-
ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality
Paper • 2510.22037 • Published • 18 -
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 467 -
The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain
Paper • 2509.26507 • Published • 525 -
Scaling Language-Centric Omnimodal Representation Learning
Paper • 2510.11693 • Published • 97
Clément Castellon
Clemspace
AI & ML interests
Reinforcement learning, Neural Architecture Search, Transformers
Recent Activity
updated
a collection
9 days ago
Bangers 2025
updated
a collection
9 days ago
Bangers 2025
updated
a collection
9 days ago
Bangers 2025
Organizations
-
Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation
Paper • 2412.06531 • Published • 72 -
Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents
Paper • 2309.17207 • Published -
Titans: Learning to Memorize at Test Time
Paper • 2501.00663 • Published • 26 -
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Paper • 2502.11089 • Published • 165
-
ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality
Paper • 2510.22037 • Published • 18 -
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 467 -
The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain
Paper • 2509.26507 • Published • 525 -
Scaling Language-Centric Omnimodal Representation Learning
Paper • 2510.11693 • Published • 97
-
Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation
Paper • 2412.06531 • Published • 72 -
Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents
Paper • 2309.17207 • Published -
Titans: Learning to Memorize at Test Time
Paper • 2501.00663 • Published • 26 -
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Paper • 2502.11089 • Published • 165
datasets
0
None public yet