ABS uses Behavioral Divergence to adaptively scale batch sizes in RL according to policy volatility, enabling effective large-batch large-network training on ALE benchmarks.
arXiv preprint arXiv:2005.04305 , year=
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
representative citing papers
ShinkaEvolve improves sample efficiency in LLM-driven program evolution via parent sampling, code novelty rejection-sampling, and bandit LLM ensemble selection, achieving new SOTA circle packing with 150 samples and gains on math reasoning and competitive programming tasks.
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.
Repeating 0.1% of training data 100 times degrades an 800M parameter model's performance to that of a 400M model by damaging copying mechanisms and induction heads associated with generalization.
Ranked preference modeling outperforms imitation learning for language model alignment and scales more favorably with model size.
Effective data transferred from pre-training to fine-tuning is described by a power law in model parameter count and fine-tuning dataset size, acting like a multiplier on the fine-tuning data.
Sakana Fugu trains LLM orchestrators using fine-tuning, evolutionary algorithms, and RL to build query-adaptive multi-agent scaffolds, claiming SOTA results on benchmarks including SWE-Bench Pro and GPQA-Diamond.
Hybrid neuromorphic-ANN models outperform standard deep learning on few-shot benchmarks and under occlusion/impulse noise via astrocytic modulation and spiking dynamics.
Continued AI scaling remains feasible only if efficiency doublings recur repeatedly to keep logical compute affordable.
citing papers explorer
-
Scalable Reinforcement Learning via Adaptive Batch Scaling
ABS uses Behavioral Divergence to adaptively scale batch sizes in RL according to policy volatility, enabling effective large-batch large-network training on ALE benchmarks.