paper
referenced-only
2025
paper:park-iclr-in-context-learning-of-representati-2025Iclr: In-context learning of representations
ByCore Francisco Park·Andrew Lee·Ekdeep Singh Lubana·Yongyi Yang·Maya Okawa·Kento Nishi+2 more
Related work— refs + corpus + external arXiv
Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.
- The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and AnalysisJiazheng Li, Yanzheng Xiang, Hanqi Yan, Lin Gui, Yulan He Yuxiang Zhou2024≈ 78%
- Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context LearningSubhabrata Dutta, Ahmed Elshabrawy, Harish Tayyar Madabushi, Iryna Gurevych Jingcheng Niu2025≈ 76%
- Enhancing Multimodal In-Context Learning via Inductive-Deductive ReasoningHaonan Wang, Yuyan Chen, Jun Chen, Gang Liu, Qian Wang, Jiahong Yan, Yanghua Xiao Haoyu Wang2026≈ 76%
- Next-token pretraining implies in-context learningPaul M. Riechers and Henry R. Bigelow and Eric A. Alt and Adam Shai2025≈ 74%
- ICPRL: Acquiring Physical Intuition from Interactive ControlPi Bu, Ye Wang, B\"orje F. Karlsson, Ziming Wang, Tengtao Song, Qi Zhu, Jun Song, Shuo Zhang, Zhiming Ding, Bo Zheng Xinrun Xu2026≈ 74%
- Many-Shot CoT-ICL: Making In-Context Learning Truly LearnLemao Liu, Mo Yu, Dit-Yan Yeung Tsz Ting Chung2026≈ 74%
- 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≈ 74%
- Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern TransformersKarsten Roth, Quentin Bouniot, Wenjia Xu, Zeynep Akata Yiran Huang2026≈ 73%
- 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≈ 73%
- Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and BottlenecksSharon Li Yu Wang2026≈ 73%
- In-Context Reinforcement Learning via Communicative World ModelsTao Li, Yingdong Lu, Juntao Chen Fernando Martinez-Lopez2025≈ 72%
- Crafting a Good Prompt or Providing Exemplary Dialogues? A Study of In-Context Learning for Persona-based Dialogue GenerationYajing Wan, Yuru Zhang, Jing Chen, Ling Cheng, Qian Shao, Yongzhu Chang, Tangjie Lv, Rongsheng Zhang Jiashu Pu2024≈ 72%
- Implicit Statistical Inference in Transformers: Approximating Likelihood-Ratio Tests In-ContextSiddhant Gadkari Faris Chaudhry2026≈ 72%
- Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-TuningXuzheng He, Luoao Deng, Chak Tou Leong, Fan Wang, Yanzhao Yan, Xiaoyu Shen, Qiang Zhang Qingyu Yin2024≈ 72%
- Mechanistic Fine-tuning for In-context LearningPeng Luo, Mariko Kato, Rin Kaenbyou, Naoya Inoue Hakaze Cho2025≈ 72%
- ≈ 67%
- ≈ 67%
- ≈ 67%
- ≈ 67%
- ≈ 67%
- A Mathematical Framework for Transformer Circuitsin corpus2021≈ 66%
- The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?in corpus2025≈ 65%
- Learning without neurons in physical systemsin corpus2022≈ 65%
- ≈ 65%
- The Platonic Representation Hypothesisin corpus2024≈ 65%
- ≈ 65%
- ≈ 65%
- The World Inside Neural Networksin corpus2026≈ 64%
- Model Alignment Searchin corpus2025≈ 64%
- ≈ 64%
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,
- 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
- Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts
Llama-3.1-8B solves cyclic arithmetic (e.g., "what month is six months after August?") not by performing modular addition in the period of the cyclic concept (12 for months, 7 for days of the week) as