相关论文: Matrix-Driven Identification and Reconstruction of…

The challenge of Multimodal Deformable Image Registration (MDIR) lies in the conversion and alignment of features between images of different modalities. Generative models (GMs) cannot retain the necessary information enough from the source…

Image restoration aims to reconstruct the latent clear images from their degraded versions. Despite the notable achievement, existing methods predominantly focus on handling specific degradation types and thus require specialized models,…

Similarity-driven multi-view linear reconstruction (SiMLR) is an algorithm that exploits inter-modality relationships to transform large scientific datasets into smaller, more well-powered and interpretable low-dimensional spaces. SiMLR…

Dense Retrieval (DR) is now considered as a promising tool to enhance the memorization capacity of Large Language Models (LLM) such as GPT3 and GPT-4 by incorporating external memories. However, due to the paradigm discrepancy between text…

A significant challenge to make learning techniques more suitable for general purpose use is to move beyond i) complete supervision, ii) low dimensional data, iii) a single task and single view per instance. Solving these challenges allows…

In this work, a simple and efficient dual iterative refinement (DIR) method is proposed for dense correspondence between two nearly isometric shapes. The key idea is to use dual information, such as spatial and spectral, or local and global…

Depth pruning improves the deployment efficiency of large language models (LLMs) by identifying and removing redundant layers. A widely accepted standard for this identification process is to measure the similarity between layers using…

Deep learning (DL)-based tomographic SAR imaging algorithms are gradually being studied. Typically, they use an unfolding network to mimic the iterative calculation of the classical compressive sensing (CS)-based methods and process each…

Recently, Ainsworth et al. showed that using weight matching (WM) to minimize the $L^2$ distance in a permutation search of model parameters effectively identifies permutations that satisfy linear mode connectivity (LMC), where the loss…

We present Large Inverse Rendering Model (LIRM), a transformer architecture that jointly reconstructs high-quality shape, materials, and radiance fields with view-dependent effects in less than a second. Our model builds upon the recent…

Software reuse has long been recognized as a critical and widely studied topic in software engineering, offering substantial benefits in reducing development costs, improving software quality, and enhancing operational efficiency. This…

Detecting LLM training data is generally framed as a membership inference attack (MIA) problem. However, conventional MIAs operate passively on fixed model weights, using log-likelihoods or text generations. In this work, we introduce…

Selecting the best data mixture is critical for successful Supervised Fine-Tuning (SFT) of Multimodal Large Language Models. However, determining the optimal mixture weights across multiple domain-specific datasets remains a significant…

The rapid development of large language models has revolutionized natural language processing, but their fine-tuning remains computationally expensive, hindering broad deployment. Parameter-efficient fine-tuning (PEFT) methods, such as…

Model merging aims to combine multiple fine-tuned models into a single set of weights that performs well across all source tasks. While prior work has shown that merging can approximate the performance of individual fine-tuned models for…

Efficient estimation of high-dimensional matrices-including covariance and precision matrices-is a cornerstone of modern multivariate statistics. Most existing studies have focused primarily on the theoretical properties of the estimators…

Multimodal information retrieval (MMIR) has gained attention for its flexibility in handling text, images, or mixed queries and candidates. Recent breakthroughs in multimodal large language models (MLLMs) boost MMIR performance by…

In this paper, we unveil that Language Models (LMs) can acquire new capabilities by assimilating parameters from homologous models without retraining or GPUs. We first introduce DARE to set most delta parameters (i.e., the disparity between…

Large language models are becoming the go-to solution for the ever-growing number of tasks. However, with growing capacity, models are prone to rely on spurious correlations stemming from biases and stereotypes present in the training data.…

Language models (LMs) significantly improve the recognition accuracy of end-to-end (E2E) models on words rarely seen during training, when used in either the shallow fusion or the rescoring setups. In this work, we introduce LMs in the…