English
Related papers

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

200 papers

Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT). In standard ReFT frameworks, a behavior model generates multiple completions with…

Machine Learning · Computer Science 2025-11-25 Maxime Heuillet , Yufei Cui , Boxing Chen , Audrey Durand , Prasanna Parthasarathi

Neural network compression techniques typically require expensive fine-tuning or search procedures, rendering them impractical on commodity hardware. Inspired by recent LLM compression research, we present a general activation-aware…

Machine Learning · Computer Science 2025-10-14 David González-Martínez

We consider continuous-time stochastic optimal control problems featuring Conditional Value-at-Risk (CVaR) in the objective. The major difficulty in these problems arises from time-inconsistency, which prevents us from directly using…

Optimization and Control · Mathematics 2020-05-27 Christopher W. Miller , Insoon Yang

We propose a transformation capable of altering the tail properties of a distribution, motivated by extreme value theory, which can be used as a layer in a normalizing flow to approximate multivariate heavy tailed distributions. We apply…

Machine Learning · Statistics 2023-11-02 Tennessee Hickling , Dennis Prangle

In generative modeling, we often wish to produce samples that maximize a user-specified reward such as aesthetic quality or alignment with human preferences, a problem known as \textit{guidance}. Despite their widespread use, existing…

Machine Learning · Computer Science 2026-05-21 Jerry Y. Huang , Justin Lin , Sheel Shah , Kartik Nair , Nicholas M. Boffi

Expected risk minimization (ERM) is at the core of many machine learning systems. This means that the risk inherent in a loss distribution is summarized using a single number - its average. In this paper, we propose a general approach to…

Machine Learning · Computer Science 2023-01-24 Christian Fröhlich , Robert C. Williamson

Limited labeled data makes it hard to train models from scratch in medical domain, and an important paradigm is pre-training and then fine-tuning. Large pre-trained models contain rich representations, which can be adapted to downstream…

Computer Vision and Pattern Recognition · Computer Science 2023-07-20 Along He , Kai Wang , Zhihong Wang , Tao Li , Huazhu Fu

Current end-to-end autonomous driving systems are fundamentally limited by a mismatch between temporal causal reasoning and global trajectory consistency. Autoregressive (AR) models capture interaction-aware temporal dependencies via causal…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Xiyang Wang , Xinlin Wang , Tingguang Zhou , Gong Chen , Xingtai Gui , Zhi Xu , Xiaolei Wu , Feiyang Tan , Hangning Zhou , Mu Yang

We introduce a method to estimate simultaneously the tail and the threshold parameters of an extreme value regression model. This standard model finds its use in finance to assess the effect of market variables on extreme loss distributions…

Methodology · Statistics 2023-04-17 Julien Hambuckers , Marie Kratz , Antoine Usseglio-Carleve

Vision-Language-Action (VLA) models enable embodied decision-making but rely heavily on imitation learning, leading to compounding errors and poor robustness under distribution shift. Reinforcement learning (RL) can mitigate these issues…

Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model. Although existing methods are derived from different perspectives, we show…

Machine Learning · Computer Science 2026-05-08 Jeongjae Lee , Jinho Chang , Jeongsol Kim , Jong Chul Ye

Offline multi-agent reinforcement learning (MARL) aims to learn the optimal joint policy from pre-collected datasets, requiring a trade-off between maximizing global returns and mitigating distribution shift from offline data. Recent…

Machine Learning · Computer Science 2026-04-10 Teng Pang , Zhiqiang Dong , Yan Zhang , Rongjian Xu , Guoqiang Wu , Yilong Yin

Video diffusion alignment has been heavily relied on scalar rewards. These rewards are typically derived from learned reward models in human preference datasets, requiring additional training and extensive collection. Moreover, scalar…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Yifan Wang , Yanyu Li , Gordon Guocheng Qian , Sergey Tulyakov , Yun Fu , Anil Kag

Test-time adaptation (TTA) is an effective approach to mitigate performance degradation of trained models when encountering input distribution shifts at test time. However, existing TTA methods often suffer significant performance drops…

Machine Learning · Computer Science 2025-02-06 Minguk Jang , Hye Won Chung

We introduce iterative tilting, a gradient-free method for fine-tuning diffusion models toward reward-tilted distributions. The method decomposes a large reward tilt $\exp(\lambda r)$ into $N$ sequential smaller tilts, each admitting a…

Machine Learning · Statistics 2025-12-04 Jean Pachebat , Giovanni Conforti , Alain Durmus , Yazid Janati

With the scale of vision Transformer-based models continuing to grow, finetuning these large-scale pretrained models for new tasks has become increasingly parameter-intensive. Visual prompt tuning is introduced as a parameter-efficient…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Runjia Zeng , Cheng Han , Qifan Wang , Chunshu Wu , Tong Geng , Lifu Huang , Ying Nian Wu , Dongfang Liu

Parameter-Efficient Fine-Tuning (PEFT) of text-to-image models has become an increasingly popular technique with many applications. Among the various PEFT methods, Low-Rank Adaptation (LoRA) and its variants have gained significant…

Machine Learning · Computer Science 2025-08-01 Zerui Tao , Yuhta Takida , Naoki Murata , Qibin Zhao , Yuki Mitsufuji

To address limitations of the graph fractional Fourier transform (GFRFT) Wiener filtering and the traditional joint time-vertex fractional Fourier transform (JFRFT) Wiener filtering, this study proposes a filtering method based on the…

Signal Processing · Electrical Eng. & Systems 2025-07-30 Ziqi Yan , Zhichao Zhang

Reinforcement learning algorithms utilizing policy gradients (PG) to optimize Conditional Value at Risk (CVaR) face significant challenges with sample inefficiency, hindering their practical applications. This inefficiency stems from two…

Machine Learning · Computer Science 2024-07-01 Yudong Luo , Yangchen Pan , Han Wang , Philip Torr , Pascal Poupart

Visual autoregressive (VAR) modeling has marked a paradigm shift in image generation from next-token prediction to next-scale prediction. VAR predicts a set of tokens at each step from coarse to fine scale, leading to better image quality…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Renjie Wei , Songqiang Xu , Qingyu Guo , Meng Li