Vision-Language Models (VLMs) continue to struggle to make morally salient judgments in multimodal and socially ambiguous contexts. Prior works typically rely on binary or pairwise supervision, which often fail to capture the continuous and pluralistic nature of human moral reasoning. We present MM-SCALE (Multimodal Moral Scale), a large-scale dataset for aligning VLMs with human moral preferences through 5-point scalar ratings and explicit modality grounding. Each image-scenario pair is annotated with moral acceptability scores and grounded reasoning labels by humans using an interface we tailored for data collection, enabling listwise preference optimization over ranked scenario sets. By moving from discrete to scalar supervision, our framework provides richer alignment signals and finer calibration of multimodal moral reasoning. Experiments show that VLMs fine-tuned on MM-SCALE achieve higher ranking fidelity and more stable safety calibration than those trained with binary signals.
We introduce FlexMoGen, a novel framework for flexible human motion synthesis conditioned on both natural language descriptions and motion style references. Text prompts are effective at defining semantic content, but they are often limited in capturing fine-grained style details such as timing, limb articulation, and expressive dynamics. A style example clip supplements the text by conveying these nuanced motion characteristics directly, enabling the model to preserve high-level intent while reproducing the desired stylistic traits. Given a text prompt and a style example clip, FlexMoGen generates high-quality motions that preserve semantic content while faithfully reflecting the target style, offering users greater control over the animation generation process. Unlike prior methods that rely on discrete style labels and do not generalize to long or multi-style generation, FlexMoGen learns a variational style encoder without style supervision and supports long, time-varying, multi-style synthesis. Our framework jointly pre-trains the style encoder and a text-to-motion latent diffusion model within a unified architecture, modulating motion style through a lightweight adaptation module. It integrates an efficient relative positional encoding scheme and is trained on both stylized and non-stylized datasets, enabling strong generalization to unseen text-style combinations. Experiments show that FlexMoGen achieves the best balance between content fidelity and style reflection.
In this paper, we consider retargeting a tracked facial performance to other people or virtual characters. We utilize the same rig framework for both tracking and animation to remove the difficulties associated with retargeting the semantics of one framework to another. Our carefully designed set of Simon-Says expressions and regularizers is used to calibrate each rig to the motion signatures of the relevant performer or target. Although a uniform set of Simon-Says expressions can likely be used for all person-to-person retargeting, we argue that person-to-virtual-character retargeting benefits from an expression set that captures the distinct motion signature of the virtual character rig. The Simon-Says calibrated rigs tend to produce the desired expressions when exercising animation controls. Unfortunately, these well-calibrated rigs still lead to undesirable controls when tracking a performance, even though they generally produce acceptable geometry reconstructions. Thus, we propose a fine-tuning approach that modifies the rig used by the tracker to promote the output of more semantically meaningful animation controls, facilitating high efficacy retargeting. To better address real-world scenarios, the fine-tuning relies on implicit differentiation so that the tracker can be treated as a potentially non-differentiable black box. Experiments demonstrate the benefits of our calibration methods on high-fidelity expressive performance retargeting for different capture conditions, trackers, and rig frameworks.
FloraWear is a wearable living interface where people can experience close relationships with plants by caring for and wearing them. While plants can have positive effects on both mental and physical well-being, we are increasingly losing our connection to plants due to industrialization and urbanization. To build a stronger relationship with plants, we present FloraWear-a DIY, wearable living interface that facilitates an intimate connection with plants. We discuss how the design of this living interface evolved through an iterative process based on feedback from users. By interacting with FloraWear, people can practice cohabitation with plants and experience becoming a more-than-human assemblage.
The standard dual-numbers construction works well for forward-mode automatic differentiation (AD) and is attractive due to its simplicity; recently, it also has been adapted to reverse-mode AD, but practical performance, especially on array programs, leaves a lot to be desired. In this paper we introduce first-class support for multidimensional arrays in dual-numbers reverse-mode AD with little to no performance overhead. The algorithm consists of three loosely-coupled components: a semantics-preserving vectorisation code transformation (the bulk-operation transform or BOT), a fairly straightforward lifting of the basic dual-numbers reverse AD algorithm to a mostly first-order array language, and symbolic interpretation to achieve an end-to-end compilation pipeline. Unfortunately, we lose some of the nice generalisable aspects of dual-numbers AD in the process, most importantly support for higher-order code. We do support some higher-order array combinators, but only a carefully-chosen set: 'build' (elementwise array construction), 'gather' and 'scatter'. In return, the BOT can eliminate the essential (for AD) higher-orderness of the input program, meaning that AD gets essentially presented with a first-order program. This allows the naive trick of lifting dual numbers to "dual arrays" to work without much modification.
