Matthew Macfarlane (@mattvmacfarlane) 's Twitter Profile
Matthew Macfarlane

@mattvmacfarlane

PhD Candidate @AmlabUvA, currently @Microsoft. Working on Reinforcement Learning , Search and Adaptive Computation.

ID: 1839303357300879365

calendar_today26-09-2024 13:57:54

145 Tweet

659 Followers

1,1K Following

Natasha Butt (@natashaeve4) 's Twitter Profile Photo

Introducing BenchAgents: a framework for automated benchmark creation, using multiple LLM agents that interact with each other and with developers to generate diverse, high-quality, and challenging benchmarks w/ Varun Chandrasekaran Neel Joshi Besmira Nushi 💙💛 Vidhisha Balachandran Microsoft Research 🧵1/8

Introducing BenchAgents: a framework for automated benchmark creation, using multiple LLM agents that interact with each other and with developers to generate diverse, high-quality, and challenging benchmarks w/ <a href="/VarunChandrase3/">Varun Chandrasekaran</a> <a href="/neelsj/">Neel Joshi</a> <a href="/besanushi/">Besmira Nushi 💙💛</a> <a href="/vidhisha_b/">Vidhisha Balachandran</a> <a href="/MSFTResearch/">Microsoft Research</a> 🧵1/8
ARC Prize (@arcprize) 's Twitter Profile Photo

Paper submissions (due today by 11:59pm UTC) are flowing in! We're excited to share these intriguing approaches from top universities, AI labs, and Fortune 500 companies soon. Review paper + winners announcement coming Dec. 6.

Jack Parker-Holder (@jparkerholder) 's Twitter Profile Photo

Introducing 🧞Genie 2 🧞 - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents 🧠.

Matthew Macfarlane (@mattvmacfarlane) 's Twitter Profile Photo

Great to have Searching Latent Program Spaces (arxiv.org/abs/2411.08706) recognised with a 🥉3rd place paper award in the ARC Prize! It was a pleasure working on this with Clem Bonnet . Looking forward to continuing to develop these ideas even further.

Cohere Labs (@cohere_labs) 's Twitter Profile Photo

Are you interested in policy + people + AI? Interested in program synthesis? How about reinforcement learning?🧐 December 17th, tune in with our Research Connections group to chat about these topics with Levi Lelis Anna Kawakami and Dennis Soemers!

Matthew Macfarlane (@mattvmacfarlane) 's Twitter Profile Photo

Thrilled to see our NeurIPS 2024 paper, Sequential Monte Carlo Policy Optimisation (arxiv.org/abs/2402.07963), featured in Kevin's Reinforcement Learning: A Comprehensive Overview, which additionally recognises SMC as a competitive, scalable online planner. A fantastic modern