICML2025
Join us at NewInML@ICML25 Workshop — today at 8:30 AM in rooms MR 211-214. Explore cutting-edge research, meet amazing new voices in ML, and be part of the community! 🌐 newinml.github.io #ICML2025 #ML #AI #NewInML
Don't miss our poster on SafeArena!
I'll be at #ICML2025 this week presenting SafeArena (Wednesday 11AM - 1:30PM in East Exhibition Hall E-701). Come by to chat with me about web agent safety (or anything else safety-related)!
Attending #ICML2025 🇨🇦 this week! Will be presenting Aguvis (arxiv.org/abs/2412.04454) on July 15 at 11am, and joining Computer Use Agent Workshop @workshopcua on July 19. If you’re into digital agent research, especially around computer/browser use, let’s grab a coffee!
I'll be at #ICML2025 this week presenting SafeArena (Wednesday 11AM - 1:30PM in East Exhibition Hall E-701). Come by to chat with me about web agent safety (or anything else safety-related)!
SWE-agent is now Multimodal! 😎 We're releasing SWE-agent Multimodal, with image-viewing abilities and a full web browser for debugging front-ends. Evaluate your LMs on SWE-bench Multimodal or use it yourself for front-end dev. 🔗➡️
🎯Our agents now achieve a 94% top 5 success rate on ServiceNow tasks, up from the previous SOTA of 63.8%! That means an over 11-minute half-life, up from 1 minute. 📚How did we reach this milestone? Deep dive 👉 silverstream.ai/blog-news/2sig… 👇Watch our agent in action! #BPO…
🎉 Our paper “𝐻𝑜𝑤 𝑡𝑜 𝑇𝑟𝑎𝑖𝑛 𝑌𝑜𝑢𝑟 𝐿𝐿𝑀 𝑊𝑒𝑏 𝐴𝑔𝑒𝑛𝑡: 𝐴 𝑆𝑡𝑎𝑡𝑖𝑠𝑡𝑖𝑐𝑎𝑙 𝐷𝑖𝑎𝑔𝑛𝑜𝑠𝑖𝑠” got an 𝐨𝐫𝐚𝐥 at next week’s 𝗜𝗖𝗠𝗟 𝗪𝗼𝗿𝗸𝘀𝗵𝗼𝗽 𝗼𝗻 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗨𝘀𝗲 𝗔𝗴𝗲𝗻𝘁𝘀! 🖥️🧠 We present the 𝐟𝐢𝐫𝐬𝐭 𝐥𝐚𝐫𝐠𝐞-𝐬𝐜𝐚𝐥𝐞…
@COLM_conf decisions are out, and so are we The strength of submissions this year amazed us! Many many hard decisions 😩 + @AdtRaghunathan, @eunsolc, @RanjayKrishna 😴😴😴
Kyutai TTS and Unmute are now open source! The text-to-speech is natural, customizable, and fast: it can serve 32 users with a 350ms latency on a single L40S. Try it out and get started on the project page: kyutai.org/next/tts
🚨 Excited to announce two invited speakers at #BlackboxNLP 2025! Join us to hear from two leading voices in interpretability: 🎙️ Quanshi Zhang (Shanghai Jiao Tong University) 🎙️ Verna Dankers (McGill University) @vernadankers @QuanshiZhang