Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding and generation by integrating visual and textual data. However, these models frequently exhibit object hallucination problems: generating outputs that are inconsistent with the input image. Existing improved methods for mitigating hallucinations still suffer from two key limitations: dynamic approaches based on logits or attention mechanisms risk suppressing valuable linguistic priors, whereas static methods that employ fixed intervention vectors lack the flexibility to adapt to diverse images and questions. To address these issues, we propose RFI (Rectified Flow Intervention), a novel approach that harnesses the linear trajectory design of rectified flow for input-specific adaptation and employs gradient correction to ensure coherent generation, effectively combining the adaptability of dynamic methods with the stability of static ones. RFI dynamically predicts latent-space intervention vectors while requiring only a single forward pass in LVLMs per question, achieving computational efficiency (1.09x latency overhead for 100 new tokens). Extensive experiments show RFI significantly reduces hallucinations, achieving superior performance compared to existing advanced methods, highlighting its effectiveness as a lightweight plug-and-play method for reducing LVLM's hallucination in practical applications.

Lyrics generation has garnered increasing attention within the artificial intelligence community.Our task focuses on generating harmonious Cantonese lyrics.Unlike other languages, Cantonese has a unique system of nine contours and six tones, making it essential to satisfy the harmony rules that ensure the alignment between the melody and the tonal contours of the lyrics when composing lyrics.Current research has not yet addressed the challenge of generating lyrics that adhere to Cantonese harmony rules.To tackle this issue, we propose ToneCraft, a novel framework for generating Cantonese lyrics that ensures tonal and melodic harmony.It enables LLMs to generate lyrics with a fixed character count while aligning with tonal and melodic structures.We present an algorithm that combines characterlevel control, melodic guidance, and a taskspecific loss to achieve tonal harmony without compromising generation flexibility and quality.By incorporating domain-specific expertise, we leverage pure lyric datasets to train our model, eliminating the need for aligned data.Both objective evaluations and subjective assessments show that our generated lyrics align with melodic contours significantly better than existing methods.All code and data are available at: https://github.com/purepasser- by/ToneCraft.

Random chunks generation attack is a more sophisticated form of side channel attack in cross-user chunk level deduplication, in which the target chunks are checked together with randomly generated non-duplicate ones. When the number of required chunks or linear combinations equals to that of the randomly generated chunks, this issue prevents existing schemes from achieving obfuscation in the response, thereby compromising the existence privacy of the target chunks. Moreover, this vulnerability becomes even more pronounced under the hybrid attack, in which a portion of the target chunks is replaced by public ones. To address both kinds of attacks in a lightweight way, we propose a hotness strategy based secure cross-user deduplication scheme (HSDS) for cloud storage. Specifically, the cloud service provider (CSP) records the feature hotness and chunk hotness of duplicate chunks before defining specific chunks to be non-duplicate in response generation. Both the security analysis and experimental results show that the probability to expose the existence of sensitive chunks of the proposed scheme is negligible, which is effective in resisting the random chunks generation attack and its hybrid form in a lightweight way.