Carta Thomas
@CartaThomas2
Followers
57
Following
6
Statuses
30
Ph.D student at INRIA in the @FlowersINRIA. I am working on the how language and RL interact
Joined February 2023
RT @LorisGaven: Excited to share our work at the @IMOLNeurIPS2024 this Sunday! Swing by West Meeting Room 217-219 to check out our poster—I…
0
3
0
RT @ClementRomac: @CartaThomas2 and @LorisGaven will be presenting SAC-GLAM at @IMOLNeurIPS2024 tomorrow. #NeurIPS2024 TLDR: We traded PPO…
0
6
0
RT @ClementRomac: In GLAM (, we used PPO to ground LLMs in environments using online RL. In SAC-GLAM, we investiga…
0
1
0
RT @AndrewLampinen: Excited to share one of the main things I’ve been working on: scaling towards grounded language agents that can follow…
0
57
0
RT @risi1979: Introducing Neural Developmental Programs (NDPs)🧬🧠Instead of neural networks with fixed architectures, we allow neural networ…
0
269
0
RT @ClementRomac: In our last @icmlconf paper, we study how LLMs can be aligned to external enviroment dynamics through online RL. 🎬 (by @…
0
4
0
We also leveraged BabyAI (@Love2Code, @DBahdanau) ➜ And took inspiration from RL4LM (@RajKumar_RRK @rajammanabrolu) ➜
The secret to aligning LMs to human preferences is reinforcement learning. But Why&How is it used? Announcing 💻RL4LMs: library to train any @huggingface LM w/ RL 👾GRUE: benchmark of 6 NLP tasks+rewards 📈NLPO: new RL alg 4 LMs 🌐
0
0
6