All papers — page 17
- Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
arxiv:2006.16236· 2020-06-29 · text available - TTPO: Test-Time Policy Optimization
arxiv:2608.27448· 2026-08-27 · text available - TTRL: Test-Time Reinforcement Learning
arxiv:2504.16084· 2025-04-22 · text available - Understanding R1-Zero-Like Training: A Critical Perspective
arxiv:2503.20783· 2025-03-26 · text available - Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
arxiv:2604.02288· 2026-04-02 · text available - UniMASK: Unified Inference in Sequential Decision Problems
arxiv:2211.10869· 2022-11-20 · text available - Universal Reasoning Model
arxiv:2512.14693· 2025-12-16 · text available - Universal Transformers
arxiv:1807.03819· 2018-07-10 · text available - Universal Transformers Need Memory: Depth-State Trade-offs in Adaptive Recursive Reasoning
arxiv:2604.21999· 2026-04-23 · text available - Unlimiformer: Long-Range Transformers with Unlimited Length Input
arxiv:2305.01625· 2023-05-02 · text available - Unsupervised Elicitation of Language Models
arxiv:2506.10139· 2025-06-11 · text available - Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
arxiv:2006.09882· 2020-06-17 · text available - Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents
arxiv:2502.15840· 2025-02-21 · text available - Verbalizable Representations Form a Global Workspace in Language Models (Anthropic, July 2026)
url:transformer-circuits.pub/2026/workspace· 2026-07-06 · metadata only - VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
arxiv:2105.04906· 2021-05-11 · text available - VISReg: Variance-Invariance-Sketching Regularization for JEPA training
arxiv:2606.02572· 2026-06-01 · text available - Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
url:openai.com/research/weak-to-strong-generalization· 2023-12-14 · metadata only - Weight-Space Geometry of Offline Reasoning Training
arxiv:2606.23740· 2026-06-26 · text available - What Does It Take to Be a Good AI Research Agent? Studying the Role of Ideation Diversity
arxiv:2511.15593· 2025-11-19 · text available - When Activation Oracles Learn Not to Read: Concept-Specific Blind Spots in Fine-Tuned Oracles
arxiv:2607.23379· 2026-07-25 · text available - When Does Continual Learning Require Learning
arxiv:2607.07847· 2026-07-08 · text available - When Does LeJEPA Learn a World Model?
arxiv:2605.26379· 2026-05-25 · text available - Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls
arxiv:2510.00184· 2025-09-30 · text available - Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
arxiv:2603.24472· 2026-03-25 · text available