本文提出CamoShift框架，通过视觉伪装和红外偏移破坏可见光-红外对象检测器的跨模态空间对齐，使用Semantic Camouflage Module和Object-level Spatial Decoupling Module实现攻击的同时保持视觉隐蔽性。
为解决衣物变化导致的终身人物重识别问题，提出SCORE框架，通过建模身份内部多样性并强化分布知识来缓解灾难性遗忘。
This work addresses the challenge of quantizing spiking neural networks (SNNs) under low-bit constraints, where membrane potentials are typically represented in floating-point format, leading to complex distributions and high sensitivity to threshold perturbations that hinder effective quantization and induce error accumulation. To overcome this, the authors propose a post-training quantization framework that jointly quantizes both weights and recurrent membrane potential states without requiring retraining, applicable to both convolutional SNNs and spiking-driven Transformers. The method introduces a channel-wise uniform scaling bridge to align the scales of membrane potentials and weights and employs a mixed-precision allocation strategy based on neuronal firing activity and quantization sensitivity, optimizing accuracy under an average bit-width budget. Experiments demonstrate that with weights quantized to 4 bits and membrane potentials to approximately 4 bits, the models maintain high accuracy on image classification and semantic segmentation tasks.
This work addresses the challenge of real-world image restoration under complex, coupled degradations, where existing agent-based methods struggle to balance exploration and exploitation due to greedy search strategies and suffer from insufficient information utilization and catastrophic forgetting. To overcome these limitations, the paper formulates restoration as a sequential decision-making problem and proposes a self-evolving agent framework grounded in dual-process theory, integrating an intuitive executor with a deliberative planner. The approach introduces a pruning-aware Monte Carlo tree search for long-horizon reasoning and devises a degradation-aware state fingerprint to drive episodic memory, effectively mitigating forgetting and reducing cold-start costs. Evaluated with a no-reference hybrid reward and multimodal large language model–based assessment, the method achieves state-of-the-art perceptual quality and quantitative performance on both synthetic and real-world benchmarks.
This work addresses the challenge of unreliable triples in knowledge graphs and the limitations of existing classification methods in modeling semantic interactions and learning expressive representations. To this end, we propose a decoupled context encoding approach based on a disentangled attention mechanism that effectively captures interactions among the components of a triple. Furthermore, we introduce a semantic-aware hierarchical contrastive learning objective that integrates both local and global semantic information to enhance representation quality. By incorporating natural language description embeddings, our model achieves significant improvements in classification accuracy, outperforming state-of-the-art methods by 5.9% on FB15k-237 and 3.4% on YAGO3-10.
本文提出CamoShift框架，通过视觉伪装和红外偏移破坏可见光-红外对象检测器的跨模态空间对齐，使用Semantic Camouflage Module和Object-level Spatial Decoupling Module实现攻击的同时保持视觉隐蔽性。
为解决衣物变化导致的终身人物重识别问题，提出SCORE框架，通过建模身份内部多样性并强化分布知识来缓解灾难性遗忘。
This work addresses the challenge of quantizing spiking neural networks (SNNs) under low-bit constraints, where membrane potentials are typically represented in floating-point format, leading to complex distributions and high sensitivity to threshold perturbations that hinder effective quantization and induce error accumulation. To overcome this, the authors propose a post-training quantization framework that jointly quantizes both weights and recurrent membrane potential states without requiring retraining, applicable to both convolutional SNNs and spiking-driven Transformers. The method introduces a channel-wise uniform scaling bridge to align the scales of membrane potentials and weights and employs a mixed-precision allocation strategy based on neuronal firing activity and quantization sensitivity, optimizing accuracy under an average bit-width budget. Experiments demonstrate that with weights quantized to 4 bits and membrane potentials to approximately 4 bits, the models maintain high accuracy on image classification and semantic segmentation tasks.
This work addresses the challenge of real-world image restoration under complex, coupled degradations, where existing agent-based methods struggle to balance exploration and exploitation due to greedy search strategies and suffer from insufficient information utilization and catastrophic forgetting. To overcome these limitations, the paper formulates restoration as a sequential decision-making problem and proposes a self-evolving agent framework grounded in dual-process theory, integrating an intuitive executor with a deliberative planner. The approach introduces a pruning-aware Monte Carlo tree search for long-horizon reasoning and devises a degradation-aware state fingerprint to drive episodic memory, effectively mitigating forgetting and reducing cold-start costs. Evaluated with a no-reference hybrid reward and multimodal large language model–based assessment, the method achieves state-of-the-art perceptual quality and quantitative performance on both synthetic and real-world benchmarks.
This work addresses the challenge of unreliable triples in knowledge graphs and the limitations of existing classification methods in modeling semantic interactions and learning expressive representations. To this end, we propose a decoupled context encoding approach based on a disentangled attention mechanism that effectively captures interactions among the components of a triple. Furthermore, we introduce a semantic-aware hierarchical contrastive learning objective that integrates both local and global semantic information to enhance representation quality. By incorporating natural language description embeddings, our model achieves significant improvements in classification accuracy, outperforming state-of-the-art methods by 5.9% on FB15k-237 and 3.4% on YAGO3-10.