Related papers: CoMERA: Computing- and Memory-Efficient Training v…

In the rapidly evolving field of artificial intelligence, multimodal models, e.g., integrating vision and language into visual-language models (VLMs), have become pivotal for many applications, ranging from image captioning to multimodal…

Fine-tuning large language models (LLMs) has achieved remarkable performance across various natural language processing tasks, yet it demands more and more memory as model sizes keep growing. To address this issue, the recently proposed…

The prohibitive sizes of Large Language Models (LLMs) today make it difficult to deploy them on memory-constrained edge devices. This work introduces $\rm CALDERA$ -- a new post-training LLM compression algorithm that harnesses the inherent…

Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL). But conventional approaches rely on outcome-only rewards that provide sparse feedback, resulting in…

Large language models (LLMs) have revolutionized natural language understanding and generation but face significant memory bottlenecks during training. GaLore, Gradient Low-Rank Projection, addresses this issue by leveraging the inherent…

Many real-world applications collect data in a streaming environment, where learning tasks are encountered sequentially. This necessitates continual learning (CL) to update models online, enabling adaptation to new tasks while preserving…

Training Large Language Models (LLMs) is memory-intensive due to the large number of parameters and associated optimization states. GaLore, a recent method, reduces memory usage by projecting weight gradients into a low-rank subspace…

Deep learning (DL) compilers rely on cost models and auto-tuning to optimize tensor programs for target hardware. However, existing approaches depend on large offline datasets, incurring high collection costs and offering suboptimal…

Self-supervised representation learning for point cloud has demonstrated effectiveness in improving pre-trained model performance across diverse tasks. However, as pre-trained models grow in complexity, fully fine-tuning them for downstream…

Applying a pre-trained large model to downstream tasks is prohibitive under resource-constrained conditions. Recent dominant approaches for addressing efficiency issues involve adding a few learnable parameters to the fixed backbone model.…

The increasing prevalence of large language models (LLMs) such as GPT-4 in various applications has led to a surge in the size of prompts required for optimal performance, leading to challenges in computational efficiency. Prompt…

With the decline of Moore's law, optimizing program performance has become a major focus of software research. However, high-level optimizations such as API and algorithm changes remain elusive due to the difficulty of understanding the…

Large Language Models (LLMs) have garnered widespread attention due to their remarkable performance across various tasks. However, to mitigate the issue of hallucinations, LLMs often incorporate retrieval-augmented pipeline to provide them…

The demand for efficient machine learning (ML) accelerators is growing rapidly, driving the development of novel computing concepts such as resistive random access memory (RRAM)-based tiled computing-in-memory (CIM) architectures. CIM…

In recent years, the size of pre-trained language models (PLMs) has grown by leaps and bounds. However, efficiency issues of these large-scale PLMs limit their utilization in real-world scenarios. We present a suite of cost-effective…

Large Reasoning Models (LRMs) demonstrate exceptional capability in tackling complex mathematical, logical, and coding tasks by leveraging extended Chain-of-Thought (CoT) reasoning. Test-time scaling methods, such as prolonging CoT with…

Federated learning systems have been identified as an efficient approach to scaling distributed model training with a large amount of participants or data owners while guaranteeing data privacy. To apply the current most popular pre-trained…

Optimal hyperparameter selection is critical for maximizing the performance of neural networks in computer vision, particularly as architectures become more complex. This work explores the use of large language models (LLMs) for…

Low-rank adaptation (LoRA) reduces the computational and memory demands of fine-tuning large language models (LLMs) by approximating updates with low-rank matrices. However, low-rank approximation in two-dimensional space fails to capture…

Tensor decomposition is a mathematically supported technique for data compression. It consists of applying some kind of a Low Rank Decomposition technique on the tensors or matrices in order to reduce the redundancy of the data. However, it…