activity
20202026
most citedGLINT-RU: Gated Lightweight Intelligent Recurrent Units for Sequential Recommender Systems

1 citations · 1 across the 10 of their papers we have counts for

collaborators

11 papers

cs.CV2026

World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning

Wanyue Zhang, Wenxiang Wu, Wang Xu +6

Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that requires imagining how scene…

cs.CR2026

GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents

Xueyi Li, Zhuoneng Zhou, Zitao Liu +1

Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world educational environments, significantly boostin…

cs.CR2025

P-MIA: A Profiled-Based Membership Inference Attack on Cognitive Diagnosis Models

Mingliang Hou, Yinuo Wang, Teng Guo +6

Cognitive diagnosis models (CDMs) are pivotal for creating fine-grained learner profiles in modern intelligent education platforms. However, these models are trained on sensitive s…

cs.LG2025

PrivacyCD: Hierarchical Unlearning for Protecting Student Privacy in Cognitive Diagnosis

Mingliang Hou, Yinuo Wang, Teng Guo +6

The need to remove specific student data from cognitive diagnosis (CD) models has become a pressing requirement, driven by users' growing assertion of their "right to be forgotten"…

cs.CL2025

Iterative LLM-Based Generation and Refinement of Distracting Conditions in Math Word Problems

Kaiqi Yang, Hang Li, Yucheng Chu +3

Mathematical reasoning serves as a crucial testbed for the intelligence of large language models (LLMs), and math word problems (MWPs) are a popular type of math problems. Most MWP…

cs.CL2025

From Text to Talk: Audio-Language Model Needs Non-Autoregressive Joint Training

Tianqiao Liu, Xueyi Li, Hao Wang +4

Recent advances in large language models (LLMs) have attracted significant interest in extending their capabilities to multimodal scenarios, particularly for speech-to-speech conve…