Shenghong Li — accepted AI-conference papers

2026

BOLT: Decision‑Aligned Distillation and Budget-Aware Routing for Constrained Multimodal QA on Robots

Tengjun Ni, Xin Yuan, Shenghong Li, Kai Wu, Ren Ping Liu, Wei Ni +1

ICLR 2026poster

Robotic systems can require multimodal reasoning under stringent constraints of latency, memory, and energy. Standard instruction tuning and token-level distillation fail to deliver decision quality, reliability, and interpretability under these constraints. We introduce BOLT, a decision-aligned dis…

Cited by 0 Source ↗Scholar ↗

2021

DeHiB: Deep Hidden Backdoor Attack on Semi-supervised Learning via Adversarial Perturbation

Zhicong Yan, Gaolei Li, Yuan TIan, Jun Wu, Shenghong Li, Mingzhe Chen +1

AAAI 2021technical

The threat of data-poisoning backdoor attacks on learning algorithms typically comes from the labeled data. However, in deep semi-supervised learning (SSL), unknown threats mainly stem from the unlabeled data. In this paper, we propose a novel deep hidden backdoor (DeHiB) attack scheme for SSL-based…

Cited by 51 Source ↗PDF ↗Scholar ↗