🔥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

Introducing SimPO: Simpler & more effective Preference Optimization!🎉 Significantly outperforms DPO w/o a reference model!📈 Llama-3-8B-SimPO ranked among top on leaderboards!💪 ✅44.7% LC win rate on AlpacaEval 2 ✅33.8% win rate on Arena-Hard arxiv.org/abs/2405.14734 🧵[1/n]

🤨 Are Multimodal Large Language Models really as 𝐠𝐨𝐨𝐝 at 𝐜𝐡𝐚𝐫𝐭 𝐮𝐧𝐝𝐞𝐫𝐬𝐭𝐚𝐧𝐝𝐢𝐧𝐠 as existing benchmarks such as ChartQA suggest? 🚫 Our ℂ𝕙𝕒𝕣𝕏𝕚𝕧 benchmark suggests NO! 🥇Humans achieve ✨𝟖𝟎+% correctness. 🥈Sonnet 3.5 outperforms GPT-4o by 10+ points,

My new blog post argues from first principles how length normalization in preference learning objectives (e.g., SimPO) can facilitate learning from model-annotated preference data. Check it out! cs.princeton.edu/~smalladi/blog…

How can we understand neural chatbots in terms of interpretable, symbolic mechanisms? To explore this question, we constructed a Transformer that implements the classic ELIZA chatbot algorithm (with Abhishek Panigrahi and Danqi Chen). Paper: arxiv.org/abs/2407.10949 (1/6)

I'll be at ACL 2024! I'd love to chat with about interpretability, preference optimization, science of LM, or any NLP topics -- feel free to reach out! Oh, and I'll present The Heuristic Core (arxiv.org/abs/2403.03942) both as an oral (Aug 13 10:30) and a poster (Aug 12 14:00).

Come check out our poster at #ACL2024! I will be at the 4pm poster session, stop by to chat about long-context models

I’m at COLM from Monday to Wednesday. Reach out if you want to chat!

Past work observed that DPO often decreases the probability of preferred responses. So where does the probability go? 🧐 We investigate the causes for this counter-intuitive phenomenon and show that it can lead to surprising failures in alignment! 📰 arxiv.org/abs/2410.08847 🧵

Have you ever wondered why we don’t use multiple visual encoders for VideoLLMs? We thought the same! Excited to announce our latest work MERV, on using Multiple Encoders for Representing Videos in VideoLLMs, outperforming prior works with the same data. 🧵

Want to train large vision-language models but drowning in data? arxiv.org/abs/2501.00654 Introducing ICONS - we demonstrate how to select only 20% of training samples while maintaining 98.6% of the performance, and 60% of training samples to achieve 102.1% of the performance.

Introducing COMPACT: COMPositional Atomic-to-complex Visual Capability Tuning, a data-efficient approach to improve multimodal models on complex visual tasks without scaling data volume. 📦 arxiv.org/abs/2504.21850 1/10

🤔 Recent mech interp work showed that retrieval heads can explain some long-context behavior. But can we use this insight for retrieval? 📣 Introducing QRHeads (query-focused retrieval heads) that enhance retrieval Main contributions: 🔍 Better head detection: we find a