ICLR 2025 "in-context learning" Papers

13 papers found

BenTo: Benchmark Reduction with In-Context Transferability

Hongyu Zhao, Ming Li, Lichao Sun et al.

ICLR 2025poster

Can In-context Learning Really Generalize to Out-of-distribution Tasks?

Qixun Wang, Yifei Wang, Xianghua Ying et al.

ICLR 2025posterarXiv:2410.09695
15
citations

Density estimation with LLMs: a geometric investigation of in-context learning trajectories

Toni Liu, Nicolas Boulle, Raphaël Sarfati et al.

ICLR 2025posterarXiv:2410.05218
2
citations

Differential Transformer

Tianzhu Ye, Li Dong, Yuqing Xia et al.

ICLR 2025posterarXiv:2410.05258

Efficient Cross-Episode Meta-RL

Gresa Shala, André Biedenkapp, Pierre Krack et al.

ICLR 2025poster

ELICIT: LLM Augmentation Via External In-context Capability

Futing Wang, Jianhao (Elliott) Yan, Yue Zhang et al.

ICLR 2025posterarXiv:2410.09343
6
citations

Implicit In-context Learning

Zhuowei Li, Zihao Xu, Ligong Han et al.

ICLR 2025posterarXiv:2405.14660
8
citations

Improving Large Language Model Planning with Action Sequence Similarity

Xinran Zhao, Hanie Sedghi, Bernd Bohnet et al.

ICLR 2025posterarXiv:2505.01009
5
citations

Inference Scaling for Long-Context Retrieval Augmented Generation

Zhenrui Yue, Honglei Zhuang, Aijun Bai et al.

ICLR 2025posterarXiv:2410.04343
51
citations

On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery

Renpu Liu, Ruida Zhou, Cong Shen et al.

ICLR 2025posterarXiv:2410.13981
4
citations

Task Descriptors Help Transformers Learn Linear Models In-Context

Ruomin Huang, Rong Ge

ICLR 2025poster
3
citations

Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought

Jianhao Huang, Zixuan Wang, Jason Lee

ICLR 2025posterarXiv:2502.21212
18
citations

Why In-Context Learning Models are Good Few-Shot Learners?

Shiguang Wu, Yaqing Wang, Quanming Yao

ICLR 2025poster