Thomas Ferraz
thomas-ferraz
AI & ML interests
NLP in portuguese
Organizations
Reasoning LLMs
-
Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models
Paper • 2502.04404 • Published • 24 -
Learning Adaptive Parallel Reasoning with Language Models
Paper • 2504.15466 • Published • 43 -
TTRL: Test-Time Reinforcement Learning
Paper • 2504.16084 • Published • 118 -
THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models
Paper • 2504.13367 • Published • 25
Retrieve-Reasoning
Reinforcement Learning
Reasoning LLMs
-
Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models
Paper • 2502.04404 • Published • 24 -
Learning Adaptive Parallel Reasoning with Language Models
Paper • 2504.15466 • Published • 43 -
TTRL: Test-Time Reinforcement Learning
Paper • 2504.16084 • Published • 118 -
THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models
Paper • 2504.13367 • Published • 25