🔥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

[1/n] 🚀Diffusion models for discrete data excel at modeling text, but they need hundreds to thousands of diffusion steps to perform well. We show that this is caused by the fact that discrete diffusion models predict each output token *independently* at each denoising step.

1/n uclanlp is researching how Black, LGBTQIA+, & women communities perceive and are affected by content moderation, as it relates to English-language social media content using reclaimed language. As part of this, we are recruiting annotators (forms.gle/KP6F9gDCo8Skjs…) …

📢 I’m recruiting PhD students UVA Computer Science for Fall 2025! 🎯 Neurosymbolic AI, probabilistic ML, trustworthiness, AI for science. See my website for more details: zzeng.me 📬 If you're interested, apply and mention my name in your application: engineering.virginia.edu/department/com…

You have some model/knowledge (e.g. Bayes Net, Probabilistic/Logic Program, DB) and some query (e.g. MAP, Causal Adjustment) you want to ask. When can you compute this efficiently? Find out @ NeurIPS today in Poster Session 6 East, #3801. Paper: arxiv.org/abs/2412.05481

I really enjoyed contributing to this project and am excited to share what we have built!

Enabling Autoregressive Models to Fill In Masked Tokens Hybrid autoregressive and masked language model for infilling by training a linear decoder that takes their concatenated hidden states as input. Provides faster inference with KV caching. MARIA significantly outperforms

Excited to release PrefEval (ICLR '25 Oral), a benchmark for evaluating LLMs’ ability to infer, memorize, and adhere to user preferences in long-context conversations! ⚠️We find that cutting-edge LLMs struggle to follow user preferences—even in short contexts. This isn't just

A few months ago, we started Inception Labs, a new generative AI startup with a rockstar founding team. At Inception, we are challenging the status quo for language generation. Our first results bring blazing fast speeds at 1000+ tokens/sec while matching the quality of leading

Video generative models hold the promise of being general-purpose simulators of the physical world 🤖 How far are we from this goal❓ 📢Excited to announce VideoPhy-2, the next edition in the series to test the physical likeness of the generated videos for real-world actions. 🧵

What happens if we tokenize cat as [ca, t] rather than [cat]? LLMs are trained on just one tokenization per word, but they still understand alternative tokenizations. We show that this can be exploited to bypass safety filters without changing the text itself. #AI #LLMs #Token

📢Scaling test-time compute via generative verification (GenRM) is an emerging paradigm and shown to be more efficient than self-consistency (SC) for reasoning. But, such claims are misleading☠️ Our compute-matched analysis shows that SC outperforms GenRM across most budgets! 🧵

The unreasonable effectiveness of model merging for cross-lingual transfer ! Our preprint evaluates a number of *modular* approaches to fine-tuning LLMs that "assign" model params to either task or language. Surprisingly, merging experts beats all ! 🧵1/4 arxiv.org/abs/2505.18356