POURCEL Guillaume
@GuillaumeAP
Followers
117
Following
3K
Media
5
Statuses
256
PhD student @univgroningen, intern @InriaScool, @FlowersINRIA. CogScI, AI. Inspired by brains (make RNNs behave like autograd) and behavior (open-ended goals)
Paris
Joined December 2017
RT @mpshanahan: Very sad to learn of the death on 18th July of Margaret (Maggie) Boden, a titan of cognitive science and AI. I met her many….
0
21
0
RT @LorisGaven: I’m attending #ICML this week! We’ll be presenting MAGELLAN during the poster session on Thursday with @CartaThomas2 & @Cle….
0
3
0
RT @pfau: You know you've got a big deal on your hands when you overwrite an existing acronym in your field
en.m.wikipedia.org
0
1
0
RT @arcprize: Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI by.@PourcelJulien, @cedcolas and @….
0
11
0
RT @PourcelJulien: Introducing SOAR 🚀, a self-improving framework for prog synth that alternates between search and learning (accepted to #….
0
39
0
RT @Thom_Wolf: we've seen nothing yet! hosted a 9-13 yo vibe-coding event w. @robertkeus this w-e (h/t @antonosika @LovableBuild). takeaway….
0
559
0
RT @karpathy: The (true) story of development and inspiration behind the "attention" operator, the one in "Attention is All you Need" that….
0
996
0
RT @RichardSSutton: I’ve changed so little. From my 1978 Bachelor’s thesis:. “The adult human mind is very complex, but the question remain….
0
64
0
RT @KhurramJaved_96: The correct parallel to Transformers is not RNNs. It is agents parameterized as RNNs that can choose to look back. C….
0
3
0
RT @ArtificialAnlys: DeepSeek takes the lead: DeepSeek V3-0324 is now the highest scoring non-reasoning model. This is the first time an op….
0
649
0
RT @cedcolas: learning progress is slow to compute empirically, but we can learn to predict it!. the agent can then organize its curriculum….
0
1
0
RT @robertghrist: so, i tried out OpenAI's new Deep Research w/o3-mini to do a literature search on network sheaves (something i'm the expe….
0
103
0
RT @noahdgoodman: Congrats to OAI on producing a reasoning model! Their opaque tweets demonstrate that they’ve (independently) found some o….
0
129
0
RT @karpathy: For friends of open source: imo the highest leverage thing you can do is help construct a high diversity of RL environments t….
0
825
0
RT @MichaelD1729: @joelbot3000 So when I first worked on unsupervised environment design, I was hoping to mitigate KU. There's a section in….
arxiv.org
A wide range of reinforcement learning (RL) problems - including robustness, transfer learning, unsupervised RL, and emergent complexity - require specifying a distribution of tasks or...
0
1
0
RT @ShaneLegg: I've been saying this within DeepMind for at least 10 years, with the additional clarification that it's about cognitive pro….
0
63
0