Author

Qianqian Xu

Observed name: Xu, Qianqian

Institutions: Chinese Academy of Sciences, Institute of Computing Technology, Beijing Academy of Artificial Intelligence

Observed institutions: Chinese Academy of Sciences, Institute of Computing Technology, Beijing Academy of Artificial Intelligence

ORCID: 0000-0002-3512-7277

Observed ORCID: 0000-0002-3512-7277

OpenAlex ID: A5158726262

When 1+1 Backfires: Rethinking Relevance-Diversity Balancing for Sample-Aware Visual Token Reduction

2026 · Yihang Huang, Peisong Wen, et al. · ACM International Conference on Multimedia (ACM MM)

Compare to Correct: Pairwise-Guided Logit Adjustment for LLM Test-Time Scaling

2026 · Hua, Cong, Xu, Qianqian, et al. · arXiv (Cornell University)

Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment

2026 · Yang, Haoming, Ma, Ke, et al. · arXiv (Cornell University)

Works count: 3

Citation count:

H-index:

I10-index: