相关论文: OASIS: Online Activation Subspace Learning for Mem…

Pipeline parallelism (PP) is widely used for training large language models (LLMs), yet its scalability is often constrained by high activation memory consumption as the number of in-flight microbatches grows with the degree of PP. In this…

The promise of learning to learn for robotics rests on the hope that by extracting some information about the learning process itself we can speed up subsequent similar learning tasks. Here, we introduce a computationally efficient online…

In recent years, researchers have increasingly been interested in how to enable Multimodal Large Language Models (MLLM) to possess spatial understanding and reasoning capabilities. However, most existing methods overlook the importance of…

The goal of offline reinforcement learning is to learn a policy from a fixed dataset, without further interactions with the environment. This setting will be an increasingly more important paradigm for real-world applications of…

Artificial intelligence (AI) models are currently driven by a significant upscaling of their complexity, with massive matrix-multiplication workloads representing the major computational bottleneck. In-memory computing (IMC) architectures…

Deep learning is experiencing a rise in large-scale models. Training large-scale models is costly, prompting researchers to train large-scale models on commodity servers that more researchers can access. The massive number of parameters…

The remarkable success of Large Language Models (LLMs) relies heavily on their substantial scale, which poses significant challenges during model deployment in terms of latency and memory consumption. Recently, numerous studies have…

Agentic search enables language models to solve knowledge-intensive tasks by adaptively acquiring external evidence over multiple steps. Reinforcement learning with verifiable rewards (RLVR) has emerged as a widely adopted training paradigm…

Large Language Models (LLMs) inevitably memorize sensitive information during training, posing significant privacy risks. Machine unlearning has emerged as a promising solution to selectively remove such information without full retraining.…

Huge neural network models have shown unprecedented performance in real-world applications. However, due to memory constraints, model parallelism must be utilized to host large models that would otherwise not fit into the memory of a single…

Large language models (LLMs) have shown impressive capabilities across various tasks. However, training LLMs from scratch requires significant computational power and extensive memory capacity. Recent studies have explored low-rank…

Given an object mask, Semi-supervised Video Object Segmentation (SVOS) technique aims to track and segment the object across video frames, serving as a fundamental task in computer vision. Although recent memory-based methods demonstrate…

The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and…

Deployment of Large Language Models (LLMs) has major computational costs, due to their rapidly expanding size. Compression of LLMs reduces the memory footprint, latency, and energy required for their inference. Post-training Quantization…

Extreme activation outliers in Large Language Models (LLMs) critically degrade quantization performance, hindering efficient on-device deployment. While channel-wise operations and adaptive gradient scaling are recognized causes, practical…

With the increase in the number of parameters in large language models, the process of pre-training and fine-tuning increasingly demands larger volumes of GPU memory. A significant portion of this memory is typically consumed by the…

Many complex real-world tasks are composed of several levels of sub-tasks. Humans leverage these hierarchical structures to accelerate the learning process and achieve better generalization. In this work, we study the inductive bias and…

Large language models have achieved remarkable success, but their extensive parameter size necessitates substantial memory for training, thereby setting a high threshold. While the recently proposed low-memory optimization (LOMO) reduces…

Reinforcement learning algorithms typically utilize an interactive simulator (i.e., environment) with a predefined reward function for policy training. Developing such simulators and manually defining reward functions, however, is often…

The state of an object reflects its current status or condition and is important for a robot's task planning and manipulation. However, detecting an object's state and generating a state-sensitive plan for robots is challenging. Recently,…