With the rapid advancement of generative models, associated privacy concerns have attracted growing attention. To address this, researchers have begun adapting machine unlearning techniques from traditional classification models to generative settings. Although notable progress has been made in this area, a unified framework for systematically organizing and integrating existing work is still lacking. The substantial differences among current studies in terms of unlearning objectives and evaluation protocols hinder the objective and fair comparison of various approaches. While some studies focus on specific types of generative models, they often overlook the commonalities and systematic characteristics inherent in Generative Model Unlearning (GenMU). To bridge this gap, we provide a comprehensive review of current research on GenMU and propose a unified analytical framework for categorizing unlearning objectives, methodological strategies, and evaluation metrics. In addition, we explore the connections between GenMU and related techniques, including model editing, reinforcement learning from human feedback, and controllable generation. We further highlight the potential practical value of unlearning techniques in real-world applications. Finally, we identify key challenges and outline future research directions aimed at laying a solid foundation for further advancements in this field. We consistently maintain the related open-source materials at https://github.com/caxLee/Generative-model-unlearning-survey.

The use of large language models (LLMs) in hiring promises to streamline candidate screening, but it also raises serious concerns regarding accuracy and algorithmic bias where sufficient safeguards are not in place. In this work, we benchmark several state-of-the-art foundational LLMs - including models from OpenAI, Anthropic, Google, Meta, and Deepseek, and compare them with our proprietary domain-specific hiring model (Match Score) for job candidate matching. We evaluate each model's predictive accuracy (ROC AUC, Precision-Recall AUC, F1-score) and fairness (impact ratio of cut-off analysis across declared gender, race, and intersectional subgroups). Our experiments on a dataset of roughly 10,000 real-world recent candidate-job pairs show that Match Score outperforms the general-purpose LLMs on accuracy (ROC AUC 0.85 vs 0.77) and achieves significantly more equitable outcomes across demographic groups. Notably, Match Score attains a minimum race-wise impact ratio of 0.957 (near-parity), versus 0.809 or lower for the best LLMs, (0.906 vs 0.773 for the intersectionals, respectively). We discuss why pretraining biases may cause LLMs with insufficient safeguards to propagate societal biases in hiring scenarios, whereas a bespoke supervised model can more effectively mitigate these biases. Our findings highlight the importance of domain-specific modeling and bias auditing when deploying AI in high-stakes domains such as hiring, and caution against relying on off-the-shelf LLMs for such tasks without extensive fairness safeguards. Furthermore, we show with empirical evidence that there shouldn't be a dichotomy between choosing accuracy and fairness in hiring: a well-designed algorithm can achieve both accuracy in hiring and fairness in outcomes.

The widespread availability of video recording through smartphones and digital devices has made video-based evidence more accessible than ever. Surveillance footage plays a crucial role in security, law enforcement, and judicial processes. However, with the rise of advanced video editing tools, tampering with digital recordings has become increasingly easy, raising concerns about their authenticity. Ensuring the integrity of surveillance videos is essential, as manipulated footage can lead to misinformation and undermine judicial decisions. This paper provides a comprehensive review of existing forensic techniques used to detect video forgery, focusing on their effectiveness in verifying the authenticity of surveillance recordings. Various methods, including compression-based analysis, frame duplication detection, and machine learning-based approaches, are explored. The findings highlight the growing necessity for more robust forensic techniques to counteract evolving forgery methods. Strengthening video forensic capabilities will ensure that surveillance recordings remain credible and admissible as legal evidence.

We introduce Kimi K2, a Mixture-of-Experts (MoE) large language model with 32 billion activated parameters and 1 trillion total parameters. We propose the MuonClip optimizer, which improves upon Muon with a novel QK-clip technique to address training instability while enjoying the advanced token efficiency of Muon. Based on MuonClip, K2 was pre-trained on 15.5 trillion tokens with zero loss spike. During post-training, K2 undergoes a multi-stage post-training process, highlighted by a large-scale agentic data synthesis pipeline and a joint reinforcement learning (RL) stage, where the model improves its capabilities through interactions with real and synthetic environments. Kimi K2 achieves state-of-the-art performance among open-source non-thinking models, with strengths in agentic capabilities. Notably, K2 obtains 66.1 on Tau2-Bench, 76.5 on ACEBench (En), 65.8 on SWE-Bench Verified, and 47.3 on SWE-Bench Multilingual -- surpassing most open and closed-sourced baselines in non-thinking settings. It also exhibits strong capabilities in coding, mathematics, and reasoning tasks, with a score of 53.7 on LiveCodeBench v6, 49.5 on AIME 2025, 75.1 on GPQA-Diamond, and 27.1 on OJBench, all without extended thinking. These results position Kimi K2 as one of the most capable open-source large language models to date, particularly in software engineering and agentic tasks. We release our base and post-trained model checkpoints to facilitate future research and applications of agentic intelligence.

A multi-modal guardrail must effectively filter image content based on user-defined policies, identifying material that may be hateful, reinforce harmful stereotypes, contain explicit material, or spread misinformation. Deploying such guardrails in real-world applications, however, poses significant challenges. Users often require varied and highly customizable policies and typically cannot provide abundant examples for each custom policy. Consequently, an ideal guardrail should be scalable to the multiple policies and adaptable to evolving user standards with minimal retraining. Existing fine-tuning methods typically condition predictions on pre-defined policies, restricting their generalizability to new policies or necessitating extensive retraining to adapt. Conversely, training-free methods struggle with limited context lengths, making it difficult to incorporate all the policies comprehensively. To overcome these limitations, we propose to condition model's judgment on "precedents", which are the reasoning processes of prior data points similar to the given input. By leveraging precedents instead of fixed policies, our approach greatly enhances the flexibility and adaptability of the guardrail. In this paper, we introduce a critique-revise mechanism for collecting high-quality precedents and two strategies that utilize precedents for robust prediction. Experimental results demonstrate that our approach outperforms previous methods across both few-shot and full-dataset scenarios and exhibits superior generalization to novel policies.

