2025
Introducing Visual Perception Token into Multimodal Large Language Model.
CoRR, February, 2025
CoT-Valve: Length-Compressible Chain-of-Thought Tuning.
CoRR, February, 2025
2024
TinyFusion: Diffusion Transformers Learned Shallow.
CoRR, 2024
Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient.
CoRR, 2024
LiteFocus: Accelerated Diffusion Inference for Long Audio Synthesis.
CoRR, 2024
Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
SlimSAM: 0.1% Data Makes Segment Anything Slim.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Isomorphic Pruning for Vision Models.
Proceedings of the Computer Vision - ECCV 2024, 2024
DeepCache: Accelerating Diffusion Models for Free.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
2023
0.1% Data Makes Segment Anything Slim.
CoRR, 2023
LLM-Pruner: On the Structural Pruning of Large Language Models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Structural Pruning for Diffusion Models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
DepGraph: Towards Any Structural Pruning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
2022
Prompting to Distill: Boosting Data-Free Knowledge Distillation via Reinforced Prompt.
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022
2021
A Trigger-Sense Memory Flow Framework for Joint Entity and Relation Extraction.
Proceedings of the WWW '21: The Web Conference 2021, 2021
MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021
Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition.
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021
2020
Enrich cross-lingual entity links for online wikis via multi-modal semantic matching.
Inf. Process. Manag., 2020
Boosting Cross-lingual Entity Alignment with Textual Embedding.
Proceedings of the Natural Language Processing and Chinese Computing, 2020
Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Network.
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020
SynET: Synonym Expansion using Transitivity.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2020, 2020
Adversarial Self-Supervised Data-Free Distillation for Text Classification.
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 2020