Katja Hofmann

Researcher at Microsoft Research Cambridge, UK

About

Future interactive systems will learn directly from their users, and continuously adapt to their preferences. My research goal is to develop exploration, reward, and learning approaches that will make this possible. [...]

Pages

  • About
  • Contact
  • Publications

Search

Contact

Katja Hofmann

Intelligent Systems Lab Amsterdam
Informatics Institute
University of Amsterdam

Room C3.258
Science Park 904
1098 XH Amsterdam

+31 (20) 525 6767

LinkedIn
Twitter

Recent Posts

  • Query Formulation with Query Auto-Completion
  • RUSSIR 2014: Lectures on Online Experimentation for Information Retrieval
  • Fast and Reliably Online Learning to Rank for Information Retrieval
  • Practical Online Retrieval Evaluation
  • Balancing Exploration and Exploitation in Online Learning to Rank for IR

Recent Tweets

Tweets by katjahofmann

RSS Microsoft Research News

  • Systematic debugging for AI agents: Introducing the AgentRx framework
  • PlugMem: Transforming raw agent interactions into reusable knowledge
  • Phi-4-reasoning-vision and the lessons of training a multimodal reasoning model
  • CORPGEN advances AI agents for real work
  • Media Authenticity Methods in Practice: Capabilities, Limitations, and Directions
  • Project Silica’s advances in glass storage technology
  • Rethinking imitation learning with Predictive Inverse Dynamics Models
  • Paza: Introducing automatic speech recognition benchmarks and models for low resource languages
  • UniRG: Scaling medical imaging report generation with multimodal reinforcement learning
  • Argos: Multimodal reinforcement learning with agentic verifier for AI agents

RSS Recent MSR Publications

  • Systematic debugging for AI agents: Introducing the AgentRx framework
  • PlugMem: Transforming raw agent interactions into reusable knowledge
  • Phi-4-reasoning-vision and the lessons of training a multimodal reasoning model
  • Trailer: The Shape of Things to Come
  • CORPGEN advances AI agents for real work
  • Media Authenticity Methods in Practice: Capabilities, Limitations, and Directions
  • Project Silica’s advances in glass storage technology
  • Rethinking imitation learning with Predictive Inverse Dynamics Models
  • Paza: Introducing automatic speech recognition benchmarks and models for low resource languages
  • UniRG: Scaling medical imaging report generation with multimodal reinforcement learning

RSS New at ILPS

  • An error has occurred; the feed is probably down. Try again later.
Blog at WordPress.com.
  • Subscribe Subscribed
    • Katja Hofmann
    • Already have a WordPress.com account? Log in now.
  • Privacy
    • Katja Hofmann
    • Subscribe Subscribed
    • Sign up
    • Log in
    • Copy shortlink
    • Report this content
    • View post in Reader
    • Manage subscriptions
    • Collapse this bar
Design a site like this with WordPress.com
Get started