Ravi Hammond

PhD @ Oxford | Artificial Intelligence | Ex Google, Microsoft, Palantir, and Atlassian

[British Open-ended Learning and Discovery Lab @bold_lab_ai]

We hope you’ve enjoyed a sneak peek of work from BOLD and our collaborators at #ICML2026! See below for a full summary of where you can find us this week:

▶️ (Poster) Procedural Generation of Algorithm Discovery Tasks in Machine Learning, Hall A #1803, Tuesday 10:30 - 12:15, led by @AlexDGoldie

▶️ (Poster) h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning, Hall A #2704, led by Alesia Ivanova @sumeetrm

▶️ (Poster) Goal-Conditioned Agents that Learn Everything All at Once, Hall A #310, Tuesday 14:00 - 15:45, led by @mitrma

▶️ (Poster) Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Creative Writing, Hall A #2605, Wednesday 14:30 - 14:15, led by Tejas Krishnan @sumeetrm

▶️ (Poster) Evolution Strategies at the Hyperscale, Hall A #3712, Thursday 10:30 - 12:15, led by @bidiptas13 @JuanDuquevan Mattie Fellows

▶️ (Poster) Dreaming in Code for Curriculum Learning in Open-Ended Worlds, Hall A #213, Wednesday 17:00 - 18:45, led by @k_mitsides

▶️ (Poster) Evolution Strategies at the Hyperscale, Hall A #3712, Thursday 10:30 - 12:15, led by @bidiptas13 @JuanDuquevan Mattie Fellows

▶️ (Poster) The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind, Hall A #3504, Thursday 14:30 - 16:15, led by @_andreilupu

▶️ (Poster) LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning, Hall A #1705, Thursday 14:30 - 16:15, led by @sumeetrm @DanielNichols10 @CharlieLondon02 Peggy Li Fabio Pizzati

▶️ (Talk) Superhuman Scientific Discovery, RLxF Worskhop, Friday 15:30 - 16:00, by @robertarail

▶️ (Panel) RLxF Worskhop, Friday 16:00 - 17:00, by @robertarail

▶️ (Workshop) Amortising Bayesian Experimental Design for Sequential Information Gathering in LLMs, FoGen Workshop, Friday, led by @jakobhartmann99 James Harvey Jhonathan Navott

▶️ (Workshop) Elicitation Format Drives Divergent LLM Geopolitical Forecasts, AI Forecasting Workshop, Saturday, led by @hariharansuhas @michalbravansky

▶️ (Workshop) EGGROLL-IPO: Pluralistic Alignment via Decentralised Post-Training with Population Preferences, Pluralistic Alignment Workshop, Saturday, led by @alfie_lamerton

▶️ (Workshop Spotlight) Abstraction for Offline Goal-Conditioned Reinforcement Learning, DEMO Workshop, Saturday, led by @ClarisseWibault

[British Open-ended Learning and Discovery Lab @bold_lab_ai]

Another #ICML2026 BOLD paper, led by @bidiptas13, Mattie Fellows and @JuanDuquevan. We introduce EGGROLL, a novel general-purpose machine learning algorithm that provides a hundredfold increase in training speed over naïve evolution strategies.

EGGROLL practically eliminates the barrier between inference and training, allowing us to easily fine-tune LLMs for reasoning or train new architectures from scratch.

Check the paper at: https://t.co/fIYiU0WPna

[British Open-ended Learning and Discovery Lab @bold_lab_ai]

🪩 Next #ICML2026 paper: DiscoGen, led by @AlexDGoldie. DiscoGen is a procedural generator of algorithm discovery problems for AI research agents, supporting the creation of over 100 billion diverse tasks! Tasks vary across many axes, such as their field of machine learning or datasets they use. They can even support different evaluations, such as the time an algorithm takes to train (speedrunning ⚡️), its energy usage (efficiency 🌱) or its performance 💪!

Check out the paper at: https://t.co/W6YB9CwFno

Give the code a look: https://t.co/30oEbzJEgr

Or install the DiscoGen package for your research: pip install discogen

[British Open-ended Learning and Discovery Lab @bold_lab_ai]

🔦 Another #ICML2026 paper from BOLD, and this time it's a SPOTLIGHT led by @ClarisseWibault. In this work, we introduce Recurrent Structural Policy Gradient for Partially Observable Mean-field Games with Common Noise. Our algorithm learns more realistic history-dependent behaviour, while also leveraging known structure to benefit from faster convergence than model-free RL methods!

Check out the project page at: https://t.co/2EUuEkC2jw, which includes links to our Mean-Field Game library, as well as a Google Colab example implementation!

