📷 Calling all Speech, Language & ML enthusiasts! 📷 Join us at the Mid-Atlantic Student Colloquium on Speech, Language, Learning, hosted by Johns Hopkins University on May 3, 2024!

📢 MASC-SLL Call for Papers is out! 📢 🎓 Are you a student passionate about Speech, Language, and Learning? 🗣️✨ 🌟 Present your research at the Mid-Atlantic Student Colloquium on Speech, Language, and Learning (MASC-SLL) at Johns Hopkins Johns Hopkins Engineering on May 3rd! 🌟

Excited to share that CPO has been accepted at ICML 2024!

I know your timeline is flooded now with word salads of "insane, HER, 10 features you missed, we're so back". Sit down. Chill. <gasp> Take a deep breath like Mark does in the demo </gasp>. Let's think step by step: - Technique-wise, OpenAI has figured out a way to map audio to

📢 Happy to share that our paper on #LLM safety in multilingual contexts has been accepted at #ACL 2024! ✨ We show the difficulty of alleviating multilingual safety issues in LLMs through standard alignment methods. arxiv.org/abs/2401.13136 🧵1/7

#RLHF is taking the spotlight. We usually focus on boosting reward and policy models to enhance RLHF outcomes. Our paper dives into the interactions between PM and RM from a data-centric way, revealing that their seamlessness is crucial to RLHF outcomes. arxiv.org/abs/2406.07971

Will be presenting my work on LLM-MT at #naacl today, at In-Person Poster Session 7 (11am). Please come if you are interested in machien translation and multilinguality! Would also love to discuss multimodal LLM (speech + text) and non-autoregressive decoding (NAT, diffusion)!

Here’s some better news: Combining CPO and SimPO can likely improve the model! Check out more details in our GitHub code: github.com/fe1ixxu/CPO_SI…

We're very excited to release 🌟DiVA — Distilled Voice Assistant 🔊 Will Held ✅End-to-end differentiable speech LM; early fusion with Whisper and Llama 3 8B ✅Improves generalization by using distillation rather than supervised loss ✅Trained only using open-access

Introducing *Transfusion* - a unified approach for training models that can generate both text and images. arxiv.org/pdf/2408.11039 Transfusion combines language modeling (next token prediction) with diffusion to train a single transformer over mixed-modality sequences. This