The embedding of Large Language Models (LLMs) into autonomous agents is a rapidly developing field which enables dynamic, configurable behaviours without the need for extensive domain-specific training. In our previous work, we introduced SANDMAN, a Deceptive Agent architecture leveraging the Five-Factor OCEAN personality model, demonstrating that personality induction significantly influences agent task planning. Building on these findings, this study presents a novel method for measuring and evaluating how induced personality traits affect task selection processes - specifically planning, scheduling, and decision-making - in LLM-based agents. Our results reveal distinct task-selection patterns aligned with induced OCEAN attributes, underscoring the feasibility of designing highly plausible Deceptive Agents for proactive cyber defense strategies.

The subjective evaluation of early stage engineering designs, such as conceptual sketches, traditionally relies on human experts. However, expert evaluations are time-consuming, expensive, and sometimes inconsistent. Recent advances in vision-language models (VLMs) offer the potential to automate design assessments, but it is crucial to ensure that these AI ``judges'' perform on par with human experts. However, no existing framework assesses expert equivalence. This paper introduces a rigorous statistical framework to determine whether an AI judge's ratings match those of human experts. We apply this framework in a case study evaluating four VLM-based judges on key design metrics (uniqueness, creativity, usefulness, and drawing quality). These AI judges employ various in-context learning (ICL) techniques, including uni- vs. multimodal prompts and inference-time reasoning. The same statistical framework is used to assess three trained novices for expert-equivalence. Results show that the top-performing AI judge, using text- and image-based ICL with reasoning, achieves expert-level agreement for uniqueness and drawing quality and outperforms or matches trained novices across all metrics. In 6/6 runs for both uniqueness and creativity, and 5/6 runs for both drawing quality and usefulness, its agreement with experts meets or exceeds that of the majority of trained novices. These findings suggest that reasoning-supported VLM models can achieve human-expert equivalence in design evaluation. This has implications for scaling design evaluation in education and practice, and provides a general statistical framework for validating AI judges in other domains requiring subjective content evaluation.

We present the challenging task of automatically creating a high-level Wikipedia-style article that aggregates information from multiple diverse videos about real-world events, such as natural disasters or political elections. Videos are intuitive sources for retrieval-augmented generation (RAG), but most contemporary RAG workflows focus heavily on text and existing methods for video-based summarization focus on low-level scene understanding rather than high-level event semantics. To close this gap, we introduce WikiVideo, a benchmark consisting of expert-written articles and densely annotated videos that provide evidence for articles' claims, facilitating the integration of video into RAG pipelines and enabling the creation of in-depth content that is grounded in multimodal sources. We further propose Collaborative Article Generation (CAG), a novel interactive method for article creation from multiple videos. CAG leverages an iterative interaction between an r1-style reasoning model and a VideoLLM to draw higher level inferences about the target event than is possible with VideoLLMs alone, which fixate on low-level visual features. We benchmark state-of-the-art VideoLLMs and CAG in both oracle retrieval and RAG settings and find that CAG consistently outperforms alternative methods, while suggesting intriguing avenues for future work.

Adapting pre-trained foundation models for diverse downstream tasks is a core practice in artificial intelligence. However, the wide range of tasks and high computational costs make full fine-tuning impractical. To overcome this, parameter-efficient fine-tuning (PEFT) methods like LoRA have emerged and are becoming a growing research focus. Despite the success of these methods, they are primarily designed for linear layers, focusing on two-dimensional matrices while largely ignoring higher-dimensional parameter spaces like convolutional kernels. Moreover, directly applying these methods to higher-dimensional parameter spaces often disrupts their structural relationships. Given the rapid advancements in matrix-based PEFT methods, rather than designing a specialized strategy, we propose a generalization that extends matrix-based PEFT methods to higher-dimensional parameter spaces without compromising their structural properties. Specifically, we treat parameters as elements of a Lie group, with updates modeled as perturbations in the corresponding Lie algebra. These perturbations are mapped back to the Lie group through the exponential map, ensuring smooth, consistent updates that preserve the inherent structure of the parameter space. Extensive experiments on computer vision and natural language processing validate the effectiveness and versatility of our approach, demonstrating clear improvements over existing methods.

Multimodal Large Language Models (MLLMs) suffer from high computational costs due to their massive size and the large number of visual tokens. In this paper, we investigate layer-wise redundancy in MLLMs by introducing a novel metric, Layer Contribution (LC), which quantifies the impact of a layer's transformations on visual and text tokens, respectively. The calculation of LC involves measuring the divergence in model output that results from removing the layer's transformations on the specified tokens. Our pilot experiment reveals that many layers of MLLMs exhibit minimal contribution during the processing of visual tokens. Motivated by this observation, we propose ShortV, a training-free method that leverages LC to identify ineffective layers, and freezes visual token updates in these layers. Experiments show that ShortV can freeze visual token in approximately 60% of the MLLM layers, thereby dramatically reducing computational costs related to updating visual tokens. F or example, it achieves a 50% reduction in FLOPs on LLaVA-NeXT-13B while maintaining superior performance. The code will be publicly available at https://github.com/icip-cas/ShortV.

