13 citations · 16 across the 17 of their papers we have counts for
19 papers
PGSB: Pretrained-Guided Shared Basis for LoRA Model Merging
Muqing Liu, Chongjie Si, Zhuoya Liu +1
Large pretrained models have achieved remarkable success across diverse domains, yet adapting them to multiple downstream tasks remains challenging: full fine-tuning is costly, whi…
FlexLoRA: Entropy-Guided Flexible Low-Rank Adaptation
Muqing Liu, Chongjie Si, Yuheng Jia
Large pre-trained models achieve remarkable success across diverse domains, yet fully fine-tuning incurs prohibitive computational and memory costs. Parameter-efficient fine-tuning…
AdaMuon: Adaptive Muon Optimizer
Chongjie Si, Debing Zhang, Wei Shen
We propose AdaMuon, a novel optimizer that combines element-wise adaptivity with orthogonal updates for large-scale neural network training. AdaMuon incorporates two tightly couple…
DualEdit: Dual Editing for Knowledge Updating in Vision-Language Models
Zhiyi Shi, Binjie Wang, Chongjie Si +3
Model editing aims to efficiently update a pre-trained model's knowledge without the need for time-consuming full retraining. While existing pioneering editing methods achieve prom…
Weight Spectra Induced Efficient Model Adaptation
Chongjie Si, Xuankun Yang, Muqing Liu +5
Large-scale foundation models have demonstrated remarkable versatility across a wide range of downstream tasks. However, fully fine-tuning these models incurs prohibitive computati…
MAP: Revisiting Weight Decomposition for Low-Rank Adaptation
Chongjie Si, Zhiyi Shi, Yadao Wang +3
The rapid development of large language models has revolutionized natural language processing, but their fine-tuning remains computationally expensive, hindering broad deployment.…
Revisiting Sparsity Constraint Under High-Rank Property in Partial Multi-Label Learning
Chongjie Si, Yidan Cui, Fuchao Yang +2
Partial Multi-Label Learning (PML) extends the multi-label learning paradigm to scenarios where each sample is associated with a candidate label set containing both ground-truth la…
Why Can Accurate Models Be Learned from Inaccurate Annotations?
Chongjie Si, Yidan Cui, Fuchao Yang +2
Learning from inaccurate annotations has gained significant attention due to the high cost of precise labeling. However, despite the presence of erroneous labels, models trained on…
NAN: A Training-Free Solution to Coefficient Estimation in Model Merging
Chongjie Si, Kangtao Lv, Jingjing Jiang +6
Model merging offers a training-free alternative to multi-task learning by combining independently fine-tuned models into a unified one without access to raw data. However, existin…
Co-Reinforcement Learning for Unified Multimodal Understanding and Generation
Jingjing Jiang, Chongjie Si, Jun Luo +2
This paper presents a pioneering exploration of reinforcement learning (RL) via group relative policy optimization for unified multimodal large language models (ULMs), aimed at sim…
Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations
Chongjie Si, Zhiyi Shi, Xuehui Wang +3
Adapting pre-trained foundation models for diverse downstream tasks is a core practice in artificial intelligence. However, the wide range of tasks and high computational costs mak…
Unveiling the Mystery of Weight in Large Foundation Models: Gaussian Distribution Never Fades
Chongjie Si, Jingjing Jiang, Wei Shen
This paper presents a pioneering exploration of the mechanisms underlying large foundation models' (LFMs) weights, aiming to simplify AI research. Through extensive observation and…
Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning
Chongjie Si, Zhiyi Shi, Shifan Zhang +3
Large language models demonstrate impressive performance on downstream tasks, yet they require extensive resource consumption when fully fine-tuning all parameters. To mitigate thi…
See Further for Parameter Efficient Fine-tuning by Standing on the Shoulders of Decomposition
Chongjie Si, Xiaokang Yang, Wei Shen
The rapid expansion of large foundation models within the pre-training and fine-tuning framework has underscored that larger models often yield better results. However, the scaling…
Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning
Chongjie Si, Xuehui Wang, Xue Yang +6
Adapting pre-trained foundation models for various downstream tasks has been prevalent in artificial intelligence. Due to the vast number of tasks and high costs, adjusting all par…
Tendency-driven Mutual Exclusivity for Weakly Supervised Incremental Semantic Segmentation
Chongjie Si, Xuehui Wang, Xiaokang Yang +1
Weakly Incremental Learning for Semantic Segmentation (WILSS) leverages a pre-trained segmentation model to segment new classes using cost-effective and readily available image-lev…
Appeal: Allow Mislabeled Samples the Chance to be Rectified in Partial Label Learning
Chongjie Si, Xuehui Wang, Yan Wang +2
In partial label learning (PLL), each instance is associated with a set of candidate labels among which only one is ground-truth. The majority of the existing works focuses on cons…
Complementary Classifier Induced Partial Label Learning
Yuheng Jia, Chongjie Si, Min-ling Zhang
In partial label learning (PLL), each training sample is associated with a set of candidate labels, among which only one is valid. The core of PLL is to disambiguate the candidate…
Multi-label Classification with High-rank and High-order Label Correlations
Chongjie Si, Yuheng Jia, Ran Wang +3
Exploiting label correlations is important to multi-label classification. Previous methods capture the high-order label correlations mainly by transforming the label matrix to a la…