Advanced Algorithms and Applications

Últimos artículos

• Sample-efficient LLM Optimization with Reset Replay

  Zichuan Liu, Jinyu Wang, Lei Song, Jiang Bian · 8 de mayo de 2026

  Recent advancements in LLM post-training, particularly through reinforcement learning and preference optimization, are key to boosting their reasoning capabilities. However, these methods often suffer from low sample efficiency and a susceptibility to primacy bias, a phenomenon where overfitting to …

• Neural Bandit Based Optimal LLM Selection for a Pipeline of Subtasks

  Baran Atalar, Eddie Zhang, Carlee Joe-Wong · 23 de abril de 2026

  As large language models (LLMs) become increasingly popular, there is a growing need to predict which out of a set of LLMs will yield a successful answer to a given query at low cost. This problem promises to become even more relevant as LLM agents are asked to solve an increasing variety of "agenti…

• Near-Optimal Online Deployment and Routing for Streaming LLMs

  Shaoang Li, Jian Li · 30 de enero de 2026

  The rapid pace at which new large language models (LLMs) appear, and older ones become obsolete, forces providers to manage a streaming inventory under a strict concurrency cap and per-query cost budgets. We cast this as an online decision problem that couples stage-wise deployment (at fixed mainten…

• Is On-Policy Data always the Best Choice for Direct Preference Optimization-based LM Alignment?

  Zetian Sun, Dongfang Li, Xuhui Chen, Baotian Hu, Min Zhang · 28 de enero de 2026

  The alignment of language models~(LMs) with human preferences is critical for building reliable AI systems. The problem is typically framed as optimizing an LM policy to maximize the expected reward that reflects human preferences. Recently, Direct Preference Optimization~(DPO) was proposed as a LM …

• Geometry Aware Meta-Learning Neural Network for Joint Phase and Precoder Optimization in RIS

  Dahlia Devapriya, Aparna V C, Sheetal Kalyani · 10 de diciembre de 2025

  In reconfigurable intelligent surface (RIS) aided systems, the joint optimization of the precoder matrix at the base station and the phase shifts of the RIS elements involves significant complexity. In this paper, we propose a complex-valued, geometry aware meta-learning neural network that maximize…

• SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving

  Andreas Kosmas Kakolyris, Dimosthenis Masouros, Petros Vavaroutsos, Sotirios Xydis, Dimitrios Soudris · 4 de diciembre de 2025

  As Large Language Models (LLMs) gain traction, their reliance on power-hungry GPUs places ever-increasing energy demands, raising environmental and monetary concerns. Inference dominates LLM workloads, presenting a critical challenge for providers: minimizing energy costs under Service-Level Objecti…

• Predictive Control and Regret Analysis of Non-Stationary MDP with Look-ahead Information

  Ziyi Zhang, Yorie Nakahira, Guannan Qu · 17 de noviembre de 2025

  Policy design in non-stationary Markov Decision Processes (MDPs) is inherently challenging due to the complexities introduced by time-varying system transition and reward, which make it difficult for learners to determine the optimal actions for maximizing cumulative future rewards. Fortunately, in …

• Test-Time Alignment of LLMs via Sampling-Based Optimal Control in pre-logit space

  Sekitoshi Kanai, Tsukasa Yoshida, Hiroshi Takahashi, Haru Kuroki, Kazumune Hashimoto · 31 de octubre de 2025

  Test-time alignment of large language models (LLMs) attracts attention because fine-tuning LLMs requires high computational costs. In this paper, we propose a new test-time alignment method called adaptive importance sampling on pre-logits (AISP) on the basis of the sampling-based model predictive c…

• Contrastive Conditional-Unconditional Alignment for Long-tailed Diffusion Model

  Fang Chen, Alex Villa, Gongbo Liang, Xiaoyi Lu, Meng Tang · 28 de octubre de 2025

  Training data for class-conditional image synthesis often exhibit a long-tailed distribution with limited images for tail classes. Such an imbalance causes mode collapse and reduces the diversity of synthesized images for tail classes. For class-conditional diffusion models trained on imbalanced dat…

• Offline Preference Optimization via Maximum Marginal Likelihood Estimation

  Saeed Najafi, Alona Fyshe · 28 de octubre de 2025

  Aligning Large Language Models (LLMs) with human preferences is crucial, but standard methods like Reinforcement Learning from Human Feedback (RLHF) are often complex and unstable. In this work, we propose a new, simpler approach that recasts alignment through the lens of Maximum Marginal Likelihood…