Westlake ENCODE Lab

@inproceedings{li2026lisa,
  title = {LISA: Locality-Informed Speculative Decoding for Accelerating Autoregressive Image Generation},
  author = {Li, Ying and Jian, Siyong and Wang, Zhaode and Chen, Zhiwen and Lv, Chengfei and Wang, Huan},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year = {2026},
}

@inproceedings{wang2026evar,
  title = {EVAR: Edge Visual Autoregressive Models via Principled Pruning},
  author = {Wang, Zefang and Li, Ying and Li, Yanyu and Su, Mingluo and Xu, Simin and Tian, Guanzhong and Wang, Huan},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year = {2026},
}

@inproceedings{zhang2026tars,
  title = {TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs},
  author = {Zhang, Kejia and Tao, Keda and Luo, Zhiming and Liu, Chang and Tang, Jiasheng and Wang, Huan},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year = {2026},
}

@inproceedings{li2026arcdecode,
  title = {ARC-Decode: Accelerated Decoding with Risk-Bounded Acceptance},
  author = {Li, Ying and Wang, Zhaode and Chen, Zhiwen and Lv, Chengfei and Wang, Huan},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
}

@inproceedings{li2026prismmoe,
  title = {Prism-MoE: Efficient Dense-to-MoE Conversion for Visual Autoregressive Generation},
  author = {Li, Ying and Wang, Zefang and Wang, Zhaode and Chen, Zhiwen and Lv, Chengfei and Wang, Huan},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
}

@inproceedings{du2026rlkv,
  title = {Which Heads Matter for Reasoning? RL-Guided KV Cache Compression},
  author = {Du, Wenjie and Jiang, Li and Tao, Keda and Liu, Xue and Wang, Huan},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
}

@inproceedings{tuo2026sparsessm,
  title = {SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot},
  author = {Tuo, Kaiwen and Wang, Huan},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
}

@inproceedings{liao2026jacobi,
  title = {Parallel Jacobi Decoding for Fast Autoregressive Image Generation},
  author = {Liao, Boya and Li, Ying and Jian, Siyong and Wang, Huan},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
}

@inproceedings{pan2026qvggt,
  title = {QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer},
  author = {Pan, Zhizhen and Wang, Hesong and Wang, Huan},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
}

@inproceedings{wang2026earlytom,
  title = {EarlyTom: Early Token Compression Completes Fast Video Understanding},
  author = {Wang, Hesong and Jin, Xin and Lu, Lu and Li, Chenhaowen and Chen, Jian and Liu, Qiang and Wang, Huan},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
}

@inproceedings{tao2026omnizip,
  title = {OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models},
  author = {Tao, Keda and Shao, Kele and Yu, Bohan and Wang, Weiqiang and Liu, Jian and Wang, Huan},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
}

@inproceedings{chen2026streamingtom,
  title = {StreamingTOM: Streaming Token Compression for Efficient Video Understanding},
  author = {Chen, Xueyi and Tao, Keda and Shao, Kele and Wang, Huan},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
}

@inproceedings{feng2026reasonmap,
  title = {Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps},
  author = {Feng, Sicheng and Wang, Song and Ouyang, Shuyi and Kong, Lingdong and Song, Zikai and Zhu, Jianke and Wang, Huan and Wang, Xinchao},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
}

@inproceedings{jin2026mergemix,
  title = {MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding},
  author = {Jin, Xin and Li, Siyuan and Jian, Siyong and Yu, Kai and Wang, Huan},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
}

@inproceedings{zhu2026obsdiff,
  title = {OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot},
  author = {Zhu, Junhan and Wang, Hesong and Su, Mingluo and Wang, Zefang and Wang, Huan},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
}

@inproceedings{feng2026rewardmap,
  title = {RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning},
  author = {Feng, Sicheng and Tuo, Kaiwen and Wang, Song and Kong, Lingdong and Zhu, Jianke and Wang, Huan},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
}

@inproceedings{li2026arpg,
  title = {Autoregressive Image Generation with Randomized Parallel Decoding},
  author = {Li, Haopeng and Yang, Jinyue and Li, Guoqi and Wang, Huan},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
}

@inproceedings{li2025freqexit,
  title = {FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware Guidance},
  author = {Li, Ying and Lv, Chengfei and Wang, Huan},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
}

@inproceedings{shao2025holitom,
  title = {HoliTom: Holistic Token Merging for Fast Video Large Language Models},
  author = {Shao, Kele and Tao, Keda and Qin, Can and You, Haoxuan and Sui, Yang and Wang, Huan},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
}

@inproceedings{zhang2025poisoncure,
  title = {Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs},
  author = {Zhang, Kejia and Tao, Keda and Tang, Jiasheng and Wang, Huan},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
}