And the paper at: https://t.co/fNhM7aUMNO

[Ravi Hammond @ravihammond]

@_rockt @UCL_DARK @egrefen @robertarail @jparkerholder I'm excited to be a part of the journey!

[Ravi Hammond @ravihammond]

@bold_lab_ai Exciting to see BOLD finally announced!

[British Open-ended Learning and Discovery Lab @bold_lab_ai]

Hello world :)
We are BOLD — the British Open-ended Learning and Discovery Lab!

BOLD is a new academic research lab fully focussed on paradigm breaking discoveries in fundamental AI. We work towards more efficient & open AI that is built around human needs and capabilities.

To pursue these breakthroughs, we pioneer new modes of collaboration in academia that are more focussed, resourced, agile, and collaborative. Rather than fragmenting resources, today we are sunsetting 5 of the UKs leading AI labs to join forces under our joined scientific vision.

Our vision is centered around three pillars:
⚡ Beyond backpropagation – questioning the foundations of the field.
🤝 Human-centric learning & discovery – treating humans as core to our algorithms
🤖 Embodied learning – fast learning and adapting methods that deal with the messy real world

BOLD is backed by @UKRI_News and @EPSRC with £30M – and this is just the beginning. We are urgently looking for partners and sponsors to 10x this.

👉 https://t.co/eFVFW31mqz

👉 https://t.co/Eoad4G18KL

@j_foerst, @CULLYAntoine, @tonizza82, @shimon8282, @tonizza82, Ani Calinescu & @_rockt

[Alistair Letcher @_aletcher]

Model-free agents learn to maximise reward without modelling the environment. Right?

In recent work, we challenge this narrative by proving that agents, trained on a sufficiently rich set of goals, encode a unique and accurate world model in their value functions.
1/

[Ravi Hammond @ravihammond]

I've started my PhD at the University of Oxford, focusing on Artificial Intelligence! I’m beyond excited to see where this journey leads. Here’s to new knowledge, challenges, and discoveries ahead!

[Ravi Hammond @ravihammond]

I was awarded the Citizen of the Year today!

I received this award in recognition for my work with my annual bootcamp, where I train students to get job offers big-tech companies.

Here is the recording of my acceptance speech:
https://t.co/V8v4tbwtlZ

[Ravi Hammond @ravihammond]

I was on another podcast with Sav!

Topics:
-Oxford University
- Citizen of the Year
- Chat GPT
- Is AI damaging youth?
- Does AI scare you?
- Colonising Mars
- AI Mind Reading
- AR vs VR
- Electric Cars

Youtube
https://t.co/FX6KJZj3DX

Spotify:
https://t.co/02FFFyXLzF

[TheSeshWithSav @SeshWithSav]

https://t.co/ZMiXJj7Ynw new episode available now with the extremely gifted @ravihammond ! Don’t miss this one. Enjoy!
#ai #podcast #artificalintelligence #oxford #openai #chatgpt

[Ravi Hammond @ravihammond]

I had a great time chatting to Sav on his podcast last week.

Topics:
- Early struggles
- Big Tech
- NASA Space Robotics Challenge
- Super human AI
- Alphafold
- AI cure disease
- My bootcamp
- Collaborative AI

Spotify
https://t.co/QBZ10Di2S3

Youtube
https://t.co/pwhrtu9Mx1

[Ravi Hammond @ravihammond]

@polynoamial @chubicki Agreed, Survivor is the natural next step👍. Ensuring it has a good sense of humour won't be difficult!

[Ravi Hammond @ravihammond]

@polynoamial This is incredible work Noam, congratulations! I'm a grad students, but am working towards goal-oriented NLP for Catan. I follow your work extremely closely.

[Ravi Hammond @ravihammond]

I'm extremely excited to be attending #RLDM this week! As a new reinforcement learning student, it will be an honour to meet many experienced researchers in the field.

[Ravi Hammond @ravihammond]

@_andreilupu @j_foerst @robertarail @FacebookAI @UniofOxford Congratulations Andrei! I'm excited to read your future research with the team.

[Jakob Foerster @j_foerst]

I drafted a quick "How to" guide for writing ML papers. I hope this will be useful (if a little late!) for #NeurIPS2022. Happy paper writing and best of luck!!
https://t.co/rYXrxPPxfq

[Ravi Hammond @ravihammond]

@j_foerst This is an extremely useful guide Jakob; thanks a lot for writing it up. I especially like the "compare and contrast" against alternative attempts advice. I'll be sure to use this when writing my next paper!

[Ravi Hammond @ravihammond]

@polynoamial @demishassabis @TheGoffy I just flicked through your games. Great job with your final game as Germany! Crushing