A self-speculative decoding method with training-free, knapsack-based adaptive layer selection that accounts for context-dependent attention overhead
A proactive planning strategy for long-context reasoning that focuses on preventing logical pitfalls and false assumptions before plan generation - ___[ACL 2026](https://2026.aclweb.org)___
Novel membership inference attack framework for large language models via an expectation maximization algorithm - ___[EACL 2026](https://2026.eacl.org)___
Listwise reranking with uncertainty-aware adaptive computation via Bayesian modeling of documents' relevance with TrueSkill - ___[NeurIPS 2025](https://neurips.cc)___
A bilingual benchmark for abstraction, comprehension, and reasoning evaluation in academic contexts - ___[Findings of EMNLP 2025](https://2025.emnlp.org/)___
Multi-scale adaptive context RAG for long-context large language models