collaborators

8 papers

cs.CL2026

ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails

Yan Wang, Zhixuan Chu, Zihao Xue +9

Reasoning-based LLM guardrails improve safety moderation by generating explicit rationales before issuing final decisions. However, their rationales do not always lead to faithful…

cs.AI2026

Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers

Zihao Xue, Yan Wang, Zhen Bi +7

Diffusion Transformers have become a powerful backbone for text-to-image generation, but their layered and cross-modal generation process makes safety control fundamentally differe…

cs.AI2026

Make LLM Learn to Synthesize from Streaming Experiences through Feedback

Zhenlin Hu, Yan Wang, Zhen Bi +7

Large language models (LLMs) have been widely adopted for synthetic data generation, significantly reducing annotation costs. However, most existing studies treat synthesis as a se…

cs.LG2026

Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs

Xianya Fang, Feiyang Ren, Xiang Chen +4

Multimodal LLMs are powerful but prone to object hallucinations, which describe non-existent entities and harm reliability. While recent unlearning methods attempt to mitigate this…

cs.LG2026

RooflineBench: A Benchmarking Framework for On-Device LLMs via Roofline Analysis

Zhen Bi, Xueshu Chen, Luoyang Sun +4

The transition toward localized intelligence through Small Language Models (SLMs) has intensified the need for rigorous performance characterization on resource-constrained edge ha…

cs.AI2026

Logical Structure as Knowledge: Enhancing LLM Reasoning via Structured Logical Knowledge Density Estimation

Zhen Bi, Zhenlin Hu, Xueshu Chen +7

The reasoning capabilities of Large Language Models (LLMs) are increasingly attributed to training data quality rather than mere parameter scaling. However, existing data-centric p…