Xinyin Ma

58 papers A* 15A 1Journal 35Unranked 7
YearRankTypeTitle / Venue / Authors
2026 J jnl
Invisible Safety Threat: Malicious Finetuning for LLM via Steganography.
CoRR
Guangnian Wan, Xinyin Ma, Gongfan Fang, Xinchao Wang
2026 J jnl
Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models.
CoRR
Guangnian Wan, Qi Li, Gongfan Fang, Xinyin Ma, Xinchao Wang
2026 A* conf
Taming the Phantom: Token-Asymmetric Filtering for Hallucination Mitigation in Large Vision-Language Models.
AAAI
Shuyi Ouyang, Hongyi Wang, Gongfan Fang, Xinyin Ma, Lanfen Lin, Xinchao Wang
2026 J jnl
dVoting: Fast Voting for dLLMs.
CoRR
Sicheng Feng, Zigeng Chen, Xinyin Ma, Gongfan Fang, Xinchao Wang
2025 — conf
CoT-Valve: Length-Compressible Chain-of-Thought Tuning.
ACL (1)
Xinyin Ma, Guangnian Wan, Runpeng Yu, Gongfan Fang, Xinchao Wang
2025 J jnl
CoT-Valve: Length-Compressible Chain-of-Thought Tuning.
CoRR
Xinyin Ma, Guangnian Wan, Runpeng Yu, Gongfan Fang, Xinchao Wang
2025 A* conf
Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient.
CVPR
Zigeng Chen, Xinyin Ma, Gongfan Fang, Xinchao Wang
2025 J jnl
ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation.
CoRR
Siao Tang, Xinyin Ma, Gongfan Fang, Xinchao Wang
2025 A* conf
Diffusion Model is Effectively Its Own Teacher.
CVPR
Xinyin Ma, Runpeng Yu, Songhua Liu, Gongfan Fang, Xinchao Wang
2025 J jnl
Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding.
CoRR
Runpeng Yu, Xinyin Ma, Xinchao Wang
2025 J jnl
Efficient Reasoning Models: A Survey.
CoRR
Sicheng Feng, Gongfan Fang, Xinyin Ma, Xinchao Wang
2025 J jnl
Efficient Reasoning Models: A Survey.
Trans. Mach. Learn. Res.
Sicheng Feng, Gongfan Fang, Xinyin Ma, Xinchao Wang
2025 J jnl
In-Video Instructions: Visual Signals as Generative Control.
CoRR
Gongfan Fang, Xinyin Ma, Xinchao Wang
2025 J jnl
Introducing Visual Perception Token into Multimodal Large Language Model.
CoRR
Runpeng Yu, Xinyin Ma, Xinchao Wang
2025 J jnl
MixReasoning: Switching Modes to Think.
CoRR
Haiquan Lu, Gongfan Fang, Xinyin Ma, Qi Li, Xinchao Wang
2025 J jnl
SparseD: Sparse Attention for Diffusion Language Models.
CoRR
Zeqing Wang, Gongfan Fang, Xinyin Ma, Xingyi Yang, Xinchao Wang
2025 J jnl
Thinkless: LLM Learns When to Think.
CoRR
Gongfan Fang, Xinyin Ma, Xinchao Wang
2025 A* conf
TinyFusion: Diffusion Transformers Learned Shallow.
CVPR
Gongfan Fang, Kunjun Li, Xinyin Ma, Xinchao Wang
2025 J jnl
VeriThinker: Learning to Verify Makes Reasoning Model Efficient.
CoRR
Zigeng Chen, Xinyin Ma, Gongfan Fang, Ruonan Yu, Xinchao Wang
2025 J jnl
dKV-Cache: The Cache for Diffusion Language Models.
CoRR
Xinyin Ma, Runpeng Yu, Gongfan Fang, Xinchao Wang
2025 J jnl
dParallel: Learnable Parallel Decoding for dLLMs.
CoRR
Zigeng Chen, Gongfan Fang, Xinyin Ma, Ruonan Yu, Xinchao Wang
2024 A* conf
AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising.
NeurIPS
Zigeng Chen, Xinyin Ma, Gongfan Fang, Zhenxiong Tan, Xinchao Wang
2024 J jnl
AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising.
CoRR
Zigeng Chen, Xinyin Ma, Gongfan Fang, Zhenxiong Tan, Xinchao Wang
2024 J jnl
Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient.
CoRR
Zigeng Chen, Xinyin Ma, Gongfan Fang, Xinchao Wang
2024 A* conf
DeepCache: Accelerating Diffusion Models for Free.
CVPR
Xinyin Ma, Gongfan Fang, Xinchao Wang
2024 — conf
Isomorphic Pruning for Vision Models.
ECCV (30)
Gongfan Fang, Xinyin Ma, Michael Bi Mi, Xinchao Wang
2024 J jnl
Isomorphic Pruning for Vision Models.
CoRR
Gongfan Fang, Xinyin Ma, Michael Bi Mi, Xinchao Wang
2024 A* conf
Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching.
NeurIPS
Xinyin Ma, Gongfan Fang, Michael Bi Mi, Xinchao Wang
2024 J jnl
Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching.
CoRR
Xinyin Ma, Gongfan Fang, Michael Bi Mi, Xinchao Wang
2024 A conf
LiteFocus: Accelerated Diffusion Inference for Long Audio Synthesis.
