Jianli Zhao

Jianli Zhao, Tingchen Fu, Rylan Schaeffer et al.

Large reasoning models (LRMs) achieve higher task performance with more inference-time computation, and prior works suggest this scaled reasoning may also strengthen safety by improving refusal. Yet we find the opposite: the same reasoning can be used to bypass safeguards. We introduce Chain-of-Thought Hijacking, a jailbreak attack on reasoning models. The attack pads harmful requests with long sequences of harmless puzzle reasoning. Across HarmBench, CoT Hijacking reaches a 99%, 94%, 100%, and 94% attack success rate (ASR) on Gemini 2.5 Pro, GPT o4 mini, Grok 3 mini, and Claude 4 Sonnet, respectively - far exceeding prior jailbreak methods for LRMs. To understand the effectiveness of our attack, we turn to a mechanistic analysis, which shows that mid layers encode the strength of safety checking, while late layers encode the verification outcome. Long benign CoT dilutes both signals by shifting attention away from harmful tokens. Targeted ablations of attention heads identified by this analysis causally decrease refusal, confirming their role in a safety subnetwork. These results show that the most interpretable form of reasoning - explicit CoT - can itself become a jailbreak vector when combined with final-answer cues. We release prompts, outputs, and judge decisions to facilitate replication.

Liang Li, Jianli Zhao, Sheng Fang et al.

Hyperspectral images (HSIs) are often degraded by complex mixed noise during acquisition and transmission, making effective denoising essential for subsequent analysis. Recent hybrid approaches that bridge model-driven and data-driven paradigms have shown great promise. However, most of these approaches lack effective alternation between different priors or modules, resulting in loosely coupled regularization and insufficient exploitation of their complementary strengths. Inspired by tensor robust principal component analysis (TRPCA), we propose a novel deep unfolding network (DU-TRPCA) that enforces stage-wise alternation between two tightly integrated modules: low-rank and sparse. The low-rank module employs thresholded tensor singular value decomposition (t-SVD), providing a widely adopted convex surrogate for tensor low-rankness and has been demonstrated to effectively capture the global spatial-spectral structure of HSIs. The Top-K sparse transformer module adaptively imposes sparse constraints, directly matching the sparse regularization in TRPCA and enabling effective removal of localized outliers and complex noise. This tightly coupled architecture preserves the stage-wise alternation between low-rank approximation and sparse refinement inherent in TRPCA, while enhancing representational capacity through attention mechanisms. Extensive experiments on synthetic and real-world HSIs demonstrate that DU-TRPCA surpasses state-of-the-art methods under severe mixed noise, while offering interpretability benefits and stable denoising dynamics inspired by iterative optimization. Code is available at https://github.com/liangli97/TRPCA-Deep-Unfolding-HSI-Denoising.

Jianli Zhao, Changhao Xu, Bin Jiang

Relational triple extraction is a fundamental task in the field of information extraction, and a promising framework based on table filling has recently gained attention as a potential baseline for entity relation extraction. However, inherent shortcomings such as redundant information and incomplete triple recognition remain problematic. To address these challenges, we propose an Implicit Perspective for relational triple Extraction based on Diffusion model (IPED), an innovative approach for extracting relational triples. Our classifier-free solution adopts an implicit strategy using block coverage to complete the tables, avoiding the limitations of explicit tagging methods. Additionally, we introduce a generative model structure, the block-denoising diffusion model, to collaborate with our implicit perspective and effectively circumvent redundant information disruptions. Experimental results on two popular datasets demonstrate that IPED achieves state-of-the-art performance while gaining superior inference speed and low computational complexity. To support future research, we have made our source code publicly available online.

Sheng Fang, Kaiyu Li, Zhe Li et al.

Image translation for change detection or classification in bi-temporal remote sensing images is unique. Although it can acquire paired images, it is still unsupervised. Moreover, strict semantic preservation in translation is always needed instead of multimodal outputs. In response to these problems, this paper proposes a new method, SRUIT (Semantically Robust Unsupervised Image-to-image Translation), which ensures semantically robust translation and produces deterministic output. Inspired by previous works, the method explores the underlying characteristics of bi-temporal Remote Sensing images and designs the corresponding networks. Firstly, we assume that bi-temporal Remote Sensing images share the same latent space, for they are always acquired from the same land location. So SRUIT makes the generators share their high-level layers, and this constraint will compel two domain mapping to fall into the same latent space. Secondly, considering land covers of bi-temporal images could evolve into each other, SRUIT exploits the cross-cycle-consistent adversarial networks to translate from one to the other and recover them. Experimental results show that constraints of sharing weights and cross-cycle consistency enable translated images with both good perceptual image quality and semantic preservation for significant differences.