Qian Li
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
ML×1Complexity×1Crypto×1
Frequent co-authors
Research Timeline
2026
Rethinking Fraud Safety Evaluation: Multi-Round Attacks Reveal Safety-Utility Tradeoffs in Graph-Context LLM Defenders
The paper evaluates graph-context LLM defenders against multi-round, adaptive fraud attacks, finding that while graph context improves early safety, it significantly increases benign over-refusal due to how the LLM consumes structured context.
Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete
The paper demonstrates that positional encodings are not necessary for transformers to achieve universal computation, showing that the inherent mechanism of sliding context windows already provides sufficient positional information.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.CCRecentJun 1, 2026
Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete
The paper demonstrates that positional encodings are not necessary for transformers to achieve universal computation, showing that the inherent mechanism of sliding context windows already provides su…
View →
cs.CRRecentMay 20, 2026