Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality Paper • 2405.21060 • Published May 31 • 63
Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning Paper • 2406.00392 • Published Jun 1 • 12
Show, Don't Tell: Aligning Language Models with Demonstrated Feedback Paper • 2406.00888 • Published Jun 2 • 30
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark Paper • 2406.01574 • Published Jun 3 • 42