Razvan Pascanu

Razvan Pascanu on Hugging Face Daily Papers: 7 papers, 2 in the top 3 of their day, 179 upvotes.

1. LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities 20 upvotes, #9 of 2025-04-23
2. Agency Is Frame-Dependent 21 upvotes, #8 of 2025-02-10
3. Retrieval-Augmented Decision Transformer: External Memory for In-context RL 6 upvotes, #38 of 2024-10-10
4. RecurrentGemma: Moving Past Transformers for Efficient Open Language Models 35 upvotes, #3 of 2024-04-12
5. Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models 58 upvotes, #2 of 2024-03-01
6. Improving fine-grained understanding in image-text pre-training 19 upvotes, #5 of 2024-01-19
7. Promoting Exploration in Memory-Augmented Adam using Critical Momenta 2 upvotes, #10 of 2023-07-20

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.