Related papers: DELTA: Dynamic Layer-Aware Token Attention for Eff…

Large Language Models (LLMs) process every token through all layers of a transformer stack, causing wasted computation on simple queries and insufficient flexibility for harder ones that need deeper reasoning. Adaptive-depth methods can…

Attention is a core operation in large language models (LLMs) and vision-language models (VLMs). We present BD Attention (BDA), the first lossless algorithmic reformulation of attention. BDA is enabled by a simple matrix identity from Basis…

Recent reasoning Large Language Models (LLMs) demonstrate remarkable problem-solving abilities but often generate long thinking traces whose utility is unclear. Our work aims to improve their efficiency, enabling them to reach high…

Efficient long-sequence generation is a critical challenge for Large Language Models. While recent sparse decoding methods improve efficiency, they suffer from KV cache misalignment, where approximation errors accumulate and degrade…

The attention operator remains a critical performance bottleneck in large language models (LLMs), particularly for long-context scenarios. While FlashAttention is the most widely used and effective GPU-aware acceleration algorithm, it must…

Large Vision-Language Models (LVLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they still face critical challenges in modeling long-range dependencies under the usage of Rotary Positional…

Modern foundation models such as large language models (LLMs) and large multi-modal models (LMMs) require a massive amount of computational and memory resources. We propose a new framework to convert such LLMs/LMMs into a reduced-dimension…

Large Language Models (LLMs) face significant computational bottlenecks during inference due to the quadratic complexity of self-attention mechanisms, particularly as context lengths increase. We introduce SpecAttn, a novel training-free…

Transformer models are computationally costly on long sequences since regular attention has quadratic $O(n^2)$ time complexity. We introduce Wavelet-Enhanced Random Spectral Attention (WERSA), a novel mechanism of linear $O(n)$ time…

Sparsity has long been a central theme in LLM efficiency, but its role in context processing remains unresolved. As LLM workloads shift toward longer contexts and agentic interactions, the compute and memory bottlenecks of attention become…

Large language models (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underperform on multi-step reasoning tasks. Based on empirical analyses of the Qwen-2.5 model…

One of the most striking findings in modern research on large language models (LLMs) is that scaling up compute during training leads to better results. However, less attention has been given to the benefits of scaling compute during…

The growing demand for on-device large language model (LLM) inference highlights the need for efficient mobile edge computing (MEC) solutions, especially in resource-constrained settings. Speculative decoding offers a promising solution by…

Inference in diffusion large language models (dLLMs) is computationally expensive, as full self-attention must be repeatedly executed at each step of the denoising process without KV cache. Recent sparse attention methods for dLLMs mitigate…

LLMs have fundamentally transformed dense retrieval, upgrading backbones from discriminative encoders to generative architectures. However, a critical disconnect remains: while LLMs possess strong reasoning capabilities, current retrievers…

Large vision-language models (VLMs) enable joint processing of text and images. However, incorporating vision data significantly increases the prompt length, resulting in a longer time to first token (TTFT). This bottleneck can be…

The prefill stage in long-context LLM inference remains a computational bottleneck. Recent token-ranking heuristics accelerate inference by selectively processing a subset of semantically relevant tokens. However, existing methods suffer…

Long-context modeling is crucial for next-generation language models, yet the high computational cost of standard attention mechanisms poses significant computational challenges. Sparse attention offers a promising direction for improving…

As large language models (LLMs) continue to support increasingly longer contexts, the memory demand for key-value (KV) caches during decoding grows rapidly, becoming a critical bottleneck in both GPU memory capacity and PCIe bandwidth.…

Large language models (LLMs) process entire input contexts indiscriminately, which is inefficient when the information required to answer a query is localized within the context. We present dynamic context cutoff, a novel method enabling…