Related papers: TIDE: Efficient and Lossless MoE Diffusion LLM Inf…

In 5G smart cities, edge computing is employed to provide nearby computing services for end devices, and the large-scale models (e.g., GPT and LLaMA) can be deployed at the network edge to boost the service quality. However, due to the…

Diffusion language models promise parallel generation, yet still lag behind autoregressive (AR) models in quality. We stem this gap to a failure of introspective consistency: AR models agree with their own generations, while DLMs often do…

Large Language Models (LLMs) have demonstrated impressive performance across various tasks, and their application in edge scenarios has attracted significant attention. However, sparse-activated Mixture-of-Experts (MoE) models, which are…

In recent years, large language models (LLMs) have witnessed remarkable advancements, with the test-time scaling law consistently enhancing the reasoning capabilities. Through systematic evaluation and exploration of a diverse spectrum of…

The emergence of Mixture-of-Experts (MoE) has transformed the scaling of large language models by enabling vast model capacity through sparse activation. Yet, converting these performance gains into practical edge deployment remains…

Diffusion Policies have become widely used in Imitation Learning, offering several appealing properties, such as generating multimodal and discontinuous behavior. As models are becoming larger to capture more complex capabilities, their…

Efficiently deploying large language models (LLMs) in real-world scenarios remains a critical challenge, primarily due to hardware heterogeneity, inference framework limitations, and workload complexities.Efficiently deploying large…

Recently, Mixture-of-Experts (MoE) models have gained attention for efficiently scaling large language models. Although these models are extremely large, their sparse activation enables inference to be performed by accessing only a fraction…

Deploying Large Language Models (LLMs) on edge devices remains challenging due to their quadratically increasing computations with the sequence length. Existing studies for dynamic attention pruning are designed for hardware with massively…

The promising applications of large language models are often limited by the constrained GPU memory capacity available on edge devices. Mixture-of-Experts (MoE) models help address this issue by activating only a subset of the model's…

Mixture-of-Experts (MoE) architectures are widely used in modern large language models and multimodal models. However, inference efficiency is often limited by highly dynamic and skewed expert workloads across different modalities. During…

Diffusion language models (DLMs) enable parallel, non-autoregressive text generation, yet existing DLM mixture-of-experts (MoE) models inherit token-choice (TC) routing from autoregressive systems, leading to load imbalance and rigid…

The Text-to-Video (T2V) model aims to generate dynamic and expressive videos from textual prompts. The generation pipeline typically involves multiple modules, such as language encoder, Diffusion Transformer (DiT), and Variational…

Mixture-of-Experts (MoE) models improve the scalability of large language models (LLMs) by activating only a small subset of relevant experts per input. However, the sheer number of expert networks in an MoE model introduces a significant…

Multimodal large language models (MLLMs) have achieved impressive performance, but high-resolution visual inputs result in long sequences of visual tokens and substantial inference latency. Reducing redundant visual tokens is critical to…

Large language models (LLMs) are typically trained on fixed snapshots of the web, which means that their knowledge becomes stale and their predictions risk temporal leakage: relying on information that lies in the future relative to a…

Large language models run every token through every layer, regardless of difficulty. We present TIDE, a post-training system that attaches tiny learned routers at periodic checkpoint layers and, at inference time, selects the earliest layer…

Diffusion-based LLMs (dLLMs) fundamentally depart from traditional autoregressive (AR) LLM inference: they leverage bidirectional attention, block-wise KV cache refreshing, cross-step reuse, and a non-GEMM-centric sampling phase. These…

We introduce LLaDA-MoE, a large language diffusion model with the Mixture-of-Experts (MoE) architecture, trained from scratch on approximately 20T tokens. LLaDA-MoE achieves competitive performance with significantly reduced computational…

Large Language Models (LLMs) with the Mixture-of-Experts (MoE) architectures have shown promising performance on various tasks. However, due to the huge model sizes, running them in resource-constrained environments where the GPU memory is…