Alexandre Brown 🇨🇦

PhD student, researcher at @Mila_Quebec ~ RL , working on humanoids and stuff

[Alexandre Brown 🇨🇦 @AlexandreBrown0]

🚀 I'm excited to share our new paper: SegDAC: Segmentation-Driven Actor-Critic for Visual Reinforcement Learning

🧠 SegDAC combines large vision models with online RL to reason about its environment at the object and sub-object level, avoiding noisy pixel-level reasoning.

🛠️ Using YOLO-World and SAM, SegDAC breaks the scene into semantically meaningful segments and learns to attend to a variable number of segments and proprioceptive signals, focusing on the most relevant information to complete the task.

⚡ Trained purely with online RL, without human labels or demonstrations.

🏆 Outperforms previous online RL state-of-the-art methods across all difficulty levels on our challenging visual generalization benchmark, with up to 2x better visual generalization in the hardest setting.

📄 Paper: https://t.co/hGfOlVf6O0
🌐 Project Page: https://t.co/edcgnRPrYw

Work done with @GlenBerseth at @Mila_Quebec

#ReinforcementLearning #RobotLearning #ArtificialIntelligence #Robotics

[John Robert Lamarr Greer @Ho66470Hokage]

@francoisfleuret The hard problem will come with even harder acceptance of the solution.

[Stone Tao @Stone_Tao]

to all the people who thought ai video gen of waves are realistic think again

nice work!

[François Fleuret @francoisfleuret]

Fight this urge of feeling smart because you disagree with smart people. It does not come from a good place.

[Alexandre Brown 🇨🇦 @AlexandreBrown0]

@hopsxbt @IlirAliu_ @fluence_project Your tweet makes no sense

[Alexandre Brown 🇨🇦 @AlexandreBrown0]

@crystalwizard What is consciousness?

[Alexandre Brown 🇨🇦 @AlexandreBrown0]

@creus_roger Nice.

[Joseph Suarez 🐡 @jsuarez]

I don't care what your model benchmarks say. Codex xhigh just tried to add bubble sort to my high-perf C experience buffer

[Glen Berseth @GlenBerseth]

Very proud and honoured to continue my work with @CIFAR_News and @Mila_Quebec. Via their support, my research reaches new heights!

[Vikash Kumar @Vikashplus]

Whole body controllers - effective with contact rich behaviors - are the unsung HEROs of robotics🦸‍♂️

Without them all we will have - is a bunch of over powerful pincers picking & placing tiny objects on the table.

(a bit harsh but true)

[The Habitant @the_habitant]

4 years ago, we finished dead-last in the NHL

Today, we are headed to the Final 4, after beating two other top-5 teams, all while being the second youngest team in the entire league.

This is the BEGINNING of the #GoHabsGo era. We’re nowhere near our prime.

[Alexandre Brown 🇨🇦 @AlexandreBrown0]

@GlenBerseth My intuition is that with some regularization in place to prevent useless continuous rotations, no joint limit might actually help getting out of weird and awkward joint states (just continue the rotation instead of needing to undo a motion).

[The Habitant @the_habitant]

I genuinely hate how this team plays when they have a lead so much

[Richard Sutton @RichardSSutton]

The bitter lesson in 26 words:

Don’t be distracted by human knowledge, as AI has been historically.
Instead focus on methods for creating knowledge that scale with computation, like search and learning.

[Yann LeCun @ylecun]

@ziv_ravid Continuous, high-dimensional, noisy data.
LLMs totally suck at those.

[Glen Berseth @GlenBerseth]

World models are becoming a powerful approach for making the most of available data, but how do we create them to help build better agents? Come check out this workshop at @RL_Conference and submit related ideas!

[Roger Creus Castanyer @creus_roger]

Launching Agentick 🤖🧠

A unified benchmark for training and evaluating general sequential decision-making agents.

RL agents, LLMs, VLMs, hybrids, bots, and humans can all be evaluated on:

same tasks. same seeds. same score.

First result: no single agent dominates.

🧵

[Harrison Kinsley @Sentdex]

what dat clanka doin

[Pedro Domingos @pmddomingos]

It's clever, saying you're restricting access to your model because it's dangerous, when the real reason is you don't have the compute. Makes you look more powerful instead of less.

[Alexandre Brown 🇨🇦 @AlexandreBrown0]

@pmddomingos Ah yes another "in 5 years" prediction

[Harrison Kinsley @Sentdex]

picking something up off the floor w/ a humanoid is more challenging than a backflip