--This study focuses on Embodied Complex-Question Answering task, which means the embodied robot need to understand human questions with intricate structures and abstract semantics. The core of this task lies in making appropriate plans based on the perception of the visual environment. Existing methods often generate plans in a once-for-all manner, i.e., one-step planning . Such approach rely on large models, without sufficient understanding of the environment. Considering multi-step planning, the framework for formulating plans in a sequential manner is proposed in this paper . T o ensure the ability of our framework to tackle complex questions, we create a structured semantic space, where hierarchical visual perception and chain expression of the question essence can achieve iterative interaction. This space makes sequential task planning possible. Within the framework, we first parse human natural language based on a visual hierarchical scene graph, which can clarify the intention of the question. Then, we incorporate external rules to make a plan for current step, weakening the reliance on large models. Every plan is generated based on feedback from visual perception, with multiple rounds of interaction until an answer is obtained. This approach enables continuous feedback and adjustment, allowing the robot to optimize its action strategy. T o test our framework, we contribute a new dataset with more complex questions. Experimental results demonstrate that our approach performs excellently and stably on complex tasks. And also, the feasibility of our approach in real-world scenarios has been established, indicating its practical applicability. Index T erms --Embodied complex-question answering, task planning, language parsing, structured semantic space. HE development of versatile embodied agents capable of understanding natural language commands in indoor environments and executing various tasks through visual interaction has been a long-standing goal.

Unlearnable data (ULD) has emerged as an innovative defense technique to prevent machine learning models from learning meaningful patterns from specific data, thus protecting data privacy and security. By introducing perturbations to the training data, ULD degrades model performance, making it difficult for unauthorized models to extract useful representations. Despite the growing significance of ULD, existing surveys predominantly focus on related fields, such as adversarial attacks and machine unlearning, with little attention given to ULD as an independent area of study. This survey fills that gap by offering a comprehensive review of ULD, examining unlearnable data generation methods, public benchmarks, evaluation metrics, theoretical foundations and practical applications. We compare and contrast different ULD approaches, analyzing their strengths, limitations, and trade-offs related to unlearnability, imperceptibility, efficiency and robustness. Moreover, we discuss key challenges, such as balancing perturbation imperceptibility with model degradation and the computational complexity of ULD generation. Finally, we highlight promising future research directions to advance the effectiveness and applicability of ULD, underscoring its potential to become a crucial tool in the evolving landscape of data protection in machine learning.

Large Audio Language Models (LALMs) have significantly advanced audio understanding but introduce critical security risks, particularly through audio jailbreaks. While prior work has focused on English-centric attacks, we expose a far more severe vulnerability: adversarial multilingual and multi-accent audio jailbreaks, where linguistic and acoustic variations dramatically amplify attack success. In this paper, we introduce Multi-AudioJail, the first systematic framework to exploit these vulnerabilities through (1) a novel dataset of adversarially perturbed multilingual/multi-accent audio jailbreaking prompts, and (2) a hierarchical evaluation pipeline revealing that how acoustic perturbations (e.g., reverberation, echo, and whisper effects) interacts with cross-lingual phonetics to cause jailbreak success rates (JSRs) to surge by up to +57.25 percentage points (e.g., reverberated Kenyan-accented attack on MERaLiON). Crucially, our work further reveals that multimodal LLMs are inherently more vulnerable than unimodal systems: attackers need only exploit the weakest link (e.g., non-English audio inputs) to compromise the entire model, which we empirically show by multilingual audio-only attacks achieving 3.1x higher success rates than text-only attacks. We plan to release our dataset to spur research into cross-modal defenses, urging the community to address this expanding attack surface in multimodality as LALMs evolve.

Autonomous navigation is usually trained offline in diverse scenarios and fine-tuned online subject to real-world experiences. However, the real world is dynamic and changeable, and many environmental encounters/effects are not accounted for in real-time due to difficulties in describing them within offline training data or hard to describe even in online scenarios. However, we know that the human operator can describe these dynamic environmental encounters through natural language, adding semantic context. The research is to deploy Large Language Models (LLMs) to perform real-time contextual code adjustment to autonomous navigation. The challenge not evaluated in literature is what LLMs are appropriate and where should these computationally heavy algorithms sit in the computation-communication edge-cloud computing architectures. In this paper, we evaluate how different LLMs can adjust both the navigation map parameters dynamically (e.g., contour map shaping) and also derive navigation task instruction sets. We then evaluate which LLMs are most suitable and where they should sit in future edge-cloud of 6G telecommunication architectures.

To fully understand the behavior of a large language model (LLM) requires our understanding of its input space. If this input space differs from our assumption, our understanding of and conclusions about the LLM is likely flawed, regardless of its architecture. Here, we elucidate the structure of the token embeddings, the input domain for LLMs, both empirically and theoretically. We present a generalized and statistically testable model where the neighborhood of each token splits into well-defined signal and noise dimensions. This model is based on a generalization of a manifold called a fiber bundle, so we denote our hypothesis test as the ``fiber bundle null.'' Failing to reject the null is uninformative, but rejecting it at a specific token indicates that token has a statistically significant local structure, and so is of interest to us. By running our test over several open-source LLMs, each with unique token embeddings, we find that the null is frequently rejected, and so the token subspace is provably not a fiber bundle and hence also not a manifold. As a consequence of our findings, when an LLM is presented with two semantically equivalent prompts, and if one prompt contains a token implicated by our test, that prompt will likely exhibit more output variability proportional to the local signal dimension of the token.