相关论文: A3 : an Analytical Low-Rank Approximation Framewor…

Large Language Models (LLMs) have reshaped the landscape of artificial intelligence by demonstrating exceptional performance across various tasks. However, substantial computational requirements make their deployment challenging on devices…

Parameter-efficient finetuning (PEFT) aims to mitigate the substantial computational and memory overhead involved in adapting large-scale pretrained models to diverse downstream tasks. Among numerous PEFT strategies, Low-Rank Adaptation…

In this work, we propose an extreme compression technique for Large Multimodal Models (LMMs). While previous studies have explored quantization as an efficient post-training compression method for Large Language Models (LLMs), low-bit…

The efficient implementation of large language models (LLMs) is crucial for deployment on resource-constrained devices. Low-rank tensor compression techniques, such as tensor-train (TT) networks, have been widely studied for…

While post-training compression techniques effectively reduce the memory footprint, latency, and power consumption of Large Language Models (LLMs), they often result in noticeable accuracy degradation and remain limited by hardware and…

Pre-trained language models (PLMs) demonstrate remarkable intelligence but struggle with emerging tasks unseen during training in real-world applications. Training separate models for each new task is usually impractical. Multi-task…

Large Language Models (LLMs) have demonstrated remarkable proficiency in language comprehension and generation; however, their widespread adoption is constrained by substantial bandwidth and computational demands. While pruning and low-rank…

Decomposing weight matrices into quantization and low-rank components ($\mathbf{W} \approx \mathbf{Q} + \mathbf{L}\mathbf{R}$) is a widely used technique for compressing large language models (LLMs). Existing joint optimization methods…

Modern Large Language Models (LLMs) are increasingly trained to support very large context windows. We present Compactor, a training-free, query-agnostic KV compression strategy that uses approximate leverage scores to determine token…

Transformer models have achieved remarkable results in various natural language tasks, but they are often prohibitively large, requiring massive memories and computational resources. To reduce the size and complexity of these models, we…

Improving the efficiency of inference in Large Language Models (LLMs) is a critical area of research. Post-training Quantization (PTQ) is a popular technique, but it often faces challenges at low-bit levels, particularly in downstream…

Pre-training large language models is dominated by the memory cost of storing full-rank weights, gradients, and optimizer states. Low-rank pre-training has emerged to address this, and the space of methods has grown rapidly. A central…

Retrieval-Augmented Generation (RAG) effectively enhances Large Language Models (LLMs) by incorporating retrieved external knowledge into the generation process. Reasoning models improve LLM performance in multi-hop QA tasks, which require…

Large language models (LLMs) excel at language understanding and generation, but their enormous computational and memory requirements hinder deployment. Compression offers a potential solution to mitigate these constraints. However, most…

Traditional post-training quantization (PTQ) is considered an effective approach to reduce model size and accelerate inference of large-scale language models (LLMs). However, existing low-rank PTQ methods require costly fine-tuning to…

The advent of pre-trained large language models (LLMs) has revolutionized various natural language processing tasks. These models predominantly employ an auto-regressive decoding mechanism that utilizes Key-Value (KV) caches to eliminate…

This paper investigates the under-explored area of low-rank weight training for large-scale Conformer-based speech recognition models from scratch. Our study demonstrates the viability of this training paradigm for such models, yielding…

Attention mechanisms underpin the success of large language models (LLMs), yet their substantial computational and memory overhead poses challenges for optimizing efficiency and performance. A critical bottleneck arises as KV cache and…

Large Language Models (LLMs) are increasingly deployed in scenarios demanding ultra-long context reasoning, such as agentic workflows and deep research understanding. However, long-context inference is constrained by the KV cache, a…

Large language models (LLMs) achieve strong performance across diverse domains but remain difficult to deploy in resource-constrained environments due to their size. Low-rank compression is a common remedy, typically minimizing weight…