English
Related papers

Related papers: RAPTOR: Ridge-Adaptive Logistic Probes

200 papers

Ridge regression (RR) is a regularization technique that penalizes the L2-norm of the coefficients in linear regression. One of the challenges of using RR is the need to set a hyperparameter ($\alpha$) that controls the amount of…

Methodology · Statistics 2020-05-08 Ariel Rokem , Kendrick Kay

The widespread utilization of language models in modern applications is inconceivable without Parameter-Efficient Fine-Tuning techniques, such as low-rank adaptation ($\texttt{LoRA}$), which adds trainable adapters to selected layers.…

Machine Learning · Computer Science 2025-10-17 Andrey Veprikov , Vladimir Solodkin , Alexander Zyl , Andrey Savchenko , Aleksandr Beznosikov

Determining the relative position and orientation of objects in an environment is a fundamental building block for a wide range of robotics applications. To accomplish this task efficiently in practical settings, a method must be fast, use…

Robotics · Computer Science 2020-12-18 Benjamin Ramtoula , Adam Caccavale , Giovanni Beltrame , Mac Schwager

Large-scale image-text pre-trained models enable zero-shot classification and provide consistent accuracy across various data distributions. Nonetheless, optimizing these models in downstream tasks typically requires fine-tuning, which…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Sungyeon Kim , Boseung Jeong , Donghyun Kim , Suha Kwak

Soft prompts have been popularized as a cheap and easy way to improve task-specific LLM performance beyond few-shot prompts. Despite their origin as an automated prompting method, however, soft prompts and other trainable prompts remain a…

Machine Learning · Computer Science 2025-04-04 Oam Patel , Jason Wang , Nikhil Shivakumar Nayak , Suraj Srinivas , Himabindu Lakkaraju

Reinforcement learning (RL) is a promising tool to solve robust optimal well control problems where the model parameters are highly uncertain, and the system is partially observable in practice. However, RL of robust control policies often…

Machine Learning · Computer Science 2022-07-14 Atish Dixit , Ahmed H. ElSheikh

Proportional-integral-derivative (PID) controller is widely used across various industrial process control applications because of its straightforward implementation. However, it can be challenging to fine-tune the PID parameters in…

Systems and Control · Electrical Eng. & Systems 2022-06-09 Hozefa Jesawada , Amol Yerudkar , Carmen Del Vecchio , Navdeep Singh

Recent work has shown that language models (LMs) have strong multi-step (i.e., procedural) reasoning capabilities. However, it is unclear whether LMs perform these tasks by cheating with answers memorized from pretraining corpus, or, via a…

Computation and Language · Computer Science 2023-10-24 Yifan Hou , Jiaoda Li , Yu Fei , Alessandro Stolfo , Wangchunshu Zhou , Guangtao Zeng , Antoine Bosselut , Mrinmaya Sachan

A regularized version of Mixture Models is proposed to learn a principal graph from a distribution of $D$-dimensional data points. In the particular case of manifold learning for ridge detection, we assume that the underlying manifold can…

Machine Learning · Computer Science 2023-07-13 Tony Bonnaire , Aurélien Decelle , Nabila Aghanim

Quadruped robots face limitations in long-range navigation efficiency due to their reliance on legs. To ameliorate the limitations, we introduce a Reinforcement Learning-based Active Transporter Riding method (\textit{RL-ATR}), inspired by…

Robotics · Computer Science 2026-02-10 Minsung Yoon , Sung-Eui Yoon

Low-rank Adaptation (LoRA) has emerged as a powerful method for fine-tuning large-scale foundation models. Despite its popularity, the theoretical understanding of LoRA has remained limited. This paper presents a theoretical analysis of…

Machine Learning · Computer Science 2025-06-10 Tuan Truong , Chau Nguyen , Huy Nguyen , Minh Le , Trung Le , Nhat Ho

The remarkable capability of Transformers to do reasoning and few-shot learning, without any fine-tuning, is widely conjectured to stem from their ability to implicitly simulate a multi-step algorithms -- such as gradient descent -- with…

Machine Learning · Computer Science 2024-10-14 Khashayar Gatmiry , Nikunj Saunshi , Sashank J. Reddi , Stefanie Jegelka , Sanjiv Kumar

The organizer of a machine learning competition faces the problem of maintaining an accurate leaderboard that faithfully represents the quality of the best submission of each competing team. What makes this estimation problem particularly…

Machine Learning · Computer Science 2015-02-17 Avrim Blum , Moritz Hardt

A reinforcement learning (RL) based methodology is proposed and implemented for online fine-tuning of PID controller gains, thus, improving quadrotor effective and accurate trajectory tracking. The RL agent is first trained offline on a…

Systems and Control · Electrical Eng. & Systems 2025-02-10 Serhat Sönmez , Luca Montecchio , Simone Martini , Matthew J. Rutherford , Alessandro Rizzo , Margareta Stefanovic , Kimon P. Valavanis

Natural Language Processing (NLP) systems are increasingly taking the form of sophisticated modular pipelines, e.g., Retrieval Augmented Generation (RAG), where each module may involve a distinct Language Model (LM) and an associated prompt…

Computation and Language · Computer Science 2024-10-08 Dilara Soylu , Christopher Potts , Omar Khattab

Planning provides a framework for optimizing sequential decisions in complex environments. Recent advances in efficient planning in deterministic or stochastic high-dimensional domains with continuous action spaces leverage backpropagation…

Machine Learning · Computer Science 2021-06-15 Noah Patton , Jihwan Jeong , Michael Gimelfarb , Scott Sanner

Reinforcement learning has become essential for strengthening the reasoning abilities of large language models, yet current exploration mechanisms remain fundamentally misaligned with how these models actually learn. Entropy bonuses and…

Machine Learning · Computer Science 2025-12-18 Zhenwen Liang , Sidi Lu , Wenhao Yu , Kishan Panaganti , Yujun Zhou , Haitao Mi , Dong Yu

Harnessing the reasoning power of Large Language Models (LLMs) for recommender systems is hindered by two fundamental challenges. First, current approaches lack a mechanism for automated, data-driven discovery of effective reasoning…

Information Retrieval · Computer Science 2026-02-26 Jie Jiang , Yang Wu , Qian Li , Yuling Xiong , Hongbo Tang , Xun Liu , Haoze Wang , Jun Zhang , Huan Yu , Hailong Shi

Reinforcement learning (RL)-based quadrotor control policies have achieved impressive performance in tasks such as fast navigation in cluttered environments and drone racing, where the focus is on speed and agility. However, in several…

LLMs can solve complex tasks by generating long, multi-step reasoning chains. Test-time scaling (TTS) can further improve performance by sampling multiple variants of intermediate reasoning steps, verifying their correctness, and selecting…