arXiv:2510.18637v1 Announce Type: cross Abstract: Semantic segmentation of electron microscopy (EM) images of biological samples remains a challenge in the life sciences. EM data captures details of biological structures, sometimes with such complexity that even human observers can find it…
arXiv:2510.17917v1 Announce Type: new Abstract: Data unlearning aims to remove the influence of specific training samples from a trained model without requiring full retraining. Unlike concept unlearning, data unlearning in diffusion models remains underexplored and often suffers from quality degradation…
arXiv:2305.08813v2 Announce Type: replace Abstract: Nonlinear activation functions are widely recognized for enhancing the expressivity of neural networks, which is the primary reason for their widespread implementation. In this work, we focus on ReLU activation and reveal a novel and…
arXiv:2510.17923v1 Announce Type: new Abstract: Reinforcement Learning (RL) has emerged as a powerful paradigm for advancing Large Language Models (LLMs), achieving remarkable performance in complex reasoning domains such as mathematics and code generation. However, current RL methods face a fundamental…
arXiv:2502.08227v3 Announce Type: replace Abstract: Sample selection is a prevalent approach in learning with noisy labels, aiming to identify confident samples for training. Although existing sample selection methods have achieved decent results by reducing the noise rate of the selected…
arXiv:2510.17928v1 Announce Type: new Abstract: Reliable verifiable data has become a key driver of capability gains in modern language models, enabling stable reinforcement learning with verifiable rewards and effective distillation that transfers competence across math, coding, and agentic tasks. Yet…
arXiv:2505.16333v3 Announce Type: replace Abstract: Differential Transformer has recently gained significant attention for its impressive empirical performance, often attributed to its ability to perform noise canceled attention. However, precisely how differential attention achieves its empirical benefits remains poorly understood. Moreover,…
arXiv:2510.17933v1 Announce Type: new Abstract: Detecting regime shifts in chaotic time series is hard because observation-space signals are entangled with intrinsic variability. We propose Parameter–Space Changepoint Detection (Param–CPD), a two–stage framework that first amortizes Bayesian inference of governing parameters with…
arXiv:2507.09252v3 Announce Type: replace Abstract: We propose TPP-SD, a novel approach that accelerates Transformer temporal point process (TPP) sampling by adapting speculative decoding (SD) techniques from language models. By identifying the structural similarities between thinning algorithms for TPPs and speculative…
arXiv:2510.17937v1 Announce Type: new Abstract: We present UniRL-Zero, a unified reinforcement learning (RL) framework that boosts, multimodal language model understanding and reasoning, diffusion model multimedia generation, and their beneficial interaction capabilities within a unified model. Our work defines six scenarios…
