collaborators

7 papers

cs.CR2026

Diversity Matters: Distributional Feature Coverage Sample Selection for Data-Efficient Backdoor Attacks

Yi Yang, Xiaoke Chen, Jinyang Huang +6

Backdoor attacks compromise training data so that a model retains clean accuracy but predicts an attacker-chosen target on triggered inputs. At very low poisoning rates, only a few…

cs.AI2026

AcademiClaw: When Students Set Challenges for AI Agents

Junjie Yu, Pengrui Lu, Weiye Si +75

Benchmarks within the OpenClaw ecosystem have thus far evaluated exclusively assistant-level tasks, leaving the academic-level capabilities of OpenClaw largely unexamined. We intro…

cs.CR2026

Checkerboard: A Simple, Effective, Efficient and Learning-free Clean Label Backdoor Attack with Low Poisoning Budget

Yi Yang, Jinyang Huang, Binbin Liu +5

Backdoor attacks threaten the deep learning supply chain by poisoning a small fraction of the training data so that a model behaves normally on clean inputs but misclassifies trigg…

cs.LG2026

LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation

Siqing Song, Chuang Wang, Yong Lang +2

Deploying large language models (LLMs) in resource-constrained environments is hindered by heavy computational and memory requirements. We present LBLLM, a lightweight binarization…

eess.AS2026

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs

Jing Peng, Chenghao Wang, Yi Yang +5

Speech LLM post-training increasingly relies on efficient cross-modal alignment and robust low-resource adaptation, yet collecting large-scale audio-text pairs remains costly. Text…

cs.LG2026

Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference

Quantong Qiu, Zhiyi Hong, Yi Yang +5

The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanis…