Related papers: L$^3$: Large Lookup Layers

Large language models (LLMs) call for extension of context to handle many critical applications. However, the existing approaches are prone to expensive costs and inferior quality of context extension. In this work, we proposeExtensible…

We present MoE-MLA-RoPE, a novel architecture combination that combines Mixture of Experts (MoE) with Multi-head Latent Attention (MLA) and Rotary Position Embeddings (RoPE) for efficient language modeling. Our approach addresses the…

Knowledge editing (KE) enables precise modifications to factual content in large language models (LLMs). Existing KE methods are largely designed for dense architectures, limiting their applicability to the increasingly prevalent sparse…

Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoencoders (SAEs) offer a promising solution by decomposing activations into interpretable…

The interpretability of Mixture-of-Experts (MoE) models, especially those with heterogeneous designs, remains underexplored. Existing attribution methods for dense models fail to capture dynamic routing-expert interactions in sparse MoE…

Multimodal Large Language Models (MLLMs) have demonstrated outstanding performance across a variety of domains. However, training MLLMs is often inefficient, as much of the computation is redundant due to the long input sequences from…

Mixture of Experts (MoE) LLMs have recently gained attention for their ability to enhance performance by selectively engaging specialized subnetworks or "experts" for each input. However, deploying MoEs on memory-constrained devices remains…

Mixture-of-Experts (MoE) architectures enable conditional computation by routing inputs to multiple expert subnetworks and are often motivated as a mechanism for scaling large language models. In this project, we instead study MoE behavior…

Transformer-based large language models (LLMs) are comprised of billions of parameters arranged in deep and wide computational graphs. Several studies on LLM efficiency optimization argue that it is possible to prune a significant portion…

Recent advances in large language models highlighted the excessive quadratic cost of self-attention. Despite the significant research efforts, subquadratic attention methods still suffer from inferior performance in practice. We hypothesize…

Sparse Mixture-of-Experts (MoE) architectures have emerged as a promising approach to decoupling model capacity from computational cost. At the core of the MoE model is the router, which learns the underlying clustering structure of the…

Large language models (LLMs) are in need of sufficient contexts to handle many critical applications, such as retrieval augmented generation and few-shot learning. However, due to the constrained window size, the LLMs can only access to the…

Expert parallelism is vital for effectively training Mixture-of-Experts (MoE) models, enabling different devices to host distinct experts, with each device processing different input data. However, during expert parallel training, dynamic…

In this paper, we address the challenge of determining the layer-wise sparsity rates of large language models (LLMs) through a theoretical perspective. Specifically, we identify a critical issue of ''$\textbf{reconstruction error…

Mixture-of-Experts (MoE) models can achieve promising results with outrageous large amount of parameters but constant computation cost, and thus it has become a trend in model scaling. Still it is a mystery how MoE layers bring quality…

All-MLP architectures have attracted increasing interest as an alternative to attention-based models. In NLP, recent work like gMLP shows that all-MLPs can match Transformers in language modeling, but still lag behind in downstream tasks.…

Large Language Models (LLMs) have achieved remarkable results. However, existing models are expensive to train and deploy, and it is also difficult to expand their knowledge beyond pre-training data without forgetting previous knowledge.…

Despite their remarkable natural language understanding capabilities, Large Language Models (LLMs) have been underutilized for retrieval tasks. We present Search-R3, a novel framework that addresses this limitation by adapting LLMs to…

Large language models (LLMs) encounter significant adaptation challenges in diverse multitask finetuning. Mixture-of-experts (MoE) provides a promising solution with a dynamic architecture, enabling effective task decoupling. However,…

Larger networks generally have greater representational power at the cost of increased computational complexity. Sparsifying such networks has been an active area of research but has been generally limited to static regularization or…