相关论文: Stochastic Sparse Attention for Memory-Bound Infer…

Weakly-supervised semantic segmentation (WSSS) with image-level labels is an important and challenging task. Due to the high training efficiency, end-to-end solutions for WSSS have received increasing attention from the community. However,…

Efficient long-context understanding and reasoning are increasingly vital for large language model (LLM) applications such as multi-turn dialogue and program analysis. However, the core self-attention mechanism scales quadratically with…

Attention mechanism has been crucial for image diffusion models, however, their quadratic computational complexity limits the sizes of images we can process within reasonable time and memory constraints. This paper investigates the…

There exist endless examples of dynamical systems with vast available data and unsatisfying mathematical descriptions. Sparse regression applied to symbolic libraries has quickly emerged as a powerful tool for learning governing equations…

To manage the complexity of transformers in video compression, local attention mechanisms are a practical necessity. The common approach of partitioning frames into patches, however, creates architectural flaws like irregular receptive…

The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods either compress visual embeddings or apply sparse attention…

As the length of input text increases, the key-value (KV) cache in LLMs imposes prohibitive GPU memory costs and limits long-context inference on resource constrained devices. Existing approaches, such as KV quantization and pruning, reduce…

Diffusion Transformers (DiTs) achieve strong video generation quality but suffer from high inference cost due to dense 3D attention, motivating sparse attention techniques for improving efficiency. However, existing training-free sparse…

Stochastic approximation (SA) is a key method used in statistical learning. Recently, its non-asymptotic convergence analysis has been considered in many papers. However, most of the prior analyses are made under restrictive assumptions…

With the rise of Transformer models in NLP and CV domain, Multi-Head Attention has been proven to be a game-changer. However, its expensive computation poses challenges to the model throughput and efficiency, especially for the long…

Sparse learning is a very important tool for mining useful information and patterns from high dimensional data. Non-convex non-smooth regularized learning problems play essential roles in sparse learning, and have drawn extensive attentions…

Multi-modality image fusion, particularly infrared and visible, plays a crucial role in integrating diverse modalities to enhance scene understanding. Although early research prioritized visual quality, preserving fine details and adapting…

Transformer models rely heavily on the scaled dot-product attention (SDPA) operation, typically implemented as FlashAttention. Characterized by its frequent interleaving of matrix multiplications and softmax operations, FlashAttention fails…

Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…

Attention steering is an important technique for controlling model focus, enabling capabilities such as prompt highlighting, where the model prioritises user-specified text. However, existing attention steering methods require explicit…

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide array of text-centric tasks. However, their `large' scale introduces significant computational and storage challenges, particularly in…

Are low-attention visual tokens truly redundant in vision-language reasoning? Existing pruning methods often assume so, ranking visual tokens by shallow text-to-image attention and discarding low-scoring patches to accelerate LVLM…

Quantization is a technique used in deep neural networks (DNNs) to increase execution performance and hardware efficiency. Uniform post-training quantization (PTQ) methods are common, since they can be implemented efficiently in hardware…

Large language models are expensive to deploy. We introduce Sparse Knowledge Distillation (SparseKD), a post-training method that compresses transformer models by combining structured SVD pruning with self-referential knowledge…

Under modern test-time compute and agentic paradigms, language models process ever-longer sequences. Efficient text generation with transformer architectures is increasingly constrained by the Key-Value cache memory footprint and bandwidth.…