Related papers: FlashSampling: Fast and Memory-Efficient Exact Sam…

The rapid advancements in artificial intelligence (AI), particularly the Large Language Models (LLMs), have profoundly affected our daily work and communication forms. However, it is still a challenge to deploy LLMs on resource-constrained…

Often, machine learning applications have to cope with dynamic environments where data are collected in the form of continuous data streams with potentially infinite length and transient behavior. Compared to traditional (batch) data…

Recent studies indicate that the denoising process in deep generative diffusion models implicitly learns and memorizes semantic information from the data distribution. These findings suggest that capturing more complex data distributions…

The deployment of large language models (LLMs) presents significant challenges due to their enormous memory footprints, low arithmetic intensity, and stringent latency requirements, particularly during the autoregressive decoding stage.…

Large-scale AI models, such as Large Language Models (LLMs) and Diffusion Models (DMs), have grown rapidly in size, creating significant challenges for efficient deployment on resource-constrained hardware. In this paper, we introduce…

We present a sparse linear system solver that is based on a multifrontal variant of Gaussian elimination, and exploits low-rank approximation of the resulting dense frontal matrices. We use hierarchically semiseparable (HSS) matrices, which…

This paper presents new parallel algorithms for generating Euclidean minimum spanning trees and spatial clustering hierarchies (known as HDBSCAN$^*$). Our approach is based on generating a well-separated pair decomposition followed by using…

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…

The proliferation of 100B+ parameter Large Language Models (LLMs) with 100k+ context length support have resulted in increasing demands for on-chip memory to support large KV caches. Techniques such as StreamingLLM and SnapKV demonstrate…

Speculative decoding is a standard method for accelerating the inference speed of large language models. However, scaling it for production environments poses several engineering challenges, including efficiently implementing different…

Recent years have witnessed the emergence of textual commonsense knowledge bases, aimed at providing more nuanced and context-rich knowledge. The integration of external commonsense into language models has been shown to be a key enabler in…

The optimization of submodular functions constitutes a viable way to perform clustering. Strong approximation guarantees and feasible optimization w.r.t. streaming data make this clustering approach favorable. Technically, submodular…

In this paper, we focus on exploring effective methods for faster and accurate semantic segmentation. A common practice to improve the performance is to attain high-resolution feature maps with strong semantic representation. Two strategies…

Diffusion-based talking head models generate high-quality, photorealistic videos but suffer from slow inference, limiting practical applications. Existing acceleration methods for general diffusion models fail to exploit the temporal and…

Graph neural network (GNN) potentials such as SchNet improve the accuracy and transferability of molecular dynamics (MD) simulation by learning many-body interactions, but remain slower than classical force fields due to fragmented kernels…

Event-based multimodal large language models (MLLMs) enable robust perception in high-speed and low-light scenarios, addressing key limitations of frame-based MLLMs. However, current event-based MLLMs often rely on dense image-like…

Embedding models in natural language processing (NLP) increasingly rely on deep architectures such as BERT, while simpler models such as Word2Vec provide efficient representations but limited interpretability. The Tsetlin Machine (TM)…

Novel methods are presented in this initial study for the fusion of GPU kernels in the artificial compressibility method (ACM), using tensor product elements with constant Jacobians and flux reconstruction. This is made possible through the…

There is extensive evidence that biological neural networks encode information in the precise timing of the spikes generated and transmitted by neurons, which offers several advantages over rate-based codes. Here we adopt a vector space…

Distribution Matching Distillation (DMD) provides an effective distribution-level correction for few-step generation, while relying on an auxiliary fake-score network to track the evolving generative distribution. Recent work combines…