Related papers: SSV: Sparse Speculative Verification for Efficient…

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.…

Vision Language Models (VLMs) have rapidly advanced in integrating visual and textual reasoning, powering applications across high-resolution image understanding, long-video analysis, and multi-turn conversation. However, their scalability…

Multimodal latent-space reasoning aims to replace explicit thinking with images by performing visual reasoning directly in a compact latent space. However, existing approaches largely rely on visual supervision and produce latent…

The synergistic mechanism based on Speculative Decoding (SD) has garnered considerable attention as a simple yet effective approach for accelerating the inference of large language models (LLMs). Nonetheless, the high rejection rates…

The inference process for large language models is slow and memory-intensive, with one of the most critical bottlenecks being excessive Key-Value (KV) cache accesses. This paper introduces "Double Sparsity," a novel post-training sparse…

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…

Sparse attention methods exploit the inherent sparsity in attention to speed up the prefilling phase of long-context inference, mitigating the quadratic complexity of full attention computation. While existing sparse attention methods rely…

Long-context inference is increasingly constrained by the KV cache: resident memory grows with context length, and decoding becomes limited by repeated High Bandwidth Memory (HBM) streaming rather than arithmetic. Existing methods such as…

Sparse Matrix-Vector Multiplication (SpMV) has become a critical performance bottleneck in the local deployment of sparse Large Language Models (LLMs), where inference predominantly operates on workloads during the decoder phase with a…

Speculative decoding (SD) accelerates large language model inference by allowing a lightweight draft model to propose outputs that a stronger target model verifies. However, its token-centric nature allows erroneous steps to propagate.…

As Large Language Models (LLMs) scale to longer context windows, the computational cost of attention mechanisms, which traditionally grows quadratically with input length, presents a critical challenge for real-time and memory-constrained…

Speculative Decoding (SD) accelerates inference in large language models by using a smaller draft model to propose tokens, which are then verified by a larger target model. However, the throughput gains of SD are fundamentally limited by a…

In vision-language models (VLMs), visual tokens usually bear a significant amount of computational overhead despite sparsity of information in them when compared to text tokens. To address this, most existing methods learn a network to…

Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verification is often the bottleneck (e.g. verification is $4\times$ slower than token generation when a…

Diffusion Large Language Models (dLLMs) enable breakthroughs in reasoning and parallel decoding but suffer from prohibitive quadratic computational complexity and memory overhead during inference. Current caching techniques accelerate…

Large Vision-Language Models (LVLMs) may produce outputs that are unfaithful to reality, also known as visual hallucinations (VH), which significantly impedes their real-world usage. To alleviate VH, various decoding strategies have been…

Speculative decoding is a technique to leverage hardware concurrency in order to enable multiple steps of token generation in a single forward pass, thus improving the efficiency of large-scale autoregressive (AR) Transformer models.…

The computational complexity of solving nonlinear support vector machine (SVM) is prohibitive on large-scale data. In particular, this issue becomes very sensitive when the data represents additional difficulties such as highly imbalanced…

LLM deployment on resource-constrained edge devices faces severe latency constraints, particularly in real-time applications where delayed responses can compromise safety or usability. Among many approaches to mitigate the inefficiencies of…

Inference with Multimodal Large Language Models (MLLMs) is slow due to their large-language-model backbone which suffers from memory bandwidth bottleneck and generates tokens auto-regressively. In this paper, we explore the application of…