Generating realistic and coordinated 3D human motion for multiple individuals within complex environments remains a significant challenge. Existing text-to-motion methods are often ``blind'' to the physical scene, leading to implausible motions, while scene-conditioned (HSI) approaches demand cumbersome full 3D data and largely neglect multi-person dynamics. To address these limitations, we introduce the VL2Motion paradigm and its embodiment, MMG-VL, a hierarchical framework that generates coordinated multi-person motions from the most accessible inputs: a single 2D image and natural language. MMG-VL first employs a Scene-Aware Intent Planner (SAIP) to interpret the visual context and decompose the user's command into a set of spatially-grounded, multi-person action blueprints. Subsequently, a Coordinated Motion Synthesizer (CMS) translates these blueprints into high-fidelity 3D motion sequences. The synergy between these stages is driven by two novel loss functions: a Spatial-Semantic Grounding Loss to ensure the planner's output is grounded in visual reality, and a Coordinated Environmental Realism Loss that enforces physical constraints and coherent group dynamics during synthesis. To facilitate this research, we introduce HumanVL, the first large-scale dataset featuring multi-person activities in multi-room scenes, providing aligned images, text, blueprints, 3D motions, and scene geometry. Extensive experiments demonstrate that MMG-VL significantly outperforms existing methods in generating spatially coherent, physically realistic, and coordinated multi-person motions, paving the way for more scalable and intuitive creation of dynamic virtual worlds.

Fusing hyperspectral image (HSI) and multispectral image (MSI) is essential to merge HSI’s spectral richness with MSI’s spatial detail. This paper introduces TS-DANet, a novel two-part network for HSI-MSI fusion designed to address the limitations of current methods in model prior utilization and spectral-spatial feature extraction. In the initial part, we use truncated singular value decomposition (TSVD) interaction to extract spectral priors from low-resolution HSI (LR-HSI) and spatial sparsity priors from high-resolution MSI (HR-MSI), integrating these through a physics-based optimization for image fusion. We also incorporate a dual-attention mechanism, featuring a dynamic spectral attention module for detailed spectral features and a multi-scale spatial attention module for detailed spatial features. The second part employs a dynamic residual optimization module to further refine spatial and spectral information. Extensive experiments on three remote sensing datasets show that TS-DANet outperforms existing state-of-the-art algorithms in fusion performance. The code will be available at https://github.com.

Object detection models, while achieving greater performance, often suffer from recurring errors such as misclassifications or missed detections. Existing explainable AI (XAI) tools primarily offer static, observation-based explanations and rarely support interactive correction or retraining, especially for non-expert users. To bridge this gap, we introduce CorrectMe, an interactive framework that integrates human-in-the-loop correction and explanation into object detection workflows. CorrectMe empowers users to iteratively explore, interpret, and rectify model errors through a unified interface featuring semantic embedding visualizations, saliency-based explanations, and natural language rationales. Users can revise predictions and incrementally retrain the model, streamlining the refinement process through lightweight updates rather than full-scale retraining or annotation. Through application scenarios and user studies, we demonstrate that CorrectMe enables more strategic corrections, improves model understanding, and lowers the barrier to practical refinement of object detection models.

LLM-as-a-Judge uses a large language model (LLM) to select the best response from a set of candidates for a given question. LLM-as-a-Judge has many applications such as LLM-powered search, reinforcement learning with AI feedback (RLAIF), and tool selection. In this work, we propose JudgeDeceiver, an optimization-based prompt injection attack to LLM-as-a-Judge. JudgeDeceiver injects a carefully crafted sequence into an attacker-controlled candidate response such that LLM-as-a-Judge selects the candidate response for an attacker-chosen question no matter what other candidate responses are. Specifically, we formulate finding such sequence as an optimization problem and propose a gradient based method to approximately solve it. Our extensive evaluation shows that JudgeDeceive is highly effective, and is much more effective than existing prompt injection attacks that manually craft the injected sequences and jailbreak attacks when extended to our problem. We also show the effectiveness of JudgeDeceiver in three case studies, i.e., LLM-powered search, RLAIF, and tool selection. Moreover, we consider defenses including known-answer detection, perplexity detection, and perplexity windowed detection. Our results show these defenses are insufficient, highlighting the urgent need for developing new defense strategies.

Multimodal Large Language Models (MLLMs) have gained significant attention recently, showing remarkable potential in artificial general intelligence. However, assessing the utility of MLLMs presents considerable challenges, primarily due to the absence multimodal benchmarks that align with human preferences. Drawing inspiration from the concept of LLM-as-a-Judge within LLMs, this paper introduces a novel benchmark, termed MLLM-as-a-Judge, to assess the ability of MLLMs in assisting judges across diverse modalities, encompassing three distinct tasks: Scoring Evaluation, Pair Comparison, and Batch Ranking. Our study reveals that, while MLLMs demonstrate remarkable human-like discernment in Pair Comparisons, there is a significant divergence from human preferences in Scoring Evaluation and Batch Ranking tasks. Furthermore, a closer examination reveals persistent challenges in the evaluative capacities of LLMs, including diverse biases, hallucinatory responses, and inconsistencies in judgment, even in advanced models such as GPT-4V. These findings emphasize the pressing need for enhancements and further research efforts to be undertaken before regarding MLLMs as fully reliable evaluators. In light of this, we advocate for additional efforts dedicated to supporting the continuous development within the domain of MLLM functioning as judges. The code and dataset are publicly available at our project homepage: https://mllm-judge.github.io/.

A city’s history and culture studies involves understanding the literary works and historical events that have shaped the city’s identity. Increased availability of quantitative historical data has provided new opportunities. Taking Nanjing as an example, this paper proposes EmoGeoCity, a visual analytics system to study a city’s cultural and historical evolution, through the use of digital humanities methods and emotional geography. The system incorporates sentiment analysis into historical research to quantify the emotional content of works and synthesize an overall emotion trend within a specific location. A dynamic emotional map, integrating locations, works, and events, enables a macroscopic observation of city emotions over time. An emotional polyline is designed to provide a microscopic interpretation of the emotion trend of a single location. Exploration through the system reveals the evolution of the city from an emotional geographic perspective, which gives insights for humanities researchers studying a city’s history and literature, as well as for the general public interested in gaining knowledge on historical sites. Case and user studies illustrate the effectiveness and usability of our system.