相关论文: Functional Component Ablation Reveals Specializati…

Representation-based Siamese networks have risen to popularity in lightweight text matching due to their low deployment and inference costs. While word-level attention mechanisms have been implemented within Siamese networks to improve…

Current transformer language models are trained with uniform computational budgets across all layers, implicitly assuming layer homogeneity. We challenge this assumption through empirical analysis of SmolLM2-135M, a 30-layer, 135M-parameter…

Transformers have dominated sequence processing tasks for the past seven years -- most notably language modeling. However, the inherent quadratic complexity of their attention mechanism remains a significant bottleneck as context length…

Multimodal Transformers serve as the backbone for state-of-the-art vision-language models, yet their quadratic attention complexity remains a critical barrier to scalability. In this work, we investigate the viability of Linear Attention…

Large language models have demonstrated remarkable performance; however, their massive parameter counts make deployment highly expensive. Low-rank approximation offers a promising compression solution, yet existing approaches have two main…

Modeling long sequences is crucial for various large-scale models; however, extending existing architectures to handle longer sequences presents significant technical and resource challenges. In this paper, we propose an efficient and…

Large Language Models (LLMs) are known to contain significant redundancy, yet a systematic explanation for why certain components, particularly in higher layers, are more redundant has remained elusive. In this work, we identify the BOS…

Recent advancements in medical imaging have resulted in more complex and diverse images, with challenges such as high anatomical variability, blurred tissue boundaries, low organ contrast, and noise. Traditional segmentation methods…

Principal component analysis (PCA) frequently suffers from the disturbance of outliers and thus a spectrum of robust extensions and variations of PCA have been developed. However, existing extensions of PCA treat all samples equally even…

The attention mechanism in Transformers is an important primitive for accurate and scalable sequence modeling. Its quadratic-compute and linear-memory complexity however remain significant bottlenecks. Linear attention and state-space…

Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency. However, conventional training-free structured pruning methods often employ a heuristic metric that…

Aspect-based Sentiment Analysis (ABSA) is a crucial NLP task that extracts fine-grained opinions and sentiments from text, such as product reviews and customer feedback. Existing methods often trade off efficiency for performance:…

Multimodal large reasoning models (MLRMs) often suffer from hallucinations that stem not only from insufficient visual grounding but also from imbalanced allocation between perception and reasoning processes. Building upon recent…

The quadratic computation complexity of self-attention has been a persistent challenge when applying Transformer models to vision tasks. Linear attention, on the other hand, offers a much more efficient alternative with its linear…

The generation of factually incorrect objects, commonly known as object hallucination, remains a persistent challenge in Large Vision-Language Models (LVLMs). Current approaches to address this issue - ranging from expensive data-driven…

Large Language Models (LLMs) have shown immense potential in enhancing various aspects of our daily lives, from conversational AI to search and AI assistants. However, their growing capabilities come at the cost of extremely large model…

We introduce FFN Fusion, an architectural optimization technique that reduces sequential computation in large language models by identifying and exploiting natural opportunities for parallelization. Our key insight is that sequences of…

Attention mechanisms, especially self-attention, have played an increasingly important role in deep feature representation for visual tasks. Self-attention updates the feature at each position by computing a weighted sum of features using…

Diffusion models and multi-scale features are essential components in semantic segmentation tasks that deal with remote-sensing images. They contribute to improved segmentation boundaries and offer significant contextual information.…

Large language models (LLMs) offer powerful capabilities but incur substantial computational costs, driving the need for efficient compression techniques. This study evaluates the impact of popular compression methods - Magnitude Pruning,…