Related papers: Merge and Guide: Unifying Model Merging and Guided…

Fine-grained entity recognition is crucial for reasoning and decision-making in task-oriented dialogues, yet current large language models (LLMs) continue to face challenges in domain adaptation and retrieval controllability. We introduce…

Graph Neural Networks (GNNs) have shown remarkable success in molecular tasks, yet their interpretability remains challenging. Traditional model-level explanation methods like XGNN and GNNInterpreter often fail to identify valid…

The integration of visual understanding and generation into unified multimodal models represents a significant stride toward general-purpose AI. However, a fundamental question remains unanswered by existing benchmarks: does this…

The fusion of input and guidance images that have a tradeoff in their information (e.g., hyperspectral and RGB image fusion or pansharpening) can be interpreted as one general problem. However, previous studies applied a task-specific…

Item indexing, which maps a large corpus of items into compact discrete representations, is critical for both discriminative and generative recommender systems, yet existing Vector Quantization (VQ)-based approaches struggle with the highly…

In-betweening human motion generation aims to synthesize intermediate motions that transition between user-specified keyframes. In addition to maintaining smooth transitions, a crucial requirement of this task is to generate diverse motion…

Knowledge Tracing (KT) aims to model a student's learning trajectory and predict performance on the next question. A key challenge is how to better represent the relationships among students, questions, and knowledge concepts (KCs).…

Masked generative models (MGMs) have emerged as a powerful framework for image synthesis, combining parallel decoding with strong bidirectional context modeling. However, generating high-quality samples typically requires many iterative…

Existing image generation models face critical challenges regarding the trade-off between computation and fidelity. Specifically, models relying on a pretrained Variational Autoencoder (VAE) suffer from information loss, limited detail, and…

Multimodal emotion recognition in conversation (MERC) requires representations that effectively integrate signals from multiple modalities. These signals include modality-specific cues, information shared across modalities, and interactions…

Molecular generative models often assume meaningful latent geometry, but apparent property predictability can reflect sequence-level shortcuts rather than chemical organization. We study this issue in an unsupervised autoregressive…

Unified multimodal models have recently attracted considerable attention for their remarkable abilities in jointly understanding and generating diverse content. However, as contexts integrate increasingly numerous interleaved multimodal…

This research aims to accelerate the inference speed of large language models (LLMs) with billions of parameters. We propose \textbf{S}mart \textbf{P}arallel \textbf{A}uto-\textbf{C}orrect d\textbf{E}coding (SPACE), an innovative approach…

Model merging combines knowledge from task-specific models into a unified multi-task model to avoid joint training on all task data. However, current methods face challenges due to representation bias, which can interfere with tasks…

Model merging has emerged as an efficient method to combine multiple single-task fine-tuned models. The merged model can enjoy multi-task capabilities without expensive training. While promising, merging into a single model often suffers…

Model merging aims to combine multiple task-specific expert models into a single model without joint retraining, offering a practical alternative to multi-task learning when data access or computational budget is limited. Existing methods,…

Model merging aims to integrate task-specific abilities from individually fine-tuned models into a single model without extra training. In recent model merging methods, task vector has become a fundamental building block, as it can…

We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different tasks, our method aligns the layers of the original networks…

Retrieval-Augmented Generation (RAG) has gained prominence as an effective method for enhancing the generative capabilities of Large Language Models (LLMs) through the incorporation of external knowledge. However, the evaluation of RAG…

Multi-task model merging offers a promising paradigm for integrating multiple expert models into a unified model without additional training. Existing state-of-the-art techniques, such as Task Arithmetic and its variants, merge models by…