Steve Collins
Switch527
·
AI & ML interests
None yet
Organizations
RL
-
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
Paper • 2506.06395 • Published • 133 -
MultiFinBen: A Multilingual, Multimodal, and Difficulty-Aware Benchmark for Financial LLM Evaluation
Paper • 2506.14028 • Published • 93 -
UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities
Paper • 2507.19766 • Published • 14
Benchmarks
-
MultiFinBen: A Multilingual, Multimodal, and Difficulty-Aware Benchmark for Financial LLM Evaluation
Paper • 2506.14028 • Published • 93 -
One Token to Fool LLM-as-a-Judge
Paper • 2507.08794 • Published • 31 -
A Survey of Context Engineering for Large Language Models
Paper • 2507.13334 • Published • 259
Emotion
Benchmarks
-
MultiFinBen: A Multilingual, Multimodal, and Difficulty-Aware Benchmark for Financial LLM Evaluation
Paper • 2506.14028 • Published • 93 -
One Token to Fool LLM-as-a-Judge
Paper • 2507.08794 • Published • 31 -
A Survey of Context Engineering for Large Language Models
Paper • 2507.13334 • Published • 259
RL
-
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
Paper • 2506.06395 • Published • 133 -
MultiFinBen: A Multilingual, Multimodal, and Difficulty-Aware Benchmark for Financial LLM Evaluation
Paper • 2506.14028 • Published • 93 -
UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities
Paper • 2507.19766 • Published • 14