arXiv:2511.22619v2 Announce Type: replace Abstract: As intelligence increases, so does its shadow. AI deception, in which systems induce false beliefs to secure self-beneficial outcomes, has evolved from a speculative concern to an empirically demonstrated risk across language models, AI agents, and emerging frontier systems. This project provides a comprehensive and up-to-date overview of the AI deception field, covering its core concepts, methodologies, genesis, and potential mitigations. First, we identify a formal definition of AI deception, grounded in signaling theory from studies of animal deception. We then review existing empirical studies and associated risks, highlighting deception as a sociotechnical safety challenge. We organize the landscape of AI deception research as a deception cycle, consisting of two key components: deception emergence and deception treatment. Deception emergence reveals the mechanisms underlying AI deception: systems with sufficient capability and incentive potential inevitably engage in deceptive behaviors when triggered by external conditions. Deception treatment, in turn, focuses on detecting and addressing such behaviors. On deception emergence, we analyze incentive foundations across three hierarchical levels and identify three essential capability preconditions required for deception. We further examine contextual triggers, including supervision gaps, distributional shifts, and environmental pressures. On deception treatment, we conclude detection methods covering benchmarks and evaluation protocols in static and interactive settings. Building on the three core factors of deception emergence, we outline potential mitigation strategies and propose auditing approaches that integrate technical, community, and governance efforts to address sociotechnical challenges and future AI risks. To support ongoing work in this area, we release a living resource at www.deceptionsurvey.com.

arXiv:2502.07299v3 Announce Type: replace-cross Abstract: The interactions between DNA, RNA, and proteins are fundamental to biological processes, as illustrated by the central dogma of molecular biology. Although modern biological pre-trained models have achieved great success in analyzing these macromolecules individually, their interconnected nature remains underexplored. This paper follows the guidance of the central dogma to redesign both the data and model pipeline and offers a comprehensive framework, Life-Code, that spans different biological functions. As for data flow, we propose a unified pipeline to integrate multi-omics data by reverse-transcribing RNA and reverse-translating amino acids into nucleotide-based sequences. As for the model, we design a codon tokenizer and a hybrid long-sequence architecture to encode the interactions between coding and non-coding regions through masked modeling pre-training. To model the translation and folding process with coding sequences, Life-Code learns protein structures of the corresponding amino acids by knowledge distillation from off-the-shelf protein language models. Such designs enable Life-Code to capture complex interactions within genetic sequences, providing a more comprehensive understanding of multi-omics with the central dogma. Extensive experiments show that Life-Code achieves state-of-the-art results on various tasks across three omics, highlighting its potential for advancing multi-omics analysis and interpretation.

Background: Stroke frequently leads to various functional impairments. Both virtual reality (VR) and mirror therapy (MT) have shown efficacy in stroke rehabilitation. In recent years, the combination of these two approaches has emerged as a potential treatment for stroke patients. Objective: This systematic review and meta-analysis aim to evaluate the efficacy of combined immersive and non-immersive VR with MT in stroke rehabilitation. Methods: Five electronic databases were systematically searched for relevant articles published up to Jan. 2025. Randomized controlled trials (RCTs) that investigated combination treatment of VR and MT for participants with stroke were included. A grey literature search was also conducted. The risk of bias and the certainty of the evidence were assessed using the Cochrane collaboration’s tool and the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) guideline, respectively. Results: A total of 475 participants from 14 RCTs were included, of which 7 were eligible for meta-analysis. Meta-analysis revealed significant improvements in upper extremity (UE) motor function and hand dexterity, as evidenced by Fugl-Meyer assessment of upper extremity (FMA-UE) (MD 3.50, 95% CI 1.47 to 5.53; P=0.0007), manual function test (MFT) (MD 2.15, 95% CI 1.22 to 3.09; P6 months or not) revealed significant differences in the FMA-UE outcome. However, the pooled FMA-UE improvement did not consistently exceed the established minimal clinically important difference (MCID; 4.25–7.25), indicating that while statistically significant, the clinical meaningfulness of the observed effect remains uncertain. Narrative evidence also suggested potential benefits for lower extremity function, dynamic balance, and quality of life, though these findings were not meta-analyzed and should be interpreted with caution. Conclusions: Moderate-quality evidence supports VR-MT as a promising nonpharmacological intervention to improve upper extremity function and hand dexterity in stroke rehabilitation. While the intervention demonstrates statistically significant effects, it does not reach the minimum clinically important difference for the FMA-UE outcome. Preliminary descriptive evidence indicates possible advantages for lower extremity function, balance, and quality of life. Clinical Trial: PROSPERO CRD42024572150