Poster "transformer interpretability" Papers

9 papers found

Filters:poster transformer interpretability Clear all

Conference

AAAI 2025 (3,028)COLM 2025 (418)CVPR 2025 (2,873)ICCV 2025 (2,701)ICLR 2025 (3,827)ICML 2025 (3,340)ISMAR 2025 (229)NEURIPS 2025 (5,858)AAAI 2024 (2,289)CVPR 2024 (2,716)ECCV 2024 (2,387)ICLR 2024 (2,297)ICML 2024 (2,635)

Paper Type

poster (24,624)paper (8,558)oral (1,594)spotlight (1,421)highlight (975)

Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits

Areeb Ahmad, Abhinav Joshi, Ashutosh Modi

NEURIPS 2025arXiv:2511.20273

EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification

Lin Zhang, Wenshuo Dong, Zhuoran Zhang et al.

NEURIPS 2025arXiv:2502.06852

Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition

Aliyah Hsu, Georgia Zhou, Yeshwanth Cherapanamjeri et al.

ICLR 2025arXiv:2407.00886

FlowPrune: Accelerating Attention Flow Calculation by Pruning Flow Network

Shuo Xu, Yu Chen, Shuxia Lin et al.

Pinpointing Attention-Causal Communication in Language Models

Gabriel Franco, Mark Crovella

Selective induction Heads: How Transformers Select Causal Structures in Context

Francesco D'Angelo, francesco croce, Nicolas Flammarion

ICLR 2025arXiv:2509.08184

The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation

Patrick Kahardipraja, Reduan Achtibat, Thomas Wiegand et al.

NEURIPS 2025arXiv:2505.15807

Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers

Omer Sahin Tas, Royden Wagner

ICLR 2025arXiv:2406.11624

AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers

Reduan Achtibat, Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer et al.

ICML 2024arXiv:2402.05602