Skip to main content

Utility navigation

  • Calendar
  • Contact
  • Login
  • MAKE A GIFT
Berkeley University of California
Home Home

Main navigation

  • Programs & Events
    • Research Programs
    • Workshops & Symposia
    • Public Lectures
    • Research Pods
    • Internal Program Activities
    • Algorithms, Society, and the Law
  • Participate
    • Apply to Participate
    • Propose a Program
    • Postdoctoral Research Fellowships
    • Law and Society Fellowships
    • Science Communicator in Residence Program
    • Circles
    • Breakthroughs Workshops and Goldwasser Exploratory Workshops
  • People
    • Scientific Leadership
    • Staff
    • Current Long-Term Visitors
    • Research Fellows
    • Postdoctoral Researchers
    • Scientific Advisory Board
    • Governance Board
    • Affiliated Faculty
    • Science Communicators in Residence
    • Law and Society Fellows
    • Chancellor's Professors
  • News & Videos
    • News
    • Videos
  • Support for the Institute
    • Annual Fund
    • All Funders
    • Institutional Partnerships
  • For Visitors
    • Visitor Guide
    • Plan Your Visit
    • Location & Directions
    • Accessibility
    • Building Access
    • IT Guide
  • About

Results 2331 - 2340 of 23900

Image

Support Research on the Foundations of Computing

MAKE A GIFT
MAKE A GIFT
Workshop Talk
|
Apr. 2, 2025

Inference Scaling: A New Frontier for AI Capability

Scaling laws, which demonstrate a predictable relationship between AI’s performance and the amount of training data, compute, and model size continue to drive progress in AI. In this talk, we present inference compute as a new frontier for scaling LLMs. Our recent work, Large Language Monkeys, shows that coverage - the fraction of problems solved by any attempt - persistently scales with the number of samples over four orders of magnitude. Interestingly, the relationship between coverage and the number of samples is log-linear and can be modeled with an exponentiated power law, suggesting the existence of inference-time scaling laws. In domains where answers can be automatically verified, like coding and formal proofs, we show that these increases in coverage directly translate into improved performance. In domains without verifiers, we find that identifying correct samples out of many generations remains challenging. Common methods to pick correct solutions from a collection of samples, such as majority voting or reward models, plateau beyond several hundred samples and fail to fully scale with the sample budget. We then present Archon, a framework for automatically designing effective inference-time systems composed of one or more LLMs. Archon selects, combines, and stacks layers of inference-time operation such as repeated sampling, fusion, ranking, model based unit testing, and verification to construct optimized LLM systems for target benchmarks. It alleviates the need for automated verifiers by enabling strong pass@1 performance across diverse instruction following, reasoning, math, and coding tasks. Finally, we discuss some of our recent hardware acceleration techniques to improve the computational efficiency of serving LLMs.

Workshop Talk
|
Apr. 1, 2025

Attention to Detail: Fine-Grained Vision-Language Alignment

No abstract available.

Workshop Talk
|
Apr. 1, 2025

Liquid Networks

Abstract not available.

Workshop Talk
|
Apr. 1, 2025

The Frontier between Retrieval-augmented and Long-context Language Models

Abstract not available.

Workshop Talk
|
Apr. 1, 2025

Mixed-modal Language Modeling: Chameleon, Transfusion, and Mixture of Transformers

Existing multimodal models typically have custom architectures that are designed for specific modalities (image->text, text->image, text only, etc). In this talk, I will present our recent work a series of early fusion mixed-modal models trained on arbitrary mixed sequences of images and text. I will discuss and contrast two models architectures, Chameleon and Transfusion, that make very different assumptions about how to model mixed-modal data, and argue for moving form a tokenize-everything approach to newer models that are hybrids of autoregressive transformers and diffusion. I will also cover recent efforts to better understand how to more stably train such models at scale without excessive modality competition, using a mixture of transformers technique. Together, these advances lay a possible foundation for universal models that can understand and generate data in any modality, and I will also sketch some of the steps that we still need to focus on to reach this goal.

Workshop Talk
|
Apr. 1, 2025

Reducing the Dimension of Language: A Spectral Perspective on Transformers

Can we build neural architectures that go beyond Transformers by leveraging principles from dynamical systems?
In this talk, we'll introduce a novel approach to sequence modeling that draws inspiration from the paradigm of online control of dynamical systems to achieve long-range memory, fast inference, and provable robustness.

Video
|
Apr. 1, 2025
Panel Discussion: Phase Transition in Random Circuit Sampling | Quantum Colloquium
Workshop Talk
|
Apr. 1, 2025

What will Transformers look like in 2027?

Abstract not available.

Pagination

  • Previous page Previous
  • Page 232
  • Page 233
  • Current page 234
  • Page 235
  • Page 236
  • Next page Next
Home
The Simons Institute for the Theory of Computing is the world's leading venue for collaborative research in theoretical computer science.

Footer

  • Programs & Events
  • Participate
  • Workshops & Symposia
  • Contact Us
  • Calendar
  • Accessibility

Footer social media

  • Twitter
  • Facebook
  • Youtube
© 2013–2026 Simons Institute for the Theory of Computing. All Rights Reserved.
link to homepage

Main navigation

  • Programs & Events
    • Research Programs
    • Workshops & Symposia
    • Public Lectures
    • Research Pods
    • Internal Program Activities
    • Algorithms, Society, and the Law
  • Participate
    • Apply to Participate
    • Propose a Program
    • Postdoctoral Research Fellowships
    • Law and Society Fellowships
    • Science Communicator in Residence Program
    • Circles
    • Breakthroughs Workshops and Goldwasser Exploratory Workshops
  • People
    • Scientific Leadership
    • Staff
    • Current Long-Term Visitors
    • Research Fellows
    • Postdoctoral Researchers
    • Scientific Advisory Board
    • Governance Board
    • Affiliated Faculty
    • Science Communicators in Residence
    • Law and Society Fellows
    • Chancellor's Professors
  • News & Videos
    • News
    • Videos
  • Support for the Institute
    • Annual Fund
    • All Funders
    • Institutional Partnerships
  • For Visitors
    • Visitor Guide
    • Plan Your Visit
    • Location & Directions
    • Accessibility
    • Building Access
    • IT Guide
  • About

Utility navigation

  • Calendar
  • Contact
  • Login
  • MAKE A GIFT
link to homepage