Artem Zholus
@artemzholus.bsky.social
Visiting Researcher at Meta; PhD student @mila.quebec. Ex: Intern @GoogleDeepMind, Intern @ EPFL, MSc@MIPT;
artemzholus.github.io
artemzholus.github.io
At the same time, it outperforms all domain-specific (diffusion) models while remaining virtually free of inductive bias. We demonstrate that the key to this success is simple: it's data and scale. 1/2
February 27, 2025 at 4:59 PM
At the same time, it outperforms all domain-specific (diffusion) models while remaining virtually free of inductive bias. We demonstrate that the key to this success is simple: it's data and scale. 1/2
Both papers compare with the most extensively tested baselines (DreamerV3 and TD-MPC2, both have 100+ envs in their papers). The second paper is extremely rigorous in the depth of their study (they had to prove a negative result). That’s why I think it’s more complicated than this.
November 28, 2024 at 7:16 AM
Both papers compare with the most extensively tested baselines (DreamerV3 and TD-MPC2, both have 100+ envs in their papers). The second paper is extremely rigorous in the depth of their study (they had to prove a negative result). That’s why I think it’s more complicated than this.
Hi Adhiraj, can you please add me to the pack? I work on LLMs and vision-based world models in my PhD.
November 25, 2024 at 4:45 PM
Hi Adhiraj, can you please add me to the pack? I work on LLMs and vision-based world models in my PhD.
A lot more exciting things are coming! For example, we’ll soon share the results from my internship at Google DeepMind. Stay tuned! 🧵5/5
November 23, 2024 at 4:32 AM
A lot more exciting things are coming! For example, we’ll soon share the results from my internship at Google DeepMind. Stay tuned! 🧵5/5
I also built a new foundational LLM for drug discovery: BindGPT bindgpt.github.io, which solves 3D generative molecule tasks using an LLM. We developed the full-stack pipeline: pretraining, SFT, RL, and prompting. It’s exciting for both LLM and AI4Science communities! 🧵4/5
BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning
BindGPT is a new framework for building drug discovery models that leverages compute-efficient pretraining, supervised funetuning, prompting, reinforcement learning, and tool use of LMs. This allows B...
bindgpt.github.io
November 23, 2024 at 4:32 AM
I also built a new foundational LLM for drug discovery: BindGPT bindgpt.github.io, which solves 3D generative molecule tasks using an LLM. We developed the full-stack pipeline: pretraining, SFT, RL, and prompting. It’s exciting for both LLM and AI4Science communities! 🧵4/5
A year later, I began my PhD at Mila, and my first PhD paper was accepted for an oral presentation at ICLR 2024! 🎉 We developed a world model-based agent that excels at RL memory tasks, leveraging a State-Space Model (SSM) as its primary memory backbone. Check it out: recall2imagine.github.io 🧵3/5
Recall to Imagine
R2I is a model-based agent with enhanced memory capabilities which shines in challenging memory reinforcement learning tasks.
recall2imagine.github.io
November 23, 2024 at 4:32 AM
A year later, I began my PhD at Mila, and my first PhD paper was accepted for an oral presentation at ICLR 2024! 🎉 We developed a world model-based agent that excels at RL memory tasks, leveraging a State-Space Model (SSM) as its primary memory backbone. Check it out: recall2imagine.github.io 🧵3/5
My past research also covered instruction following with embodied agents - I co-organized two NeurIPS competitions in 2021 and 2022. 2/5
November 23, 2024 at 4:32 AM
My past research also covered instruction following with embodied agents - I co-organized two NeurIPS competitions in 2021 and 2022. 2/5