🔥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

🥳 Happy to share our new work –  Kinetics: Rethinking Test-Time Scaling Laws 🤔How to effectively build a powerful reasoning agent? Existing compute-optimal scaling laws suggest 64K thinking tokens + 1.7B model > 32B model. But, It only shows half of the picture! 🚨 The O(N²)

Giving LLMs very large amounts of context can be really useful, but it can also be slow and expensive. Could scaling inference time compute help? In our latest work, we show that allowing models to spend test time compute to “self-study” a large corpora can >20x decode

Excited to be presenting our new work–HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation– at #CVPR2025 this week. VAR (Visual Autoregressive Modelling) introduced a very nice way to formulate autoregressive image generation as a next-scale prediction task (from

Checkout Sabri Eyuboglu's post for more details: x.com/EyubogluSabri/…

I like this idea very much and have long advocated for something like this. Synthetically enriched «KV prefix» is a natural augment to modern long context models.

Go, Sharon Zhou and team! Congrats to Lisa Su and AMD on such an amazing addition!

This is a proper Vibe-coding setup for GPU programmers, and can result in getting surprisingly far! I honestly think that if this authoring experience is v1, then v10 might become the normal way GPU experts start writing serious custom kernels! Great work Anne Ouyang! (finally

Congratulations, Dr. Goldie! Anna Goldie

Congratulations, Caia Costello and Adrian!

Shrinking the Generation-Verification Gap with Weak Verifiers "we introduce Weaver, a framework for designing a strong verifier by combining multiple weak, imperfect verifiers." "Weaver leverages weak supervision to estimate each verifier’s accuracy and combines their outputs

Very exciting work on using weak supervision for RL- closing the “generation-verification gap”!! Once again- principled approaches to labeling/data development are the keys!

Interesting tidbit from prof Christopher Manning: The first mention of “Large Language Model” comes from a 1998 NLP workshop Taiwan! Paper by Chun-Liang Chen, Bo-Ren Bai, Lee-Feng Chien, Lin-Shan Lee. “Large” in 1998 = 20M word corpus

See Jon Saad-Falcon's post for more details: x.com/JonSaadFalcon/… Paper: arxiv.org/abs/2506.18203 Blog: hazyresearch.stanford.edu/blog/2025-06-1… github.com/HazyResearch/s…… Datasets and Models: huggingface.co/collections/ha…

So excited to speak tomorrow about Think Prune Train at LAD'25 session on Reasoning and Self Improvement! iclad.ai

I’ve joined AIX Ventures as a General Partner, working on investing in deep AI startups. Looking forward to working with founders on solving hard problems in AI and seeing products come out of that!  Thank you Yuliya Chernova at The Wall Street Journal for covering the news: wsj.com/articles/ai-re…