Training robotic manipulation policies traditionally requires numerous demonstrations and/or environmental rollouts. While recent Imitation Learning (IL) and Reinforcement Learning (RL) methods have reduced the number of required demonstrations, they still rely on expert knowledge to collect high-quality data, limiting scalability and accessibility. We propose Sketch-to-Skill, a novel framework that leverages human-drawn 2D sketch trajectories to bootstrap and guide RL for robotic manipulation. Our approach extends beyond previous sketch-based methods, which were primarily focused on imitation learning or policy conditioning, limited to specific trained tasks. Sketch-to-Skill employs a Sketch-to-3D Trajectory Generator that translates 2D sketches into 3D trajectories, which are then used to autonomously collect initial demonstrations. We utilize these sketch-generated demonstrations in two ways: to pre-train an initial policy through behavior cloning and to refine this policy through RL with guided exploration. Experimental results demonstrate that Sketch-to-Skill achieves ~96% of the performance of the baseline model that leverages teleoperated demonstration data, while exceeding the performance of a pure reinforcement learning policy by ~170%, only from sketch inputs. This makes robotic manipulation learning more accessible and potentially broadens its applications across various domains.

In cooperative multi-agent reinforcement learning (MARL), the permutation problem where the state space grows exponentially with the number of agents reduces sample efficiency. Additionally, many existing architectures struggle with scalability, relying on a fixed structure tied to a specific number of agents, limiting their applicability to environments with a variable number of entities. While approaches such as graph neural networks (GNNs) and self-attention mechanisms have progressed in addressing these challenges, they have significant limitations as dense GNNs and self-attention mechanisms incur high computational costs. To overcome these limitations, we propose a novel agent network and a non-linear mixing network that ensure permutation-equivariance and scalability, allowing them to generalize to environments with various numbers of agents. Our agent network significantly reduces computational complexity, and our scalable hypernetwork enables efficient weight generation for non-linear mixing. Additionally, we introduce curriculum learning to improve training efficiency. Experiments on SMACv2 and Google Research Football (GRF) demonstrate that our approach achieves superior learning performance compared to existing methods. By addressing both permutation-invariance and scalability in MARL, our work provides a more efficient and adaptable framework for cooperative MARL. Our code is available at https://github.com/funny-rl/SPECTra.

Implicit bias refers to automatic or spontaneous mental processes that shape perceptions, judgments, and behaviors based on social categories such as race, gender, or age [Greenwald and Lai, 2020, Payne and Gawronski, 2010]. Implicit biases often operate rapidly and with high efficiency, requiring minimal cognitive resources while influencing judgments through the automatic activation of stored information about social groups [Melnikoff and Bargh, 2018, Bargh and Williams, 2006, Fazio et al., 1986]. This efficiency in processing allows implicit biases to operate even under conditions of limited attention or cognitive load. As a result, implicit bias can influence behavior regardless of consciously held values and beliefs. Research demonstrates that implicit bias significantly relates to real-world outcomes, with researchers describing a potential role of implicit bias in domains such as employment [Agerström and Rooth, 2011], healthcare [FitzGerald and Hurst, 2017], and criminal justice [Spencer et al., 2016].

The key-value (KV) cache in autoregressive transformers presents a significant bottleneck during inference, which restricts the context length capabilities of large language models (LLMs). While previous work analyzes the fundamental space complexity barriers in standard attention mechanism [Haris and Onak, 2025], our work generalizes the space complexity barriers result to tensor attention version. Our theoretical contributions rely on a novel reduction from communication complexity and deduce the memory lower bound for tensor-structured attention mechanisms when $d = \Omega(\log n)$. In the low dimensional regime where $d = o(\log n)$, we analyze the theoretical bounds of the space complexity as well. Overall, our work provides a theoretical foundation for us to understand the compression-expressivity tradeoff in tensor attention mechanisms and offers more perspectives in developing more memory-efficient transformer architectures.

The raster-ordered image token sequence exhibits a significant Euclidean distance between index-adjacent tokens at line breaks, making it unsuitable for autoregressive generation. To address this issue, this paper proposes Direction-Aware Diagonal Autoregressive Image Generation (DAR) method, which generates image tokens following a diagonal scanning order. The proposed diagonal scanning order ensures that tokens with adjacent indices remain in close proximity while enabling causal attention to gather information from a broader range of directions. Additionally, two direction-aware modules: 4D-RoPE and direction embeddings are introduced, enhancing the model's capability to handle frequent changes in generation direction. To leverage the representational capacity of the image tokenizer, we use its codebook as the image token embeddings. We propose models of varying scales, ranging from 485M to 2.0B. On the 256$\times$256 ImageNet benchmark, our DAR-XL (2.0B) outperforms all previous autoregressive image generators, achieving a state-of-the-art FID score of 1.37.

