相关论文: First Activations Matter: Training-Free Methods fo…

While deep learning is a powerful tool for natural language processing (NLP) problems, successful solutions to these problems rely heavily on large amounts of annotated samples. However, manually annotating data is expensive and…

The field of large language models (LLMs) has grown rapidly in recent years, driven by the desire for better efficiency, interpretability, and safe use. Building on the novel approach of "activation engineering," this study explores…

Small language models (SLMs) have emerged as efficient alternatives to large language models for task-specific applications. However, they are often employed in high-volume, low-latency settings, where efficiency is crucial. We propose…

Diffusion language models (DLMs) have emerged as a promising alternative to the long-dominant autoregressive (AR) paradigm, offering a parallelable decoding process that could yield greater efficiency. Yet, in practice, current open-source…

Active Learning (AL) has been a powerful paradigm for improving model efficiency and performance by selecting the most informative data points for labeling and training. In recent active learning frameworks, Large Language Models (LLMs)…

Multimodal Large Language Models (MLLMs) have demonstrated outstanding performance across a variety of domains. However, training MLLMs is often inefficient, as much of the computation is redundant due to the long input sequences from…

Large Language Models (LLMs) have achieved remarkable success across a wide range of natural language tasks, and recent efforts have sought to extend their capabilities to multimodal domains and resource-constrained environments. However,…

While Diffusion Transformers (DiT) have advanced non-autoregressive (NAR) speech synthesis, their high computational demands remain an limitation. Existing DiT-based text-to-speech (TTS) model acceleration approaches mainly focus on…

Can large language models converse in languages virtually absent from their training data? We investigate this question through a case study on Tulu, a Dravidian language with over 2 million speakers but minimal digital presence. Rather…

Vision-Language Action (VLA) models significantly advance robotic manipulation by leveraging the strong perception capabilities of pretrained vision-language models (VLMs). By integrating action modules into these pretrained models, VLA…

Data Augmentation (DA) -- enriching training data by adding synthetic samples -- is a technique widely adopted in Computer Vision (CV) and Natural Language Processing (NLP) tasks to improve models performance. Yet, DA has struggled to gain…

Large Language Models (LLMs) often struggle to maintain their original performance when faced with semantically coherent but task-irrelevant contextual information. Although prior studies have explored this issue using fixed-template or…

Sparse attention mechanisms aim to reduce computational overhead with minimal accuracy loss by selectively processing salient tokens. Despite their effectiveness, most methods merely exploit a model's inherent sparsity and thus plateau at…

Activation in deep neural networks is fundamental to achieving non-linear mappings. Traditional studies mainly focus on finding fixed activations for a particular set of learning tasks or model architectures. The research on flexible…

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for general-purpose robot control through natural language instructions. However, their high inference cost-stemming from large-scale token computation and…

Vision-Language-Action (VLA) models, particularly diffusion-based architectures, demonstrate transformative potential for embodied intelligence but are severely hampered by high computational and memory demands stemming from extensive…

As the context window expands, self-attention increasingly dominates the transformer's inference time. Therefore, accelerating attention computation while minimizing performance degradation is essential for the efficient deployment of Large…

The nonlinearity of activation functions used in deep learning models are crucial for the success of predictive models. There are several commonly used simple nonlinear functions, including Rectified Linear Unit (ReLU) and Leaky-ReLU…

Despite large successes of recent language models on diverse tasks, they suffer from severe performance degeneration in low-resource settings with limited training data available. Many existing works tackle this problem by generating…

Activation sparsity is a promising approach for accelerating large language model (LLM) inference by reducing computation and memory movement. However, existing activation sparsity methods typically apply uniform sparsity across…