相关论文: Discriminative Feature Feedback with General Teach…

Reward inference (learning a reward model from human preferences) is a critical intermediate step in the Reinforcement Learning from Human Feedback (RLHF) pipeline for fine-tuning Large Language Models (LLMs). In practice, RLHF faces…

Federated learning (FL) is a privacy preserving machine learning paradigm designed to collaboratively learn a global model without data leakage. Specifically, in a typical FL system, the central server solely functions as an coordinator to…

Image style transfer is an underdetermined problem, where a large number of solutions can satisfy the same constraint (the content and style). Although there have been some efforts to improve the diversity of style transfer by introducing…

In this paper, we propose a novel policy iteration method, called dynamic policy programming (DPP), to estimate the optimal policy in the infinite-horizon Markov decision processes. We prove the finite-iteration and asymptotic l\infty-norm…

In decentralized federated learning (DFL), the presence of abnormal clients, often caused by noisy or poisoned data, can significantly disrupt the learning process and degrade the overall robustness of the model. Previous methods on this…

Classifier free guidance has shown strong potential in diffusion-based reinforcement learning. However, existing methods rely on joint training of the guidance module and the diffusion model, which can be suboptimal during the early stages…

Learning is a complex dynamical process shaped by a range of interconnected decisions. Careful design of hyperparameter schedules for artificial neural networks or efficient allocation of cognitive resources by biological learners can…

Users often possess a clear visual intent but struggle to articulate it precisely in language. This intention-expression gap makes aligning generated images with latent visual preferences a fundamental challenge in text-to-image diffusion…

Drifting Models [Deng et al., 2026] train a one-step generator by evolving samples under a kernel-based drift field, avoiding ODE integration at inference. The original analysis leaves two questions open. The drift-field iteration admits a…

While Diffusion Language Models (DLMs) are theoretically well-suited for iterative refinement due to their non-causal structure, they often fail to reliably revise incorrect tokens in practice. The key challenge lies in the model's…

We explore an active learning approach for dynamic fair resource allocation problems. Unlike previous work that assumes full feedback from all agents on their allocations, we consider feedback from a select subset of agents at each epoch of…

The Web is naturally heterogeneous with user devices, geographic regions, browsing patterns, and contexts all leading to highly diverse, unique datasets. Federated Learning (FL) is an important paradigm for the Web because it enables…

Differential privacy is one of the methods to solve the problem of privacy protection in federated learning. Setting the same privacy budget for each round will result in reduced accuracy in training. The existing methods of the adjustment…

We introduce a rehearsal-free federated domain incremental learning framework, RefFiL, based on a global prompt-sharing paradigm to alleviate catastrophic forgetting challenges in federated domain-incremental learning, where unseen domains…

Feature Transformation (FT) crafts new features from original ones via mathematical operations to enhance dataset expressiveness for downstream models. However, existing FT methods exhibit critical limitations: discrete search struggles…

Flow-based policies have recently emerged as a powerful tool in offline and offline-to-online reinforcement learning, capable of modeling the complex, multimodal behaviors found in pre-collected datasets. However, the full potential of…

We study online multiple testing with feedback, where decisions are made sequentially and the true state of the hypothesis is revealed after the decision has been made, either instantly or with a delay. We propose GAIF, a feedback-enhanced…

Targeting to understand the underlying explainable factors behind observations and modeling the conditional generation process on these factors, we connect disentangled representation learning to Diffusion Probabilistic Models (DPMs) to…

As neural networks are increasingly being applied to real-world applications, mechanisms to address distributional shift and sequential task learning without forgetting are critical. Methods incorporating network expansion have shown…

We study the problem of online binary classification in settings where strategic agents can modify their observable features to receive a positive classification. We model the set of feasible manipulations by a directed graph over the…