🔥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

🚀 Excited to share POPPER --- Automated Hypothesis Validation with Agentic Sequential Falsifications. Looking forward to seeing how the community builds on this! 🚀💡 🔗 GitHub: github.com/snap-stanford/… 📄 Paper: arxiv.org/abs/2502.09858 Huge thanks to the incredible team behind

Happy to see many new integrations being built inside LOTUS! We hope that it makes writing LM programs even faster 🚀

Checkout LOTUS 1.1.0 - a bunch of new features added! 🔥🚀

1/8 🚀 Introducing S*: Test-Time Scaling for Code Generation, start of our releases in the coding domain NovaSky . S* enables (1) non-reasoning models surpass reasoning models: GPT-4o-mini + S* > o1-preview. (2) open models compete SOTA: R1-Distilled-32B +S* ~= o1 (high).

LLMs for GPU kernel🌽generation have been getting Pop🍿ular since our preview last Dec; excited to announce 📢 our full paper 📃 for KernelBench! Turns out KernelBench is quite challenging 🧠 — frontier models outperform the PyTorch Eager baseline <20% of the time. More 🧵👇

🧵Introducing LangProBe: the first benchmark testing where and how composing LLMs into language programs affects cost-quality tradeoffs! We find that, on avg across diverse tasks, smaller models within optimized programs beat calls to larger models at a fraction of the cost.

Struggling with complex data queries? Enter LOTUS! 🤯 This new engine combines LLMs with databases for powerful, AI-driven insights. Think Text2SQL on steroids! Liana Medium link: medium.com/ai-artistry/lo…

One of the main goals I had while building out multilspy (aka.ms/multilspy) was that eventually LLMs will be able to tool call LSPs. Happy to see steps in this direction: Checkout MultilspyMCP (playbooks.com/mcp/asimihsan-…), which provides an mcp implementation over multilspy!

In Large Language Monkeys, we showed the scaling laws of inference-time compute with repeated sampling--the power law relationship between the number of repeated attempts and the fraction of problems solved! The following amazing work theoretically proves the necessary and

Ember: an inference-time scaling architecture framework 🧵 (1/8)

🚨 Why Do Multi-Agent LLM Systems Fail? ⁉️ 🔥 Introducing MAST: The first multi-agent failure taxonomy - consists of 14 failure modes and 3 categories, generalizes for diverse multi-agent systems and tasks! Paper: arxiv.org/pdf/2503.13657 Code: github.com/multi-agent-sy… 🧵1/n

Excited to release SWiRL: A synthetic data generation and multi-step RL approach for reasoning and tool use! With SWiRL, the model’s capability generalizes to new tasks and tools. For example, a model trained to use a retrieval tool to solve multi-hop knowledge-intensive

I defended my PhD from Stanford CS Stanford NLP Group 🌲 w/ Stanford CS first all-female committee!! My dissertation focused on AI methods, evaluations & interventions to improve Education. So much gratitude for the support & love - and SO excited for the next chapter!!!! 🥳

So many things in the run-up to DSPy 3. Here's a first, EXPERIMENTAL one: 🚨We're releasing dspy.GRPO, an online RL optimizer for DSPy programs Your DSPy code as-is can be dspy.GRPO'ed. Yes, even compound multi-module programs. Led by Noah Ziems Lakshya A Agrawal dilara.

🎀 fine-grained, interpretable representation steering for LMs! meet RePS — Reference-free Preference Steering! 1⃣ outperforms existing methods on 2B-27B LMs, nearly matching prompting 2⃣ supports both steering and suppression (beat system prompts!) 3⃣ jailbreak-proof (1/n)

Happy Throughput Thursday! We’re excited to release Tokasaurus: an LLM inference engine designed from the ground up for high-throughput workloads with large and small models. (Joint work with Ayush Chakravarthy, Ryan Ehrlich, Sabri Eyuboglu, Bradley Brown, Joseph Shetaye,