titleLess Is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection
authorsRuoyu Chen, Siyuan Liang, Jingzhi Li, Shiming Liu, Li Liu, Hua Zhang, et al.
date2026-10-26
venueIEEE Transactions on Pattern Analysis and Machine Intelligence
iddoi:10.1109/tpami.2026.3746930
affiliationChinese Academy of Sciences; Nanyang Technological University; University of Oulu; University of Science and Technology Beijing
linksdoi arXiv
cite
relatedBeyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation
AllocFlow: End-to-End Portfolio Trading Action Generation from Raw Market Data
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents
Focused Omni-Modal GUI Agents

bibtex

@article{chen2026less,
  title={Less Is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection},
  author={Ruoyu Chen and Siyuan Liang and Jingzhi Li and Shiming Liu and Li Liu and Hua Zhang and others},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2026},
  doi={10.1109/tpami.2026.3746930}
}