LilanOvO

@JandialSurgan Thank you for your attention. We will optimize this project into a multi-agent architecture in subsequent versions to achieve the following goals: • Identify reviewer feedback that is actually actionable • Revise and improve a paper from the previous venue

@HitLilan but who's gonna help me address the reviews :P

Paper rejected? Stop spending days reformatting LaTeX between conferences. I built a tool that automatically converts LaTeX source across templates (ICLR, ACL, ICML, NeurIPS, CVPR, AAAI, and more), preserving macros, figures, and citations. github.com/LilanOvO/Auto-… #ACL2026

Formatting is just V1.0. My goal: build a multi-agent system that: • understands reviewer feedback • extracts actionable insights • helps automate revision & resubmission 🤖 If you hate formatting as much as I do, drop a ⭐! Looking for contributors—DMs open.

How it works: 1️⃣ Upload your original source (.zip) 2️⃣ Upload the target venue template (.zip) ✅ Auto-Resubmit handles the rest—mapping macros, figures, citations, layouts without breaking anything. Supports ACL, NeurIPS, ICLR, CVPR, AAAI & more. 🛠️

Paper rejected? The review process may be stochastic—but your time shouldn’t be. Instead of spending 3 days reformatting LaTeX from ICLR → ACL, I built a tool that does it in 3 minutes. Introducing Auto-Resubmit 🚀 🔗 github.com/LilanOvO/Auto-…

@HPCAITech 666

🎉 #EMNLP2025 Exclusive Giveaway & More! 🎉 💥 500 prizes up for grabs — including AirPods 🎧, GPU credits, and more! Want in? 🚀 How to Enter: 1️⃣ Like and Retweet this post 2️⃣ Visit us at Booth HPC-AI.COM to claim your spot in the lucky draw! 🔑 Limited spots - first come, first served! ⏰ 💡 Extra Perks for Researchers： EMNLP2025 authors get $30 GPU credits CVPR2026 submitters get $20 GPU credits Fuel your next big idea! ⚡ And don’t miss our B200/B300 GPUs starting at just $1.49/hour — exclusive deals available at the booth! #EMNLP2025 #AI #GPU #GPURental #LLM #Giveaway #AuthorIncentives #Research #HPCAI

@lilianweng Good Work！

🦃 At the end of Thanksgiving holidays, I finally finished the piece on reward hacking. Not an easy one to write, phew. Reward hacking occurs when an RL agent exploits flaws in the reward function or env to maximize rewards without learning the intended behavior. This is imo a major blockers for real-world deployment of more autonomous use cases of AI models. Also would like to call out more research on mitigation strategies for reward hacking, especially in the context of LLMs and RLHF. 👉lilianweng.github.io/posts/2024-11-…

@realDonaldTrump welcome your back！ooooo！

To all of those who have asked, I will not be going to the Inauguration on January 20th.

@9v8HtHD2hTheBDb 666

in fact，China hasn't started a war in 40 years