arXiv:2605.10989v1 Announce Type: new Abstract: The training of Binary Neural Networks (BNNs) is fundamentally based on gradient approximation for non-differentiable binarization operations (e.g., sign function). However, prevailing methods including the Straight-Through Estimator (STE) and its improved variants, rely on hand-crafted…
arXiv:2512.20865v2 Announce Type: replace Abstract: The increasing use of machine learning in safety-critical domains amplifies the risk of adversarial threats, especially data poisoning attacks that corrupt training data to degrade performance or induce unsafe behavior. Most existing defenses lack formal…
arXiv:2605.10991v1 Announce Type: new Abstract: Existing approaches to LLM personalization focus on constructing better personalized models or inputs, while treating inference as a single-shot process. In this work, we study Test-Time Personalization (TTP) along an unexplored axis: scaling inference-time computation…
arXiv:2603.23878v2 Announce Type: replace Abstract: The parameterized CROWN analysis, a.k.a., alpha-CROWN has emerged as a practically successful abstract interpretation method for neural network verification. However, existing implementations of alpha-CROWN are limited to Python, which complicates integration into existing DNN verifiers…
arXiv:2605.10999v1 Announce Type: new Abstract: Skills are a promising way to improve LLM agent capabilities without retraining, while keeping the added procedure reusable and controllable. However, high-quality skills are still largely written by hand. We introduce SkillGen, a multi-agent framework…
arXiv:2605.09523v2 Announce Type: replace Abstract: Neural operators provide fast surrogate models for time-dependent partial differential equations, but their standard autoregressive use usually assumes that the instantaneous field $u(t,cdot)$ is a complete state. This assumption fails for delay equations, distributed-memory systems,…
arXiv:2605.11001v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) are a simple surrogate-modelling paradigm for partial differential equations, but their standard strong-form residual formulation is ill suited to the shallow water equations (SWE). It cannot enforce local conservation, handle discontinuities,…
arXiv:2509.00931v3 Announce Type: replace-cross Abstract: We present a novel deep generative semi-supervised framework for credit card fraud detection, formulated as time series classification task. As financial transaction data streams grow in scale and complexity, traditional methods often require large labeled…
arXiv:2605.11005v1 Announce Type: new Abstract: Mixture-of-experts (MoE) architectures enable trillion-parameter LLMs with sparsely activated experts. Expert parallelism (EP) is a widely adopted MoE training strategy, but it suffers from severe all-to-all communication bottlenecks, which is exaggerated by the limited inter-node…
arXiv:2604.04894v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning ability of large language models (LLMs), but it often suffers from textit{restricted exploration}, where the policy rapidly concentrates on a narrow set of solutions.…
