1 citations · 1 across the 16 of their papers we have counts for
18 papers
ReTrace: Rejected-Trajectory Conditioning for Speculative Decoding
Luxi Lin, Zhanpeng Zeng, Shuang Peng +2
Speculative decoding accelerates autoregressive language model inference by having a lightweight draft model propose multiple candidate tokens, which are then verified in parallel…
Accelerating Unified Multimodal Models with Core-Expansion Routing and Unified Computation Scheduling
Wengyi Zhan, Chenqian Yan, Songwei Liu +2
Unified multimodal models jointly support understanding and generation, but incur substantial redundant computation across tokens, layers, and generation timesteps. Through token-i…
Parallel Vision Token Scheduling for Fast and Accurate Multimodal LMMs Inference
Wengyi Zhan, Mingbao Lin, Zhihang Lin +1
Multimodal large language models (MLLMs) deliver impressive vision-language reasoning but suffer steep inference latency because self-attention scales quadratically with sequence l…
DSNet: Detail-Semantic Deep Supervision Network for Medical Image Segmentation
Zhaohong Huang, Yuxin Zhang, Taojian Zhou +2
Deep Supervision Networks exhibit significant efficacy for the medical imaging community. Nevertheless, existing work merely supervises either the coarse-grained semantic features…
Speculative Decoding Reimagined for Multimodal Large Language Models
Luxi Lin, Zhihang Lin, Zhanpeng Zeng +1
This paper introduces Multimodal Speculative Decoding (MSD) to accelerate Multimodal Large Language Models (MLLMs) inference. Speculative decoding has been shown to accelerate Larg…
CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
Zhihang Lin, Mingbao Lin, Yuan Xie +1
This paper introduces Completion Pruning Policy Optimization (CPPO) to accelerate the training of reasoning models based on Group Relative Policy Optimization (GRPO). GRPO, while e…
DiffusionTrend: A Minimalist Approach to Virtual Fashion Try-On
Wengyi Zhan, Mingbao Lin, Shuicheng Yan +1
We introduce DiffusionTrend for virtual fashion try-on, which forgoes the need for retraining diffusion models. Using advanced diffusion models, DiffusionTrend harnesses latent inf…
AccDiffusion v2: Towards More Accurate Higher-Resolution Diffusion Extrapolation
Zhihang Lin, Mingbao Lin, Wengyi Zhan +1
Diffusion models suffer severe object repetition and local distortion when the inference resolution differs from its pre-trained resolution. We propose AccDiffusion v2, an accurate…
TextDestroyer: A Training- and Annotation-Free Diffusion Method for Destroying Anomal Text from Images
Mengcheng Li, Fei Chao
In this paper, we propose TextDestroyer, the first training- and annotation-free method for scene text destruction using a pre-trained diffusion model. Existing scene text removal…
UniVST: A Unified Framework for Training-free Localized Video Style Transfer
Quanjian Song, Mingbao Lin, Wengyi Zhan +3
This paper presents UniVST, a unified framework for localized video style transfer based on diffusion models. It operates without the need for training, offering a distinct advanta…
Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient Adaptation
Jingjing Xie, Yuxin Zhang, Mingbao Lin +2
This paper presents the first study to explore the potential of parameter quantization for multimodal large language models to alleviate the significant resource constraint encount…
EasyInv: Toward Fast and Better DDIM Inversion
Ziyue Zhang, Mingbao Lin, Shuicheng Yan +1
This paper introduces EasyInv, an easy yet novel approach that significantly advances the field of DDIM Inversion by addressing the inherent inefficiencies and performance limitati…
AccDiffusion: An Accurate Method for Higher-Resolution Image Generation
Zhihang Lin, Mingbao Lin, Meng Zhao +1
This paper attempts to address the object repetition issue in patch-wise higher-resolution image generation. We propose AccDiffusion, an accurate method for patch-wise higher-resol…
Move and Act: Enhanced Object Manipulation and Background Integrity for Image Editing
Pengfei Jiang, Mingbao Lin, Fei Chao
Current methods commonly utilize three-branch structures of inversion, reconstruction, and editing, to tackle consistent image editing task. However, these methods lack control ove…
AnySR: Realizing Image Super-Resolution as Any-Scale, Any-Resource
Wengyi Zhan, Mingbao Lin, Chia-Wen Lin +1
In an effort to improve the efficiency and scalability of single-image super-resolution (SISR) applications, we introduce AnySR, to rebuild existing arbitrary-scale SR methods into…
UIO-LLMs: Unbiased Incremental Optimization for Long-Context LLMs
Wenhao Li, Mingbao Lin, Yunshan Zhong +2
Managing long texts is challenging for large language models (LLMs) due to limited context window sizes. This study introduces UIO-LLMs, an unbiased incremental optimization approa…
Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference
Zhihang Lin, Mingbao Lin, Luxi Lin +1
Multimodal large language models (MLLMs) demand considerable computations for inference due to the extensive parameters and the additional input tokens needed for visual informatio…
ObjectAdd: Adding Objects into Image via a Training-Free Diffusion Modification Fashion
Ziyue Zhang, Mingbao Lin, Quanjian Song +2
We introduce ObjectAdd, a training-free diffusion modification method to add user-expected objects into user-specified area. The motive of ObjectAdd stems from: first, describing e…