paper-with-me

Papers

FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions

2025-04-14 · Daniel Marta, Simon Holk, Miguel Vasco, Jens Lundell, Timon Homberger, Finn Busch, Olov Andersson, Danica Kragic, Iolanda Leite

Preference-based reinforcement learning (PbRL) is a suitable approach for style adaptation of pre-trained robotic behavior: adapting the robot's policy to follow human user preferences while still being able to perform the original task. However, collecting preferences for the adaptation process in robotics is often challenging and time-consuming. In this work we explore the adaptation of pre-trained robots in the low-preference-data regime. We show that, in this regime, recent adaptation approaches suffer from catastrophic reward forgetting (CRF), where the updated reward model overfits to the new preferences, leading the agent to become unable to perform the original task. To mitigate CRF, we propose to enhance the original reward model with a small number of parameters (low-rank matrices) responsible for modeling the preference adaptation. Our evaluation shows that our method can efficiently and effectively adjust robotic behavior to human preferences across simulation benchmark tasks and multiple real-world robotic tasks.

📄 PDF Abstract BibTeX arXiv:2504.10002

Code (1)

daniellsm/flora 공식 구현

Methods 이 논문이 사용한 방법론

CRF Conditional Random Fields or CRFs are a type of probabilistic graph model that take neighboring sample context into account for tasks like classification. Prediction is…

Similar Papers 제목 키워드 기반

RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models

2025-05-24 · Yilang Zhang, Bingcong Li, Georgios B. Giannakis

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 conv…

Natural Language Understanding

Multimodal Large Language Models with Fusion Low Rank Adaptation for Device Directed Speech Detection

2024-06-13 · Shruti Palaskar, Oggi Rudovic, Sameer Dharur, Florian Pesce 외

Although Large Language Models (LLMs) have shown promise for human-like conversations, they are primarily pre-trained on text data. Incorporating audio or video improves performance, but collecting large-scale multimodal…

Batched Low-Rank Adaptation of Foundation Models

2023-12-09 · Yeming Wen, Swarat Chaudhuri

Low-Rank Adaptation (LoRA) has recently gained attention for fine-tuning foundation models by incorporating trainable low-rank matrices, thereby reducing the number of trainable parameters. While LoRA offers numerous adv…

Code Generationspeech-recognitionSpeech Recognition

AFLoRA: Adaptive Federated Fine-Tuning of Large Language Models with Resource-Aware Low-Rank Adaption

2025-05-30 · Yajie Zhou, Xiaoyi Pang, Zhibo Wang

Federated fine-tuning has emerged as a promising approach to adapt foundation models to downstream tasks using decentralized data. However, real-world deployment remains challenging due to the high computational and comm…

DiffLoRA: Differential Low-Rank Adapters for Large Language Models

2025-07-31 · Alexandre Misrahi, Nadezhda Chirkova, Maxime Louis, Vassilina Nikoulina arxiv

Differential Transformer has recently been proposed to improve performance in Transformer models by canceling out noise through a denoiser attention mechanism. In this work, we introduce DiffLoRA, a parameter-efficient a…

parameter-efficient fine-tuning