paper
referenced-only
2023
paper:arxiv-2310-17639In-context learning dynamics with random binary sequences
ByEric J Bigelow·Ekdeep Singh Lubanaⓘ·Robert P Dick·Hidenori Tanaka·Tomer D UllmanGoodfire, Goodfire AI
Related work— refs + corpus + external arXiv
Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.
- Next-token pretraining implies in-context learningPaul M. Riechers and Henry R. Bigelow and Eric A. Alt and Adam Shai2025≈ 74%
- Implicit Statistical Inference in Transformers: Approximating Likelihood-Ratio Tests In-ContextSiddhant Gadkari Faris Chaudhry2026≈ 73%
- Context and Diversity Matter: The Emergence of In-Context Learning in World ModelsZhiyuan Chen, Yuxuan Zhong, Sunjian Zheng, Pengtao Shao, Bo Yu, Shaoshan Liu, Jianan Wang, Ning Ding, Yang Cao and Yu Kang Fan Wang2026≈ 73%
- The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and AnalysisJiazheng Li, Yanzheng Xiang, Hanqi Yan, Lin Gui, Yulan He Yuxiang Zhou2024≈ 71%
- Strategy Coopetition Explains the Emergence and Transience of In-Context LearningTed Moskovitz, Sara Dragutinovic, Felix Hill, Stephanie C.Y. Chan, Andrew M. Saxe Aaditya K. Singh2025≈ 71%
- Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context LearningSubhabrata Dutta, Ahmed Elshabrawy, Harish Tayyar Madabushi, Iryna Gurevych Jingcheng Niu2025≈ 70%
- Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement LearningHaoyu Ma, Chaoyi Deng, Mingsheng Long Jialong Wu2023≈ 70%
- Learning When to Act: Interval-Aware Reinforcement Learning with Predictive Temporal StructureDavide Di Gioia2026≈ 70%
- In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax AttentionXintian Pan, Siyu Chen, Zhuoran Yang Jianliang He2025≈ 70%
- Prototypical context-aware dynamics generalization for high-dimensional model-based reinforcement learningYao Mu, Dong Li, Qichao Zhang, Dongbin Zhao, Yuzheng Zhuang, Ping Luo, Bin Wang, Jianye Hao Junjie Wang2022≈ 70%
- Protocols for Learning Classifiers on Distributed DataJeff M. Phillips, Avishek Saha, Suresh Venkatasubramanian Hal Daume III2012≈ 69%
- ≈ 69%
- In-Context Reinforcement Learning via Communicative World ModelsTao Li, Yingdong Lu, Juntao Chen Fernando Martinez-Lopez2025≈ 69%
- Learning Latent Action World Models In The WildTushar Nagarajan, Basile Terver, Nicolas Ballas, Yann LeCun, Michael Rabbat Quentin Garrido2026≈ 69%
- StructRL: Recovering Dynamic Programming Structure from Learning Dynamics in Distributional Reinforcement LearningIvo Nowak2026≈ 69%
- Learning without neurons in physical systemsin corpus2022≈ 68%
- ≈ 68%
- ≈ 67%
- ≈ 66%
- ≈ 66%
- ≈ 65%
- ≈ 65%
- Information, Processes and Gamesin corpus≈ 65%
- Active inference: demystified and comparedin corpus2021≈ 65%
- ≈ 65%
- Life as we know itin corpus2013≈ 65%
- ≈ 64%
- ≈ 64%
- Emergence and Causality in Complex Systems: A Survey on Causal Emergence and Related Quantitative Studiesin corpus2023≈ 63%
- Active Inference: A Process Theoryin corpus2017≈ 63%
Similar preprints — Semantic Scholar
Cited by (3)
- Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
In-context learning and activation steering are the same operation on a latent-concept belief: context adds log-likelihood evidence while a steering vector adds a constant shift to the log prior odds,
- Forking Fast: Efficiently Estimating Uncertainty Dynamics in Text Generation
Resampling noise in reasoning-chain uncertainty dynamics is almost exactly multinomial, so most of the cost of Forking Paths Analysis re-measures structure that neighboring tokens already contain. On
- Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
Manifold steering — intervening on model activations along paths constrained to lie on a learned activation manifold M_h rather than along Euclidean linear directions — produces behavioral trajectorie