All papers — page 15

• SPADE: Self-Play in Adaptive Synthetic Executable Environments
  arxiv:2608.19197 · 2026-08-19 · text available
• Sparse Autoencoders Find Highly Interpretable Features in Language Models
  arxiv:2309.08600 · 2023-09-15 · text available
• Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
  arxiv:2601.11061 · 2026-01-16 · text available
• Spurious Rewards: Rethinking Training Signals in RLVR
  arxiv:2506.10947 · 2025-06-12 · text available
• SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment
  arxiv:2512.02807 · 2025-12-02 · text available
• StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models
  arxiv:2403.07714 · 2024-03-12 · text available
• Step-size Optimization for Continual Learning
  arxiv:2401.17401 · 2024-01-30 · text available
• Structured Scaling of AI Discovery Across Diverse Scientific Domains
  arxiv:2604.19341 · 2026-04-21 · text available
• Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates
  arxiv:1708.07120 · 2017-08-23 · text available
• Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks
  acl:2022.emnlp-main.340 · 2022-04-16 · text available
• Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)
  arxiv:2507.12856 · 2025-07-17 · text available
• Symbolic Discovery of Optimization Algorithms
  arxiv:2302.06675 · 2023-02-13 · text available
• T5Gemma 2: Seeing, Reading, and Understanding Longer
  arxiv:2512.14856 · 2025-12-16 · text available
• Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves
  arxiv:2009.11243 · 2020-09-23 · text available
• The AdEMAMix Optimizer: Better, Faster, Older
  arxiv:2409.03137 · 2024-09-05 · text available
• The Art of Scaling Reinforcement Learning Compute for LLMs
  arxiv:2510.13786 · 2025-10-15 · text available
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
  arxiv:2503.02875 · 2025-03-04 · text available
• The GAN is dead; long live the GAN! A Modern GAN Baseline
  arxiv:2501.05441 · 2025-01-09 · text available
• The Illusion of Latent Generalization: Bi-directionality and the Reversal Curse
  arxiv:2604.04943 · 2026-03-13 · text available
• The Linear Centroids Hypothesis: Features as Directions Learned by Local Experts
  arxiv:2604.11962 · 2026-04-13 · text available
• The Llama 3 Herd of Models
  arxiv:2407.21783 · 2024-07-31 · text available
• The Lookahead Limitation: Why Multi-Operand Addition is Hard for LLMs
  arxiv:2502.19981 · 2025-02-27 · text available
• The Loss Does Not See the Basis, but Adam Does
  arxiv:2608.05136 · 2026-08-05 · text available
• The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
  arxiv:1803.03635 · 2018-03-09 · text available