🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Highlighting our #NAACL2025 papers 🧵🧵🧵

Just arrived in Albuquerque for #NAACL2025! Excited to connect and chat about LLM safety, alignment, reasoning, RLVR, and beyond. Feel free to reach out or DM if you’d like to meet up.

Excited to present two papers today and tomorrow at #NAACL2025! Look out for our oral sessions: TurkingBench: arxiv.org/abs/2403.11905 📅 4-5:30pm, Thur, May 1 📍 Ballroom A (R&E.4) Verifiable by Design: arxiv.org/abs/2404.03862 📅 9-10:30am, Fri, May 2 📍 Ballroom A (HC.1)

Excited to be presenting our paper on training language models under heavily imbalanced data tomorrow at #NAACL2025! If you want to chat about data curation for both pre- and post-training, feel free to reach out! 📝 arxiv.org/abs/2410.04579 📅 11-12:30am, Fri, May 2 📍 Hall 3

Quick reminder that our paper, Benchmarking Language Model Creativity: A Case Study on Code Generation, will be presented today! 📅 11AM-12:30PM, Fri, May 2 📍 Hall 3 📝 arxiv.org/abs/2407.09007 🎥 youtube.com/watch?v=v1cHyC…

Check out Daniel’s summary of our paper! ⬇️

Now accepted by #ACL2025! Thrilled to see our paper also referenced in Lilian Weng's latest blog post on reasoning in LLMs! Check it out: lilianweng.github.io/posts/2025-05-…

There have been various efforts on disentangling "task learning" vs "task recall" in LLMs. We've recently explored a fresh angle by borrowing from cryptography: with substitution ciphers, we transform a given task into an equivalent, but cryptic (no pun intended!!) forms.

I am excited to share that I will join Stanford AI Lab for my PhD in Computer Science in Fall 2025. Immense gratitude to my mentors: Benjamin Van Durme Daniel Khashabi 🕊️ Tianxing He Jack Jingyu Zhang Orion Weller tsvetshop Lauren Gardner Hongru Du Stella Li Guanghui Qin 🧵:

🚨 New work: We rethink how we finetune safer LLMs — not by filtering after the generation, but by tracking safety risk token by token during training. We repurpose guardrail models like 🛡️ Llama Guard and Granite Guardian to score evolving risk across each response 📉 — giving

Long-form inputs (e.g., needle-in-haystack setups) are the crucial aspect of high-impact LLM applications. While previous studies have flagged issues like positional bias and distracting documents, they've missed a crucial element: the size of the gold/relevant context. In our

🚨 Sharing our new #ACL2025NLP main paper! 🎥 Deploying video VLMs at scale? Inference compute is your bottleneck. We study how to optimally allocate inference FLOPs across LLM size, frame count, and visual tokens. 💡 Large-scale training sweeps (~100k A100 hrs) 📊 Parametric