Scalable Self-Supervised Learning for Multiphase AC-OPF in Distribution Systems with Topology Reconfiguration
本文提出了一种自监督学习框架Penalty+SLFS算法，用于解决含拓扑重构的多相交流最优潮流问题，无需标签训练，通过可微固定点潮流求解器直接从目标和约束条件中学习，实现快速且准确的求解。
0 citationsRead paper
Selected work
Representative Papers
FLARE: A Data-Efficient Surrogate for Predicting Displacement Fields in Directed Energy Deposition
This work addresses the challenge of part distortion in directed energy deposition (DED) manufacturing, which arises from thermomechanical coupling effects and is difficult to mitigate due to the high computational cost of conventional finite element simulations that hinder rapid design iteration. To overcome this limitation, the authors propose FLARE, a novel framework that constructs an affine structure in the weight space of an implicit neural field, enabling efficient prediction of post-cooling displacement fields by mapping geometric and process parameters to affine combinations of network weights. Requiring only a small number of simulation samples, FLARE achieves high data efficiency and demonstrates strong extrapolation capabilities. Experimental results show that FLARE significantly outperforms existing baselines in both in-distribution and extrapolation scenarios, confirming its accuracy and generalization performance.
0 citationsRead paper
All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Models
This work addresses the tendency of vision-language models trained via reinforcement learning to suffer from diversity collapse, leading to premature convergence onto a limited set of reasoning paths, suboptimal local solutions, and restricted scalability. To mitigate this issue, the authors propose Multi-group Policy Optimization (MUPO), a novel reinforcement learning framework that explicitly encourages divergent thinking by promoting diverse reasoning across multiple solution spaces. MUPO extends the existing Group Relative Policy Optimization (GRPO) algorithm and reveals fundamental differences between reinforcement learning agents and baseline models in terms of both reasoning breadth and depth. Experimental results demonstrate that MUPO significantly enhances reasoning diversity, overall performance, and model scalability on standard benchmarks.
0 citationsRead paper
Few Tokens Matter: Entropy Guided Attacks on Vision-Language Models
This work identifies a critical vulnerability in vision-language models (VLMs) during autoregressive generation: only ~20% of high-entropy tokens govern output path stability, rendering them highly susceptible to adversarial manipulation. Method: We propose the first Entropy-Guided Attack (EGA) framework, which employs entropy-sensitive decoding analysis to model token-level uncertainty and enables selective, token-wise perturbation injection; EGA further establishes a cross-architecture transferable attack paradigm. Results: Experiments demonstrate that EGA achieves 35–49% success in converting benign VLM outputs into harmful content, 17–26% transferability across diverse VLM architectures, and an overall attack success rate of 93–95%. This work uncovers a fundamental link between generative entropy dynamics and VLM security, introducing the first entropy-aware, token-focused adversarial attack paradigm—establishing a new benchmark for evaluating and enhancing VLM robustness and safety.
0 citationsRead paper
Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting
Existing prompt-based frozen vision-language models (VLMs) exhibit weak generalization in video anomaly detection (VAD), primarily due to overly abstract prompts that fail to model fine-grained anomaly cues—such as human-object interactions and action semantics. To address this, we propose ASK-Hint: the first action-centered, knowledge-guided structured prompting framework for VAD. ASK-Hint introduces fine-grained grouped prompts, guided question design, and semantic consistency reasoning, enabling high-accuracy and interpretable anomaly detection without VLM fine-tuning. Our method achieves strong cross-dataset and cross-model generalization, setting new state-of-the-art performance on UCF-Crime and XD-Violence. Crucially, it delivers transparent, step-by-step reasoning paths—enhancing both diagnostic utility and trustworthiness.
0 citationsRead paper
Recent publications
Latest Papers
Scalable Self-Supervised Learning for Multiphase AC-OPF in Distribution Systems with Topology Reconfiguration
本文提出了一种自监督学习框架Penalty+SLFS算法，用于解决含拓扑重构的多相交流最优潮流问题，无需标签训练，通过可微固定点潮流求解器直接从目标和约束条件中学习，实现快速且准确的求解。
0 citationsRead paper
FLARE: A Data-Efficient Surrogate for Predicting Displacement Fields in Directed Energy Deposition
This work addresses the challenge of part distortion in directed energy deposition (DED) manufacturing, which arises from thermomechanical coupling effects and is difficult to mitigate due to the high computational cost of conventional finite element simulations that hinder rapid design iteration. To overcome this limitation, the authors propose FLARE, a novel framework that constructs an affine structure in the weight space of an implicit neural field, enabling efficient prediction of post-cooling displacement fields by mapping geometric and process parameters to affine combinations of network weights. Requiring only a small number of simulation samples, FLARE achieves high data efficiency and demonstrates strong extrapolation capabilities. Experimental results show that FLARE significantly outperforms existing baselines in both in-distribution and extrapolation scenarios, confirming its accuracy and generalization performance.
0 citationsRead paper
All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Models
This work addresses the tendency of vision-language models trained via reinforcement learning to suffer from diversity collapse, leading to premature convergence onto a limited set of reasoning paths, suboptimal local solutions, and restricted scalability. To mitigate this issue, the authors propose Multi-group Policy Optimization (MUPO), a novel reinforcement learning framework that explicitly encourages divergent thinking by promoting diverse reasoning across multiple solution spaces. MUPO extends the existing Group Relative Policy Optimization (GRPO) algorithm and reveals fundamental differences between reinforcement learning agents and baseline models in terms of both reasoning breadth and depth. Experimental results demonstrate that MUPO significantly enhances reasoning diversity, overall performance, and model scalability on standard benchmarks.
0 citationsRead paper
Few Tokens Matter: Entropy Guided Attacks on Vision-Language Models
This work identifies a critical vulnerability in vision-language models (VLMs) during autoregressive generation: only ~20% of high-entropy tokens govern output path stability, rendering them highly susceptible to adversarial manipulation. Method: We propose the first Entropy-Guided Attack (EGA) framework, which employs entropy-sensitive decoding analysis to model token-level uncertainty and enables selective, token-wise perturbation injection; EGA further establishes a cross-architecture transferable attack paradigm. Results: Experiments demonstrate that EGA achieves 35–49% success in converting benign VLM outputs into harmful content, 17–26% transferability across diverse VLM architectures, and an overall attack success rate of 93–95%. This work uncovers a fundamental link between generative entropy dynamics and VLM security, introducing the first entropy-aware, token-focused adversarial attack paradigm—establishing a new benchmark for evaluating and enhancing VLM robustness and safety.
0 citationsRead paper
Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting
Existing prompt-based frozen vision-language models (VLMs) exhibit weak generalization in video anomaly detection (VAD), primarily due to overly abstract prompts that fail to model fine-grained anomaly cues—such as human-object interactions and action semantics. To address this, we propose ASK-Hint: the first action-centered, knowledge-guided structured prompting framework for VAD. ASK-Hint introduces fine-grained grouped prompts, guided question design, and semantic consistency reasoning, enabling high-accuracy and interpretable anomaly detection without VLM fine-tuning. Our method achieves strong cross-dataset and cross-model generalization, setting new state-of-the-art performance on UCF-Crime and XD-Violence. Crucially, it delivers transparent, step-by-step reasoning paths—enhancing both diagnostic utility and trustworthiness.
0 citationsRead paper