INTERSPEECH
Zhenxiong Tan, Xinyin Ma, Gongfan Fang, Xinchao Wang
2024 J jnl
LiteFocus: Accelerated Diffusion Inference for Long Audio Synthesis.
CoRR
Zhenxiong Tan, Xinyin Ma, Gongfan Fang, Xinchao Wang
2024 A* conf
Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising.
NeurIPS
Gongfan Fang, Xinyin Ma, Xinchao Wang
2024 J jnl
Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising.
CoRR
Gongfan Fang, Xinyin Ma, Xinchao Wang
2024 A* conf
SlimSAM: 0.1% Data Makes Segment Anything Slim.
NeurIPS
Zigeng Chen, Gongfan Fang, Xinyin Ma, Xinchao Wang
2024 J jnl
TinyFusion: Diffusion Transformers Learned Shallow.
CoRR
Gongfan Fang, Kunjun Li, Xinyin Ma, Xinchao Wang
2023 J jnl
0.1% Data Makes Segment Anything Slim.
CoRR
Zigeng Chen, Gongfan Fang, Xinyin Ma, Xinchao Wang
2023 J jnl
DeepCache: Accelerating Diffusion Models for Free.
CoRR
Xinyin Ma, Gongfan Fang, Xinchao Wang
2023 A* conf
DepGraph: Towards Any Structural Pruning.
CVPR
Gongfan Fang, Xinyin Ma, Mingli Song, Michael Bi Mi, Xinchao Wang
2023 J jnl
DepGraph: Towards Any Structural Pruning.
CoRR
Gongfan Fang, Xinyin Ma, Mingli Song, Michael Bi Mi, Xinchao Wang
2023 A* conf
LLM-Pruner: On the Structural Pruning of Large Language Models.
NeurIPS
Xinyin Ma, Gongfan Fang, Xinchao Wang
2023 J jnl
LLM-Pruner: On the Structural Pruning of Large Language Models.
CoRR
Xinyin Ma, Gongfan Fang, Xinchao Wang
2023 A* conf
Structural Pruning for Diffusion Models.
NeurIPS
Gongfan Fang, Xinyin Ma, Xinchao Wang
2023 J jnl
Structural Pruning for Diffusion Models.
CoRR
Gongfan Fang, Xinyin Ma, Xinchao Wang
2022 A* conf
Prompting to Distill: Boosting Data-Free Knowledge Distillation via Reinforced Prompt.
IJCAI
Xinyin Ma, Xinchao Wang, Gongfan Fang, Yongliang Shen, Weiming Lu
2022 J jnl
Prompting to Distill: Boosting Data-Free Knowledge Distillation via Reinforced Prompt.
CoRR
Xinyin Ma, Xinchao Wang, Gongfan Fang, Yongliang Shen, Weiming Lu
2021 A* conf
A Trigger-Sense Memory Flow Framework for Joint Entity and Relation Extraction.
WWW
Yongliang Shen, Xinyin Ma, Yechun Tang, Weiming Lu
2021 J jnl
A Trigger-Sense Memory Flow Framework for Joint Entity and Relation Extraction.
CoRR
Yongliang Shen, Xinyin Ma, Yechun Tang, Weiming Lu
2021 — conf
Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition.
ACL/IJCNLP (1)
Yongliang Shen, Xinyin Ma, Zeqi Tan, Shuai Zhang, Wen Wang, Weiming Lu
2021 J jnl
Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition.
CoRR
Yongliang Shen, Xinyin Ma, Zeqi Tan, Shuai Zhang, Wen Wang, Weiming Lu
2021 — conf
MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations.
EMNLP (1)
Xinyin Ma, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Weiming Lu
2021 J jnl
MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations.
CoRR
Xinyin Ma, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Weiming Lu
2020 — conf
Adversarial Self-Supervised Data-Free Distillation for Text Classification.
EMNLP (1)
Xinyin Ma, Yongliang Shen, Gongfan Fang, Chen Chen, Chenghao Jia, Weiming Lu
2020 J jnl
Adversarial Self-Supervised Data-Free Distillation for Text Classification.
CoRR
Xinyin Ma, Yongliang Shen, Gongfan Fang, Chen Chen, Chenghao Jia, Weiming Lu
2020 — conf
Boosting Cross-lingual Entity Alignment with Textual Embedding.
NLPCC (2)
Wei Xu, Chen Chen, Chenghao Jia, Yongliang Shen, Xinyin Ma, Weiming Lu
2020 J jnl
Enrich cross-lingual entity links for online wikis via multi-modal semantic matching.
Inf. Process. Manag.
Weiming Lu, Peng Wang, Xinyin Ma, Wei Xu, Chen Chen
2020 A* conf
Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Network.
IJCAI
Zeyun Tang, Yongliang Shen, Xinyin Ma, Wei Xu, Jiale Yu, Weiming Lu
2020 J jnl
Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Network.
CoRR
Zeyun Tang, Yongliang Shen, Xinyin Ma, Wei Xu, Jiale Yu, Weiming Lu
2020 — conf
SynET: Synonym Expansion using Transitivity.
EMNLP (Findings)
Jiale Yu, Yongliang Shen, Xinyin Ma, Chenghao Jia, Chen Chen, Weiming Lu