activity
20242026
collaborators

7 papers

cs.CL2026

Punctuation-aware Hybrid Trainable Sparse Attention for Large Language Models

Junxiang Qiu, Shuo Wang, Zhengsu Chen +4

Attention serves as the fundamental mechanism for long-context modeling in large language models (LLMs), yet dense attention becomes structurally prohibitive for long sequences due…

cs.CV2025

Accelerating Controllable Generation via Hybrid-grained Cache

Lin Liu, Huixia Ben, Shuo Wang +4

Controllable generative models have been widely used to improve the realism of synthetic visual content. However, such models must handle control conditions and content generation…

cs.CV2025

Accelerating Diffusion Transformer via Gradient-Optimized Cache

Junxiang Qiu, Lin Liu, Shuo Wang +3

Feature caching has emerged as an effective strategy to accelerate diffusion transformer (DiT) sampling through temporal feature reuse. It is a challenging problem since (1) Progre…

cs.CV2025

Accelerating Diffusion Transformer via Error-Optimized Cache

Junxiang Qiu, Shuo Wang, Jinda Lu +4

Diffusion Transformer (DiT) is a crucial method for content generation. However, it needs a lot of time to sample. Many studies have attempted to use caching to reduce the time con…

cs.LG2025

DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector

Jinghan Li, Yuan Gao, Jinda Lu +4

Graph Anomaly Detection (GAD) is crucial for identifying abnormal entities within networks, garnering significant attention across various fields. Traditional unsupervised methods,…

cs.CV2025

DAMA: Data- and Model-aware Alignment of Multi-modal LLMs

Jinda Lu, Junkang Wu, Jinghan Li +6

Direct Preference Optimization (DPO) has shown effectiveness in aligning multi-modal large language models (MLLM) with human preferences. However, existing methods exhibit an imbal…