Related papers: SpecMamba: Accelerating Mamba Inference on FPGA wi…

Multi-task dense scene understanding, which trains a model for multiple dense prediction tasks, has a wide range of application scenarios. Capturing long-range dependency and enhancing cross-task interactions are crucial to multi-task dense…

In this work, we take the first exploration of the recently popular foundation model, i.e., State Space Model/Mamba, in image quality assessment (IQA), aiming at observing and excavating the perception potential in vision Mamba. A series of…

Nuclei panoptic segmentation supports cancer diagnostics by integrating both semantic and instance segmentation of different cell types to analyze overall tissue structure and individual nuclei in histopathology images. Major challenges…

Speculative decoding has rapidly emerged as a leading approach for accelerating language model (LM) inference, as it offers substantial speedups while yielding identical outputs. This relies upon a small draft model, tasked with predicting…

Speculative decoding has proven to be an efficient solution to large language model (LLM) inference, where the small drafter predicts future tokens at a low cost, and the target model is leveraged to verify them in parallel. However, most…

Speculative decoding accelerates memory-bound LLM inference without quality degradation by using a fast drafter to propose multiple candidate tokens and the target model to verify them in parallel. However, conventional sequential…

In recent years, Transformers have become the de-facto architecture for sequence modeling on text and a variety of multi-dimensional data, such as images and video. However, the use of self-attention layers in a Transformer incurs…

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…

Group relative policy optimization (GRPO) has demonstrated significant potential in improving the reasoning capabilities of large language models (LLMs) via reinforcement learning. However, its practical deployment is impeded by an…

Speculative generation has emerged as a promising technique to accelerate inference in large language models (LLMs) by leveraging parallelism to verify multiple draft tokens simultaneously. However, the fundamental limits on the achievable…

Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a fast draft model to predict upcoming tokens from a slower target model, and then verifying…

Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement…

This paper introduces Multimodal Speculative Decoding (MSD) to accelerate Multimodal Large Language Models (MLLMs) inference. Speculative decoding has been shown to accelerate Large Language Models (LLMs) without sacrificing accuracy.…

State-space models like Mamba offer linear-time sequence processing and low memory, making them attractive for medical imaging. However, their robustness under realistic software and hardware threat models remains underexplored. This paper…

Multi-modal MRI offers valuable complementary information for diagnosis and treatment; however, its utility is limited by prolonged scanning times. To accelerate the acquisition process, a practical approach is to reconstruct images of the…

LLM serving platforms are increasingly deployed as multi-model cloud systems, where user demand is often long-tailed: a few popular large models receive most requests, while many smaller tail models remain underutilized. We propose…

The emergence of long-context large language models (LLMs) offers a promising alternative to traditional retrieval-augmented generation (RAG) for processing extensive documents. However, the computational overhead of long-context inference…

Transformer-based methods have achieved remarkable performance in event-based object detection, owing to the global modeling ability. However, they neglect the influence of non-event and noisy regions and process them uniformly, leading to…

Snapshot Compressive Imaging (SCI) enables fast spectral imaging but requires effective decoding algorithms for hyperspectral image (HSI) reconstruction from compressed measurements. Current CNN-based methods are limited in modeling…

Speculative decoding, which combines a draft model with a target model, has emerged as an effective approach to accelerate large language model (LLM) inference. However, existing methods often face a trade-off between the acceptance rate…