Skip to content

Author

Jianjun Zhao

We have 2 of 71 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Making Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding

EVICT is proposed, a training-free, hyperparameter-free, and lossless adaptive verification method for MoE speculative decoding that achieves up to 2.35x speedup over autoregressive decoding and an average 1.21x speedup over the state-of-the-art baseline EAGLE-3, while significantly reducing unnecessary expert activati...

Lehan Pan, Ziyang Tao, Ruo-Yu Pang et al. · 3 citations
Preprint Aug 2026

Branch and Bound for Relational Verification of Neural Networks

A branch-and-bound framework to mitigate the issue of verifying relational specifications against relational specifications, which iteratively splits the problem until all sub-problems are verified, and devise a relational neuron selection strategy based on the dual formulation of the verification problem.

Kota Fukuda, Zhen-Ya Zhang, Guan-Qin Zhang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.