The rapid advancement of Zero-Shot Text-to-Speech (ZS-TTS) technology has enabled high-fidelity voice synthesis from minimal audio cues, raising significant privacy and ethical concerns. Despite the threats to voice privacy, research to selectively remove the knowledge to replicate unwanted individual voices from pre-trained model parameters has not been explored. In this paper, we address the new challenge of speaker identity unlearning for ZS-TTS systems. To meet this goal, we propose the first machine unlearning frameworks for ZS-TTS, especially Teacher-Guided Unlearning (TGU), designed to ensure the model forgets designated speaker identities while retaining its ability to generate accurate speech for other speakers. Our proposed methods incorporate randomness to prevent consistent replication of forget speakers' voices, assuring unlearned identities remain untraceable. Additionally, we propose a new evaluation metric, speaker-Zero Retrain Forgetting (spk-ZRF). This assesses the model's ability to disregard prompts associated with forgotten speakers, effectively neutralizing its knowledge of these voices. The experiments conducted on the state-of-the-art model demonstrate that TGU prevents the model from replicating forget speakers' voices while maintaining high quality for other speakers. The demo is available at https://speechunlearn.github.io/

User-generated content (UGC) on social media platforms is vulnerable to incitements and manipulations, necessitating effective regulations. To address these challenges, those platforms often deploy automated content moderators tasked with evaluating the harmfulness of UGC and filtering out content that violates established guidelines. However, such moderation inevitably gives rise to strategic responses from users, who strive to express themselves within the confines of guidelines. Such phenomena call for a careful balance between: 1. ensuring freedom of speech -- by minimizing the restriction of expression; and 2. reducing social distortion -- measured by the total amount of content manipulation. We tackle the problem of optimizing this balance through the lens of mechanism design, aiming at optimizing the trade-off between minimizing social distortion and maximizing free speech. Although determining the optimal trade-off is NP-hard, we propose practical methods to approximate the optimal solution. Additionally, we provide generalization guarantees determining the amount of finite offline data required to approximate the optimal moderator effectively.

This perspective paper explores the future potential of "conversational intelligence" by examining how Large Language Models (LLMs) could be combined with GRAPHYP's network system to better understand human conversations and preferences. Using recent research and case studies, we propose a conceptual framework that could make AI rea-soning transparent and traceable, allowing humans to see and understand how AI reaches its conclusions. We present the conceptual perspective of "Matching Game Preferences through Dialogical Large Language Models (D-LLMs)," a proposed system that would allow multiple users to share their different preferences through structured conversations. This approach envisions personalizing LLMs by embedding individual user preferences directly into how the model makes decisions. The proposed D-LLM framework would require three main components: (1) reasoning processes that could analyze different search experiences and guide performance, (2) classification systems that would identify user preference patterns, and (3) dialogue approaches that could help humans resolve conflicting information. This perspective framework aims to create an interpretable AI system where users could examine, understand, and combine the different human preferences that influence AI responses, detected through GRAPHYP's search experience networks. The goal of this perspective is to envision AI systems that would not only provide answers but also show users how those answers were reached, making artificial intelligence more transparent and trustworthy for human decision-making.

Federated domain generalization has shown promising progress in image classification by enabling collaborative training across multiple clients without sharing raw data. However, its potential in the semantic segmentation of autonomous driving remains underexplored. In this paper, we propose FedS2R, the first one-shot federated domain generalization framework for synthetic-to-real semantic segmentation in autonomous driving. FedS2R comprises two components: an inconsistency-driven data augmentation strategy that generates images for unstable classes, and a multi-client knowledge distillation scheme with feature fusion that distills a global model from multiple client models. Experiments on five real-world datasets, Cityscapes, BDD100K, Mapillary, IDD, and ACDC, show that the global model significantly outperforms individual client models and is only 2 mIoU points behind the model trained with simultaneous access to all client data.

Due to the remarkable capabilities and growing impact of large language models (LLMs), they have been deeply integrated into many aspects of society. Thus, ensuring their alignment with human values and intentions has emerged as a critical challenge. This survey provides a comprehensive overview of practical alignment techniques, training protocols, and empirical findings in LLM alignment. We analyze the development of alignment methods across diverse paradigms, characterizing the fundamental trade-offs between core alignment objectives. Our analysis shows that while supervised fine-tuning enables basic instruction-following, preference-based methods offer more flexibility for aligning with nuanced human intent. We discuss state-of-the-art techniques, including Direct Preference Optimization (DPO), Constitutional AI, brain-inspired methods, and alignment uncertainty quantification (AUQ), highlighting their approaches to balancing quality and efficiency. We review existing evaluation frameworks and benchmarking datasets, emphasizing limitations such as reward misspecification, distributional robustness, and scalable oversight. We summarize strategies adopted by leading AI labs to illustrate the current state of practice. We conclude by outlining open problems in oversight, value pluralism, robustness, and continuous alignment. This survey aims to inform both researchers and practitioners navigating the evolving landscape of LLM alignment.