Chongjun Tu

15 papers A* 1Journal 14
YearRankTypeTitle / Venue / Authors
2026 J jnl
Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs.
Int. J. Comput. Vis.
Chongjun Tu, Peng Ye, Dongzhan Zhou, Lei Bai, Gang Yu, Tao Chen, Wanli Ouyang
2026 J jnl
LSTM-MAS: A Long Short-Term Memory Inspired Multi-Agent System for Long-Context Understanding.
CoRR
Yichen Jiang, Peng Ye, Jiakang Yuan, Chongjun Tu, Lei Bai, Tao Chen
2026 A* conf
Mitigating Low-Quality Reasoning in MLLMs: Self-Driven Refined Multimodal CoT with Selective Thinking and Step-wise Visual Enhancement.
AAAI
Chongjun Tu, Peng Ye, Dongzhan Zhou, Tao Chen, Wanli Ouyang
2025 J jnl
Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs.
CoRR
Chongjun Tu, Peng Ye, Dongzhan Zhou, Lei Bai, Gang Yu, Tao Chen, Wanli Ouyang
2025 J jnl
ClipSAM: CLIP and SAM collaboration for zero-shot anomaly segmentation.
Neurocomputing
Shengze Li, Jianjian Cao, Peng Ye, Yuhan Ding, Chongjun Tu, Tao Chen
2025 J jnl
Efficient Architecture Search via Bi-Level Data Pruning.
IEEE Trans. Circuits Syst. Video Technol.
Chongjun Tu, Peng Ye, Weihao Lin, Hancheng Ye, Chong Yu, Tao Chen, Baopu Li, Wanli Ouyang
2025 J jnl
FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding.
CoRR
Chongjun Tu, Lin Zhang, Pengtao Chen, Peng Ye, Xianfang Zeng, Wei Cheng, Gang Yu, Tao Chen
2025 J jnl
PaceLLM: Brain-Inspired Large Language Models for Long-Context Understanding.
CoRR
Kangcong Li, Peng Ye, Chongjun Tu, Lin Zhang, Chunfeng Song, Jiamin Wu, Tao Yang, Qihao Zheng, Tao Chen
2025 J jnl
Revisiting Multimodal KV Cache Compression: A Frequency-Domain-Guided Outlier-KV-Aware Approach.
CoRR
Yaoxin Yang, Peng Ye, Xudong Tan, Chongjun Tu, Maosen Zhao, Jia Hao, Tao Chen
2025 J jnl
Sparse-to-Dense Training: A Novel Training Scheme to Enhance Vision Transformers.
IEEE Trans. Circuits Syst. Video Technol.
Yongqi Huang, Peng Ye, Chongjun Tu, Tao Chen, Tong He, Wanli Ouyang
2025 J jnl
TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models.
CoRR
Xudong Tan, Peng Ye, Chongjun Tu, Jianjian Cao, Yaoxin Yang, Lin Zhang, Dongzhan Zhou, Tao Chen
2024 J jnl
ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation.
CoRR
Shengze Li, Jianjian Cao, Peng Ye, Yuhan Ding, Chongjun Tu, Tao Chen
2024 J jnl
Δ-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers.
CoRR
Pengtao Chen, Mingzhu Shen, Peng Ye, Jianjian Cao, Chongjun Tu, Christos-Savvas Bouganis, Yiren Zhao, Tao Chen
2023 J jnl
Efficient Architecture Search via Bi-level Data Pruning.
CoRR
Chongjun Tu, Peng Ye, Weihao Lin, Hancheng Ye, Chong Yu, Tao Chen, Baopu Li, Wanli Ouyang
2023 J jnl
Partial Fine-Tuning: A Successor to Full Fine-Tuning for Vision Transformers.
CoRR
Peng Ye, Yongqi Huang, Chongjun Tu, Minglei Li, Tao Chen, Tong He, Wanli Ouyang