dvnxmvl_hdf5 Profile Banner
Dane Malenfant Profile
Dane Malenfant

@dvnxmvl_hdf5

Followers
123
Following
1K
Media
15
Statuses
196

MSc. Computer Science @Mila_Quebec & @mcgillu in the LiNC lab | Currently distracted with multi-agent RL and neuroAI | Restless | Ēka ē-akimiht

Montréal, Québec
Joined December 2023
Don't wanna be here? Send us removal request.
@dvnxmvl_hdf5
Dane Malenfant
1 month
Preprint Alert 🚀.Multi-agent reinforcement learning (MARL) often assumes that agents know when other agents cooperate with them. But for humans, this isn’t always true. Example, plains indigenous groups used to leave resources for others to use at effigies called Manitokan. 1/8
Tweet media one
2
12
33
@dvnxmvl_hdf5
Dane Malenfant
11 hours
I really like how @weights_biases plots the KL in multi-agent PPO
Tweet media one
0
1
5
@dvnxmvl_hdf5
Dane Malenfant
1 day
RT @Mila_Quebec: That’s a wrap on the Indigenous AI Gathering 2025. Over two days, Indigenous knowledge keepers, technologists, youth, and….
0
2
0
@dvnxmvl_hdf5
Dane Malenfant
3 days
RT @EricElmoznino: Recently went on a podcast to talk about consciousness and AI. Very timely given how common interactions with AI systems….
0
2
0
@dvnxmvl_hdf5
Dane Malenfant
9 days
RT @bose_joey: 🎉Personal update: I'm thrilled to announce that I'm joining Imperial College London @imperialcollege as an Assistant Profess….
0
33
0
@dvnxmvl_hdf5
Dane Malenfant
9 days
RT @tmoellenhoff: Excited to announce our recent work on low-precision deep learning via biologically-inspired noisy log-normal multiplicat….
0
27
0
@dvnxmvl_hdf5
Dane Malenfant
12 days
Even simple tasks like sharing objects for others can be hard to learn.
@AmandaAskell
Amanda Askell
12 days
"Just train the AI models to be good people" might not be sufficient when it comes to more powerful models, but it sure is a dumb step to skip.
0
0
2
@dvnxmvl_hdf5
Dane Malenfant
13 days
What does it mean when I read IRL as inverse reinforcement learning instead of in real life?.
1
0
5
@dvnxmvl_hdf5
Dane Malenfant
16 days
RT @natashajaques: In our latest paper, we discovered a surprising result: training LLMs with self-play reinforcement learning on zero-sum….
0
60
0
@dvnxmvl_hdf5
Dane Malenfant
17 days
RT @thevineetjain: How to align your diffusion model with unseen objectives at inference time? Presenting Diffusion Tree Sampling/Search (D….
0
26
0
@dvnxmvl_hdf5
Dane Malenfant
18 days
RT @soniajoseph_: I like the framing of SAEs as analytic probes on CLIP: training them on CLS vs spatial tokens reveals when the network bu….
0
2
0
@dvnxmvl_hdf5
Dane Malenfant
20 days
RT @MartinKlissarov: As AI agents face increasingly long and complex tasks, decomposing them into subtasks becomes increasingly appealing.….
0
63
0
@dvnxmvl_hdf5
Dane Malenfant
20 days
RT @RayZiyan41307: From early ideas to what now feels like a book-length effort, it’s been a thoughtful journey with @MartinKlissarov and….
0
6
0
@dvnxmvl_hdf5
Dane Malenfant
20 days
RT @NSERC_CRSNG: 🔎🦬.‘Ways of the Bison’ is an inter-disciplinary education program supported by an #NSERC_PromoScience grant that teaches a….
0
2
0
@dvnxmvl_hdf5
Dane Malenfant
20 days
RT @PouyaBashivan: 🚨New paper 🚨.World models bake knowledge into weights, making them slow to adapt when environments change. We built one….
0
6
0
@dvnxmvl_hdf5
Dane Malenfant
20 days
RT @HeHerbie: 🧠 Can a neural network build a spatial map from scattered episodic experiences like humans do?. We introduce the Episodic Spa….
0
5
0
@dvnxmvl_hdf5
Dane Malenfant
22 days
RT @SSHRC_CRSH: #NIHM2025 Did you know #SSHRC has funding available for Indigenous master’s students? Learn more about the Indigenous Schol….
0
8
0
@dvnxmvl_hdf5
Dane Malenfant
22 days
RT @alexhdezgcia: 📣 Postdoc call! . We are looking for a postdoctoral researcher to work on machine learning research for materials discov….
0
3
0
@dvnxmvl_hdf5
Dane Malenfant
22 days
RT @TheEsraaSaleh: As someone who (very privately) does and enjoys creative writing, this quote nails it. My writing process is slow and of….
0
1
0
@dvnxmvl_hdf5
Dane Malenfant
22 days
RT @_akpiper: Does fiction aid memory because it gives us greater generative powers?.
0
1
0
@dvnxmvl_hdf5
Dane Malenfant
22 days
RT @benno_krojer: Started a new podcast with @tvergarabrowne !. Behind the Research of AI: .We look behind the scenes, beyond the polished….
0
13
0