Related papers: LiLM-RDB-SFC: Lightweight Language Model with Rela…

Large Language Model (LLM) serving systems remain fundamentally fragile, where frequent hardware faults in hyperscale clusters trigger disproportionate service outages in the software stack. Current recovery mechanisms are prohibitively…

Reinforcement learning (RL) has emerged as the de-facto paradigm for improving the reasoning capabilities of large language models (LLMs). We have developed RLAX, a scalable RL framework on TPUs. RLAX employs a parameter-server…

Reinforcement learning (RL) has become the pivotal post-training technique for large language model (LLM). Effectively scaling reinforcement learning is now the key to unlocking advanced reasoning capabilities and ensuring safe,…

Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments, a critical step toward generalized AI. However, the standard supervised fine-tuning (SFT) approach, which relies on large-scale…

Deep Reinforcement Learning (RL) is remarkably effective in addressing sequential resource allocation problems in domains such as healthcare, public policy, and resource management. However, deep RL policies often lack transparency and…

While internet-scale image and textual data have enabled strong generalization in Vision-Language Models (VLMs), the absence of internet-scale control data has impeded the development of similar generalization in standard reinforcement…

The integration of Large Language Models (LLMs) into autonomous driving systems demonstrates strong common sense and reasoning abilities, effectively addressing the pitfalls of purely data-driven methods. Current LLM-based agents require…

Recent DiT-based text-to-image models increasingly adopt LLMs as text encoders, yet text conditioning remains largely static and often utilizes only a single LLM layer, despite pronounced semantic hierarchy across LLM layers and…

Network Function Virtualization (NFV) and Software Defined Networking (SDN) are technologies that recently acquired a great momentum thanks to their promise of being a flexible and cost-effective solution for replacing hardware-based,…

Modern wireless networks must adapt to dynamic conditions while efficiently managing diverse service demands. Traditional deep reinforcement learning (DRL) struggles in these environments, as scattered and evolving feedback makes optimal…

We aim to improve the reasoning capabilities of diffusion language models (DLMs). While SFT is a popular post-training recipe for autoregressive models, its use in DLMs faces challenges and can even hurt performance, though the underlying…

Large language models (LLMs) are increasingly deployed in decision-making tasks, where not only accuracy but also reliable confidence estimates are essential. Well-calibrated confidence enables downstream systems to decide when to trust a…

As a key medium for human interaction and information exchange, social networking services (SNS) pose unique challenges for large language models (LLMs): heterogeneous workloads, fast-shifting norms and slang, and multilingual, culturally…

Supervised Fine-Tuning (SFT) of the language backbone plays a pivotal role in adapting Vision-Language Models (VLMs) to specialized domains such as medical reasoning. However, existing SFT practices often rely on unfiltered textual datasets…

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…

Network slicing enables multiple virtual networks to be instantiated and customized to meet heterogeneous use case requirements over 5G and beyond network deployments. However, most of the solutions available today face scalability issues…

The deployment of intelligent reinforcement learning (RL) agents on resource-constrained edge devices remains a fundamental challenge due to the substantial memory, computational, and energy requirements of modern deep learning systems.…

Although Deep Reinforcement Learning (DRL) and Large Language Models (LLMs) each show promise in addressing decision-making challenges in autonomous driving, DRL often suffers from high sample complexity, while LLMs have difficulty ensuring…

Text generation with Large Language Models (LLMs) is known to be memory bound due to the combination of their auto-regressive nature, huge parameter counts, and limited memory bandwidths, often resulting in low token rates. Speculative…

Federated Learning (FL) offers a promising approach for collaborative machine learning across distributed devices. However, its adoption is hindered by the complexity of building reliable communication architectures and the need for…