Related papers: Alchemist: Towards the Design of Efficient Online …

Transformer-based large language models (LLMs) have demonstrated exceptional capabilities in sequence modeling and text generation, with improvements scaling proportionally with model size. However, the limitations of GPU memory have…

Online continual learning (CL) aims to learn new knowledge and consolidate previously learned knowledge from non-stationary data streams. Due to the time-varying training setting, the model learned from a changing distribution easily…

Pre-trained language models (e.g., BERT (Devlin et al., 2018) and its variants) have achieved remarkable success in varieties of NLP tasks. However, these models usually consist of hundreds of millions of parameters which brings challenges…

Multi-agent applications often execute complex tasks as multi-stage workflows, where each stage is an LLM call whose output becomes part of context for subsequent steps. Existing LLM serving systems largely assume homogeneous clusters with…

We propose an online 3D semantic segmentation method that incrementally reconstructs a 3D semantic map from a stream of RGB-D frames. Unlike offline methods, ours is directly applicable to scenarios with real-time constraints, such as…

Large language model (LLM) applications are evolving beyond simple chatbots into dynamic, general-purpose agentic programs, which scale LLM calls and output tokens to help AI agents reason, explore, and solve complex tasks. However,…

The success of Large Language Models (LLMs) has significantly propelled the research of video understanding. To harvest the benefits of well-trained expert models (i.e., tools), video LLMs prioritize the exploration of tool usage…

Continual learning in online scenario aims to learn a sequence of new tasks from data stream using each data only once for training, which is more realistic than in offline mode assuming data from new task are all available. However, this…

According to the Complementary Learning Systems (CLS) theory~\cite{mcclelland1995there} in neuroscience, humans do effective \emph{continual learning} through two complementary systems: a fast learning system centered on the hippocampus for…

Continual Reinforcement Learning (CRL) aims to develop lifelong learning agents to continuously acquire knowledge across diverse tasks while mitigating catastrophic forgetting. This requires efficiently managing the stability-plasticity…

Simultaneous translation (ST) starts translations synchronously while reading source sentences, and is used in many online scenarios. The previous wait-k policy is concise and achieved good results in ST. However, wait-k policy faces two…

We study the problem of optimizing Large Language Model (LLM) inference scheduling to minimize total latency. LLM inference is an online and multi-task service process and also heavily energy consuming by which a pre-trained LLM processes…

The Transformer architecture has significantly advanced natural language processing (NLP) and has been foundational in developing large language models (LLMs) such as LLaMA and OPT, which have come to dominate a broad range of NLP tasks.…

Hard optimisation problems such as Boolean Satisfiability typically have long solving times and can usually be solved by many algorithms, although the performance can vary widely in practice. Research has shown that no single algorithm…

Quick interaction between a human teacher and a learning machine presents numerous benefits and challenges when working with web-scale data. The human teacher guides the machine towards accomplishing the task of interest. The learning…

By learning a sequence of tasks continually, an agent in continual learning (CL) can improve the learning performance of both a new task and `old' tasks by leveraging the forward knowledge transfer and the backward knowledge transfer,…

Despite rapid advances in continual learning, a large body of research is devoted to improving performance in the existing setups. While a handful of work do propose new continual learning setups, they still lack practicality in certain…

The efficiency of large language models (LLMs) remains a critical challenge, particularly in contexts where computational resources are limited. Traditional attention mechanisms in these models, while powerful, require significant…

Large Language Models (LLMs) have shown remarkable performance on complex reasoning tasks, especially when equipped with long chain-of-thought (CoT) reasoning. However, eliciting long CoT typically requires large-scale reinforcement…

We propose a novel framework and a solution to tackle the continual learning (CL) problem with changing network architectures. Most CL methods focus on adapting a single architecture to a new task/class by modifying its weights. However,…