English
Related papers

Related papers: Efficient Tail-Aware Generative Optimization via F…

200 papers

A fairly reliable trend in deep reinforcement learning is that the performance scales with the number of parameters, provided a complimentary scaling in amount of training data. As the appetite for large models increases, it is imperative…

Machine Learning · Computer Science 2023-06-14 Bogdan Mazoure , Walter Talbott , Miguel Angel Bautista , Devon Hjelm , Alexander Toshev , Josh Susskind

We propose Flow-Anchored Noise-conditioned Q-Learning (FAN), a highly efficient and high-performing offline reinforcement learning (RL) algorithm. Recent work has shown that expressive flow policies and distributional critics improve…

Machine Learning · Computer Science 2026-05-29 Sungyoung Lee , Dohyeong Kim , Eshan Balachandar , Zelal Su Mustafaoglu , Keshav Pingali

Large pre-trained models achieve remarkable performance in vision tasks but are impractical for fine-tuning due to high computational and storage costs. Parameter-Efficient Fine-Tuning (PEFT) methods mitigate this issue by updating only a…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Siqi Luo , Haoran Yang , Yi Xin , Mingyang Yi , Guangyang Wu , Guangtao Zhai , Xiaohong Liu

Heavy tails is a common feature of filtering distributions that results from the nonlinear dynamical and observation processes as well as the uncertainty from physical sensors. In these settings, the Kalman filter and its ensemble version -…

Computation · Statistics 2023-10-16 Mathieu Le Provost , Ricardo Baptista , Jeff D. Eldredge , Youssef Marzouk

Reinforcement learning (RL) is a powerful paradigm for learning to make sequences of decisions. However, RL has yet to be fully leveraged in robotics, principally due to its lack of scalability. Offline RL offers a promising avenue by…

Machine Learning · Computer Science 2025-10-10 Nicolas Espinosa-Dice , Kiante Brantley , Wen Sun

Interference prediction that accounts for extreme and rare events remains a key challenge for ultra-densely deployed sub-networks (SNs) requiring hyper-reliable low-latency communication (HRLLC), particularly under dynamic mobility, rapidly…

Signal Processing · Electrical Eng. & Systems 2025-07-22 Pramesh Gautam , Sushmita Sapkota , Carsten Bockelmann , Shashi Raj Pandey , Armin Dekorsy

Mainstream parameter-efficient fine-tuning (PEFT) methods, such as LoRA or Adapter, project a model's hidden states to a lower dimension, allowing pre-trained models to adapt to new data through this low-rank bottleneck. However, PEFT tasks…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Tingyu Qu , Tinne Tuytelaars , Marie-Francine Moens

Fine-tuning large language models (LLMs) aims to adapt pre-trained models to specific tasks using relatively small and domain-specific datasets. Among Parameter-Efficient Fine-Tuning (PEFT) methods, Low-Rank Adaptation (LoRA) stands out by…

Computation and Language · Computer Science 2026-04-16 Yarui Cao , Kai Liu

Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-trained generative models to maximize a given reward function,…

Machine Learning · Statistics 2026-02-03 Yidong Ouyang , Liyan Xie , Hongyuan Zha , Guang Cheng

A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix. This matrix is decomposed into a product of…

Computer Vision and Pattern Recognition · Computer Science 2024-10-31 Wei Dong , Yuan Sun , Yiting Yang , Xing Zhang , Zhijun Lin , Qingsen Yan , Haokui Zhang , Peng Wang , Yang Yang , Hengtao Shen

In the era of foundation models, fine-tuning pre-trained models for specific downstream tasks has become crucial. This drives the need for robust fine-tuning methods to address challenges such as model overfitting and sparse labeling.…

Machine Learning · Computer Science 2025-12-12 Shikun Liu , Deyu Zou , Nima Shoghi , Victor Fung , Kai Liu , Pan Li

Post-training of large language models involves a fundamental trade-off between supervised fine-tuning (SFT), which efficiently mimics demonstrations but tends to memorize, and reinforcement learning (RL), which achieves better…

Machine Learning · Computer Science 2026-02-03 He Zhu , Junyou Su , Peng Lai , Ren Ma , Wenjia Zhang , Linyi Yang , Guanhua Chen

Graph Neural Networks frequently exhibit significant performance degradation in the out-of-distribution test scenario. While test-time training (TTT) offers a promising solution, existing Parameter Finetuning (PaFT) paradigm suffer from…

Machine Learning · Computer Science 2026-01-30 Jiaxin Zhang , Yiqi Wang , Siwei Wang , Xihong Yang , Yu Shi , Xinwang Liu , En Zhu

Surgical Video Question Answering (VideoQA) requires accurate temporal grounding while remaining robust to natural variation in how clinicians phrase questions, where linguistic bias can arise. Standard Parameter Efficient Fine Tuning…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Luca Carlini , Chiara Lena , Cesare Hassan , Danail Stoyanov , Elena De Momi , Sophia Bano , Mobarak I. Hoque

This paper introduces a novel process for both factor and idiosyncratic volatility matrices whose eigenvalues follow the vector auto-regressive (VAR) model. We call it the factor and idiosyncratic VAR (FIVAR) model. The FIVAR model accounts…

Methodology · Statistics 2025-09-25 Minseok Shin , Donggyu Kim , Yazhen Wang , Jianqing Fan

Real-world datasets typically exhibit long-tailed (LT) distributions, where a few head classes dominate and many tail classes are severely underrepresented. While recent work shows that parameter-efficient fine-tuning (PEFT) methods like…

Machine Learning · Computer Science 2026-01-27 Masih Aminbeidokhti , Subhankar Roy , Eric Granger , Elisa Ricci , Marco Pedersoli

Multiple federated learning (FL) methods are proposed for traffic flow forecasting (TFF) to avoid heavy-transmission and privacy-leaking concerns resulting from the disclosure of raw data in centralized methods. However, these FL methods…

Machine Learning · Computer Science 2024-11-22 Qingxiang Liu , Sheng Sun , Yuxuan Liang , Xiaolong Xu , Min Liu , Muhammad Bilal , Yuwei Wang , Xujing Li , Yu Zheng

Selecting a small, high-quality subset from a large corpus for fine-tuning is increasingly important as corpora grow to tens of millions of datapoints, making full fine-tuning expensive and often unnecessary. We propose CRAFT (Clustered…

Computation and Language · Computer Science 2026-04-27 Parthasarathi Panda , Asheswari Swain , Subhrakanta Panda

We address the problem of fine-tuning diffusion models for reward-guided generation in biomolecular design. While diffusion models have proven highly effective in modeling complex, high-dimensional data distributions, real-world…

Fine-tuning is a widely used strategy for adapting pre-trained models to new tasks, yet its methodology and theoretical properties in high-dimensional nonparametric settings with variable selection have not yet been developed. We propose a…

Machine Learning · Statistics 2026-05-19 Jinhang Chai , Jianqing Fan , Cheng Gao , Qishuo Yin