This evolution indicates an expansion from industrial uses into diverse fields, including healthcare [61], [59]. The core functionalities of digital twins include an accurate mirroring of their physical counterparts, capturing all associated processes in a data-driven manner, maintaining a continuous connection that synchronizes with the real-time state of their physical twins, and simulating physical behavior for predictive analysis [85]. In the context of healthcare, a novel extension of this technology manifests in the form of Human Digital Twins (HDTs), designed to provide a comprehensive digital mirror of individual patients. HDTs not only represent physical attributes but also integrate dynamic changes across molecular, physiological, and behavioral dimensions. This advancement is aligned with a shift toward personalized healthcare (PH) paradigms, enabling tailored treatment strategies based on a patient's unique health profile, thereby enhancing preventive, diagnostic, and therapeutic processes in clinical settings [44], [50]. The personalization aspect of HDTs underscores their potential to revolutionize healthcare by facilitating precise and individualized treatment plans that optimize patient outcomes [72]. Although the potential of digital twins in healthcare has garnered much attention, practical applications remain newly developing, with critical literature highlighting that many implementations are still in exploratory stages [59]. Notably, institutions like the IEEE Computer Society and Gartner recognize this technology as a pivotal component in the ongoing evolution of healthcare systems that emphasize both precision and personalization [31], [89].

Neural Audio Synthesis (NAS) models offer interactive musical control over high-quality, expressive audio generators. While these models can operate in real-time, they often suffer from high latency, making them unsuitable for intimate musical interaction. The impact of architectural choices in deep learning models on audio latency remains largely unexplored in the NAS literature. In this work, we investigate the sources of latency and jitter typically found in interactive NAS models. We then apply this analysis to the task of timbre transfer using RAVE, a convolutional variational autoencoder for audio waveforms introduced by Caillon et al. in 2021. Finally, we present an iterative design approach for optimizing latency. This culminates with a model we call BRAVE (Bravely Realtime Audio Variational autoEncoder), which is low-latency and exhibits better pitch and loudness replication while showing timbre modification capabilities similar to RAVE. We implement it in a specialized inference framework for low-latency, real-time inference and present a proof-of-concept audio plugin compatible with audio signals from musical instruments. We expect the challenges and guidelines described in this document to support NAS researchers in designing models for low-latency inference from the ground up, enriching the landscape of possibilities for musicians.

The increasing amount of pressure related to water and energy shortages has increased the urgency of cultivating individual conservation behaviors. While the concept of nudging, i.e., providing usage-based feedback, has shown promise in encouraging conservation behaviors, its efficacy is often constrained by the lack of targeted and actionable content. This study investigates the impact of the use of large language models (LLMs) to provide tailored conservation suggestions for conservation intentions and their rationale. Through a randomized controlled trial with 1,515 university participants, we compare three virtual nudging scenarios: no nudging, traditional nudging with usage statistics, and LLM-powered nudging with usage statistics and personalized conservation suggestions. The results of statistical analyses and causal forest modeling reveal that nudging led to an increase in conservation intentions among 86.9%-98.0% of the participants. LLM-powered nudging achieved a maximum increase of 18.0% in conservation intentions, surpassing traditional nudging by 88.6%. Furthermore, structural equation modeling results reveal that exposure to LLM-powered nudges enhances self-efficacy and outcome expectations while diminishing dependence on social norms, thereby increasing intrinsic motivation to conserve.

Music-to-music-video generation is a challenging task due to the intrinsic differences between the music and video modalities. The advent of powerful text-to-video diffusion models has opened a promising pathway for music-video (MV) generation by first addressing the music-to-MV description task and subsequently leveraging these models for video generation. In this study, we focus on the MV description generation task and propose a comprehensive pipeline encompassing training data construction and multimodal model fine-tuning. We fine-tune existing pre-trained multimodal models on our newly constructed music-to-MV description dataset based on the Music4All dataset, which integrates both musical and visual information. Our experimental results demonstrate that music representations can be effectively mapped to textual domains, enabling the generation of meaningful MV description directly from music inputs. We also identify key components in the dataset construction pipeline that critically impact the quality of MV description and highlight specific musical attributes that warrant greater focus for improved MV description generation.

Despite the ever-growing importance of online moderation, there has been no large-scale study evaluating the effectiveness of alternative moderation strategies. This is largely due to the lack of appropriate datasets, and the difficulty of getting human discussants, moderators, and evaluators involved in multiple experiments. In this paper, we propose a methodology for leveraging synthetic experiments performed exclusively by Large Language Models (LLMs) to initially bypass the need for human participation in experiments involving online moderation. We evaluate six LLM moderation configurations; two currently used real-life moderation strategies (guidelines issued for human moderators for online moderation and real-life facilitation), two baseline strategies (guidelines elicited for LLM alignment work, and LLM moderation with minimal prompting) a baseline with no moderator at all, as well as our own proposed strategy inspired by a Reinforcement Learning (RL) formulation of the problem. We find that our own moderation strategy significantly outperforms established moderation guidelines, as well as out-of-the-box LLM moderation. We also find that smaller LLMs, with less intensive instruction-tuning, can create more varied discussions than larger models. In order to run these experiments, we create and release an efficient, purpose-built, open-source Python framework, dubbed "SynDisco" to easily simulate hundreds of discussions using LLM user-agents and moderators. Additionally, we release the Virtual Moderation Dataset (VMD), a large dataset of LLM-generated and LLM-annotated discussions, generated by three families of open-source LLMs accompanied by an exploratory analysis of the dataset.