相关论文: When RL Meets Adaptive Speculative Training: A Uni…

Inference accounts for the majority of latency and energy consumption in large language model (LLM) deployments, often exceeding 90% of total cost. While training-time efficiency has seen extensive progress, runtime optimization remains a…

This paper presents an expert-guided active-inference-inspired framework for adaptive UAV swarm trajectory planning. The proposed method converts multi-UAV trajectory design from a repeated combinatorial optimization problem into a…

Large language models (LLMs) often face a bottleneck in inference speed due to their reliance on auto-regressive decoding. Recently, parallel decoding has shown significant promise in enhancing inference efficiency. However, we have…

Federated learning (FL) was recently proposed to securely train models with data held over multiple locations (``clients'') under the coordination of a central server. Prolonged training times caused by slow clients may hinder the…

The discovery of reusable sub-routines simplifies decision-making and planning in complex reinforcement learning problems. Previous approaches propose to learn such temporal abstractions in a purely unsupervised fashion through observing…

The growing gap between the increasing complexity of large language models (LLMs) and the limited computational budgets of edge devices poses a key challenge for efficient on-device inference, despite gradual improvements in hardware…

Speculative decoding is an emerging technique that accelerates large language model (LLM) inference by allowing a smaller draft model to predict multiple tokens in advance, which are then verified or corrected by a larger target model. In…

Recent advances in AI weather forecasting have led to the emergence of so-called "foundation models", typically defined by expensive pretraining and minimal fine-tuning for downstream tasks. However, in the natural sciences, a desirable…

To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM inference. In each decoding step, this method first drafts…

Inference with Multimodal Large Language Models (MLLMs) is slow due to their large-language-model backbone which suffers from memory bandwidth bottleneck and generates tokens auto-regressively. In this paper, we explore the application of…

This paper develops an adaptive observation-based efficient reinforcement learning (RL) approach for systems with uncertain drift dynamics. A novel concurrent learning adaptive extended observer (CL-AEO) is first designed to jointly…

Vision-Language-Action models (VLAs) achieve remarkable performance in sequential decision-making but remain fragile to subtle environmental shifts, such as small changes in object pose. We attribute this brittleness to trajectory…

Deep learning (DL) based resource allocation (RA) has recently gained significant attention due to its performance efficiency. However, most related studies assume an ideal case where the number of users and their utility demands, e.g.,…

The reasoning large language model (RLLM) has been proven competitive in solving complex reasoning tasks such as mathematics, coding, compared to general LLM. However, the serving performance and behavior of RLLM remains unexplored, which…

Link adaptation (LA) is an essential function in modern wireless communication systems that dynamically adjusts the transmission rate of a communication link to match time- and frequency-varying radio link conditions. However, factors such…

Sequence learning has attracted much research attention from the machine learning community in recent years. In many applications, a sequence learning task is usually associated with multiple temporally correlated auxiliary tasks, which are…

Deep Q-learning jointly learns representations and values within monolithic networks, promising beneficial co-adaptation between features and value estimates. Although this architecture has attained substantial success, the coupling between…

Large Language Models (LLMs) have shown promise as educational tutors, yet effective tutoring requires more than solving problems: it must provide progressive Socratic guidance and balance multiple pedagogical objectives across multi-turn…

Speculative decoding has demonstrated its effectiveness in accelerating the inference of large language models while maintaining a consistent sampling distribution. However, the conventional approach of training a separate draft model to…

Reliable forecasts of the Earth system are crucial for human progress and safety from natural disasters. Artificial intelligence offers substantial potential to improve prediction accuracy and computational efficiency in this field, however…