arXiv ·
The paper introduces a novel actor-critic framework called Distillation Policy Optimization that combines on-policy and off-policy data for reinforcement learning. It incorporates variance reduction mechanisms like a unified advantage estimator (UAE) and a residual baseline. The empirical results demonstrate improved sample efficiency for on-policy algorithms, bridging the gap with off-policy methods.
arXiv ·
A new survey paper provides a deep dive into post-training methodologies for Large Language Models (LLMs), analyzing their role in refining LLMs beyond pretraining. It addresses key challenges such as catastrophic forgetting, reward hacking, and inference-time trade-offs, and highlights emerging directions in model alignment, scalable adaptation, and inference-time reasoning. The paper also provides a public repository to continually track developments in this fast-evolving field.
arXiv ·
This paper introduces SemDiff, a novel method for generating unrestricted adversarial examples (UAEs) by exploring the semantic latent space of diffusion models. SemDiff uses multi-attribute optimization to ensure attack success while preserving the naturalness and imperceptibility of generated UAEs. Experiments on high-resolution datasets demonstrate SemDiff's superior performance compared to state-of-the-art methods in attack success rate and imperceptibility, while also evading defenses.
arXiv ·
The paper introduces the Prism Hypothesis, which posits a correspondence between an encoder's feature spectrum and its functional role, with semantic encoders capturing low-frequency components and pixel encoders retaining high-frequency information. Based on this, the authors propose Unified Autoencoding (UAE), a model that harmonizes semantic structure and pixel details using a frequency-band modulator. Experiments on ImageNet and MS-COCO demonstrate that UAE effectively unifies semantic abstraction and pixel-level fidelity, achieving state-of-the-art performance.
arXiv ·
This paper introduces a novel fuzzy clustering method for circular time series based on a new dependence measure that considers circular arcs. The algorithm groups series generated from similar stochastic processes and demonstrates computational efficiency. The method is applied to time series of wind direction in Saudi Arabia, showcasing its practical potential.
arXiv ·
This paper introduces Provable Unrestricted Adversarial Training (PUAT), a novel adversarial training approach. PUAT enhances robustness against both unrestricted and restricted adversarial examples while improving standard generalizability by aligning the distributions of adversarial examples, natural data, and the classifier's learned distribution. The approach uses partially labeled data and an augmented triple-GAN to generate effective unrestricted adversarial examples, demonstrating superior performance on benchmarks.
arXiv ·
The first Workshop on Language Models for Low-Resource Languages (LoResLM 2025) was held in Abu Dhabi as part of COLING 2025. It provided a forum for researchers to share work on language models for low-resource languages. The workshop accepted 35 papers from 52 submissions, covering diverse languages and research areas.
arXiv ·
The Symposium on Data Mining and Applications (SDMA 2014) was organized by MEGDAM to foster collaboration among data mining and machine learning researchers in Saudi Arabia, GCC countries, and the Middle East. The symposium covered areas such as statistics, computational intelligence, pattern recognition, databases, Big Data Mining and visualization. Acceptance was based on originality, significance and quality of contribution.