3 papers
cs.CV2026
Pixel-Space Diffusion Transformers
Renye Yan, Jikang Cheng, You Wu +9
Latent diffusion models (LDMs) enable efficient high-resolution image synthesis by denoising in a VAE-compressed latent space. However, fixed visual tokenizers can discard fine tex…
physics.app-ph2026
All-Optically Controlled Memristive Reservoir Computing Capable of Bipolar and Parallel Coding
Lingxiang Hu, Dian Jiao, Kexuan Wang +7
Physical reservoir computing (RC) utilizes the intrinsic dynamical evolution of physical systems for efficient data processing. Emerging optoelectronic RC platforms,such as light-d…
cs.CR2025
ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs
Gejian Zhao, Hanzhou Wu, Xinpeng Zhang +1
Chain-of-Thought (CoT) enhances an LLM's ability to perform complex reasoning tasks, but it also introduces new security issues. In this work, we present ShadowCoT, a novel backdoo…