Log inSign up
UCL DARK profile banner
user avatar

UCL DARK

@UCL_DARK
Metamorphosed into @BOLD_Lab_AI. Previously: UCL DARK Lab at @AI_UCL led by @_rockt, @egrefen, @robertarail, and @jparkerholder.
London
ucldark.com
Joined July 2020
197
Following
4,584
Followers
RepliesMedia
  • user avatar
    UCL DARK
    @UCL_DARK
    Jun 24
    We are excited to announce that we will sunset @UCL_DARK and merge into the British Open-Ended Learning & Discovery (BOLD) Lab. It's a unique opportunity to come together as a joint fundamental AI research group. This account will be inactive going forward. Follow @bold_lab_ai 🦋
  • user avatar
    UCL DARK
    @UCL_DARK
    Sep 5, 2025
    "Always reasoning" isn't the optimal strategy for LLM agents! 🧠 Our new work from UCL DARK identifies a "Goldilocks" effect: planning too frequently, or not enough, degrades performance. We show how to train agents to dynamically allocate test-time compute for best results. 👇
    user avatar
    Bartłomiej Cupiał
    @CupiaBart
    Sep 5, 2025
    Almost all agentic pipelines prompt LLMs to explicitly plan before every action (ReAct), but turns out this isn't optimal for Multi-Step RL 🤔 Why? In our new work we highlight a crucial issue with ReAct and show that we should make and follow plans instead🧵
    Image
  • user avatar
    UCL DARK
    @UCL_DARK
    Jun 24, 2025
    New collaboration between @FLAIR_Ox and DARK 🚀
    user avatar
    Laura Ruis
    @LauraRuis
    Jun 24, 2025
    LLMs can be programmed by backprop 🔎 In our new preprint, we show they can act as fuzzy program interpreters and databases. After being ‘programmed’ with next-token prediction, they can retrieve, evaluate, and even *compose* programs at test time, without seeing I/O examples.
    Image
  • user avatar
    UCL DARK
    @UCL_DARK
    Apr 26, 2025
    Join @UCL_DARK's Tim Rocktäschel for a can't-miss keynote diving deep into how Open-Endedness, World Models, and Automated Innovation are going to shape the next wave of AI. 🔥 #ICLR2025 🇸🇬 🕑 Starting at 2PM (in 30 minutes) 📍 Hall 1 Apex
    user avatar
    Google AI
    @GoogleAI
    Apr 25, 2025
    Join Tim Rocktäschel tomorrow at 2PM in Hall 1 Apex at #ICLR2025 for a Keynote on Open-Endedness, a research paradigm focused on systems that generate endless sequences of novel but learnable artifacts, hinting at a future where AI drives its own discoveries.
    Image