English
Related papers

Related papers: Transfer Q Star: Principled Decoding for LLM Align…

200 papers

Post-training of large language models routinely interleaves supervised fine-tuning (SFT) with reinforcement learning (RL). These two methods have different objectives: SFT minimizes the cross-entropy loss between model outputs and expert…

Machine Learning · Computer Science 2026-05-07 Xueyan Niu , Bo Bai , Wei Han , Weixi Zhang

Text-to-image generation models have achieved remarkable progress in preference optimization, yet achieving robust alignment across diverse reward models remains a significant challenge. Existing multi-reward fusion approaches rely on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Ying Ba , Tianyu Zhang , Mohan Zhou , Yalong Bai , Wenyi Mo , Guiwei Zhang , Bing Su , Ji-Rong Wen

The surface code is a promising platform for a quantum memory, but its threshold under coherent errors remains incompletely understood. We study maximum-likelihood decoding of the square-lattice surface code in the presence of single-qubit…

Statistical Mechanics · Physics 2026-05-05 Stephen W. Yan , Yimu Bao , Sagar Vijay

Large language models (LLMs) demonstrate impressive performance but lack the flexibility to adapt to human preferences quickly without retraining. In this work, we introduce Test-time Preference Optimization (TPO), a framework that aligns…

Computation and Language · Computer Science 2025-01-23 Yafu Li , Xuyang Hu , Xiaoye Qu , Linjie Li , Yu Cheng

Often, constraints arise in deployment settings where even lightweight parameter updates e.g. parameter-efficient fine-tuning could induce model shift or tuning instability. We study test-time adaptation of foundation models for few-shot…

Machine Learning · Statistics 2026-02-04 Tahir Qasim Syed , Behraj Khan

This paper investigates the so-called reward-balancing methods, a novel class of algorithms for solving discounted-return reinforcement learning (RL) problems. These methods consist of iteratively adjusting the reward function to transform…

Optimization and Control · Mathematics 2026-04-23 Simone Baroncini , Bahman Gharesifard , Giuseppe Notarstefano

This article explores the adaptive relationship between Encoder Layers and Decoder Layers using the SOTA model Helsinki-NLP/opus-mt-de-en, which translates German to English. The specific method involves introducing a bias-free fully…

Computation and Language · Computer Science 2024-05-15 Yubo Song

Mechanistic interpretability has made it possible to localize circuits underlying specific behaviors in language models, but existing methods are expensive, model-specific, and difficult to scale to larger architectures. We introduce…

Computation and Language · Computer Science 2026-04-28 Shun Shao , Binxu Wang , Shay B. Cohen , Anna Korhonen , Yonatan Belinkov

Fine-tuning is a crucial process for adapting large language models (LLMs) to diverse applications. In certain scenarios, such as multi-tenant serving, deploying multiple LLMs becomes necessary to meet complex demands. Recent studies…

Computation and Language · Computer Science 2024-11-27 Bowen Ping , Shuo Wang , Hanqing Wang , Xu Han , Yuzhuang Xu , Yukun Yan , Yun Chen , Baobao Chang , Zhiyuan Liu , Maosong Sun

Large language models (LLMs) have recently demonstrated promising performance in simultaneous machine translation (SimulMT). However, applying decoder-only LLMs to SimulMT introduces a positional mismatch, which leads to a dilemma between…

Computation and Language · Computer Science 2026-03-31 Yuzhe Shang , Pengzhi Gao , Yazheng Yang , Jiayao Ma , Wei Liu , Jian Luan , Jinsong Su

We address the challenge of multi-target quantum optimization, where the objective is to simultaneously optimize multiple cost functions defined over the same quantum search space. To accelerate optimization and reduce quantum resource…

Quantum Physics · Physics 2025-09-30 Vu Tuan Hai , Bui Cao Doanh , Le Vu Trung Duong , Pham Hoai Luan , Yasuhiko Nakashima

While large language models demonstrate remarkable capabilities at task-specific applications through fine-tuning, extending these benefits across diverse languages is essential for broad accessibility. However, effective cross-lingual…

Computation and Language · Computer Science 2025-06-03 Danni Liu , Jan Niehues

Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We frame natural language inference as a search problem where the final answer is the valid…

Artificial Intelligence · Computer Science 2026-05-26 Andreas Opedal , Francesco Ignazio Re , Abulhair Saparov , Mrinmaya Sachan , Bernhard Schölkopf , Ryan Cotterell

KL-regularized reinforcement learning (RL) is a popular alignment framework to control the language model responses towards high reward outcomes. We pose a tokenwise RL objective and propose a modular solver for it, called controlled…

Existing transfer learning-based beam prediction approaches primarily rely on simple fine-tuning. When there is a significant difference in data distribution between the target domain and the source domain, simple fine-tuning limits the…

Information Theory · Computer Science 2025-09-26 Zhiqiang Xiao , Yuwen Cao , Mondher Bouazizi , Tomoaki Ohtsuki , Shahid Mumtaz

Existing methods to enhance the reasoning capability of large language models predominantly rely on supervised fine-tuning (SFT) followed by reinforcement learning (RL) on reasoning-specific data. These approaches critically depend on…

Machine Learning · Computer Science 2025-05-20 Qingyang Zhang , Haitao Wu , Changqing Zhang , Peilin Zhao , Yatao Bian

Quantum teleportation is a foundational protocol for sending quantum information through entanglement distribution and classical communication. Assuming ideal classical communication, the reliability of quantum teleportation is limited by…

Inference-time optimization scales computation to derive deliberate reasoning steps for effective performance. While previous search-based strategies address the short-sightedness of auto-regressive generation, the vast search space leads…

Machine Learning · Computer Science 2025-03-18 Fangzhi Xu , Hang Yan , Chang Ma , Haiteng Zhao , Jun Liu , Qika Lin , Zhiyong Wu

Insufficient modeling of human preferences within the reward model is a major obstacle for leveraging human feedback to improve translation quality. Fortunately, quality estimation (QE), which predicts the quality of a given translation…

Computation and Language · Computer Science 2024-03-19 Zhiwei He , Xing Wang , Wenxiang Jiao , Zhuosheng Zhang , Rui Wang , Shuming Shi , Zhaopeng Tu

Low-Rank Adaptation (LoRA) lowers the computational and memory overhead of fine-tuning large models by updating a low-dimensional subspace of the pre-trained weight matrix. Albeit efficient, LoRA exhibits suboptimal convergence and…

Machine Learning · Computer Science 2026-02-25 Yilang Zhang , Bingcong Li , Georgios B. Giannakis
‹ Prev 1 8 9 10 Next ›