Context: Large language model (LLM) agents are increasingly used as software and data-engineering assistants, yet evidence about locally deployable open-weight agents remains limited. Existing evaluations often emphasize textual responses or isolated code generation rather than the validity of complete engineering arti...
Jorge Garc\'ia-Carrasco, Javier Sanchis, Alejandro Reina-Reina et al.· 0 citations
Embodied coding agents can combine modular robot skills with frozen end-to-end policies, yet effective composition requires anticipating which policy family will succeed in the current physical state. We present RoboAware, which builds on coding agents' skill orchestration by learning only a state-conditioned responsib...
Bohan Zhou, Xingbei Chen, Emily Huang et al.· 0 citations
Causal video diffusion models generate video autoregressively, which suits streaming, interactive, and long-video generation. Under standard training, however, they often yield lower generation quality than bidirectional models of the same size. Many existing approaches address this gap by initializing from or distilli...
Bowen Zheng, Zhiguang Liu, Jiarong Ou et al.· 0 citations
We present GROB, a multi-agent architecture for investigating candidate autonomous-agent activity through public Internet traces when privileged telemetry is unavailable. The system performs controlled, read-only collection of public traces and preserves selected observations for later resolution. In a frozen September...
Chiara Bonfanti, Cataldo Basile· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Prototypes in classification models are almost always vectors, and a vector has no readable form. This paper asks what happens when a prototype is an image. Documents give the question a natural form, because a document can be rendered as a multi-channel image in which every token becomes a pixel, so a class representa...
Mohammad Zare, Pirooz Shamsinejadbabaki· 0 citations
AI research progress can be viewed as the interaction between two processes: benchmark creation and method discovery. Historically, both were driven by human intelligence. However, recent advances in AI have accelerated automated method discovery, while automated benchmark creation has received comparatively less atten...
Kislay Aditya Oj, Nidhi Jain, Sri Surya Varma Datla et al.· 0 citations
Unified atomistic modeling has the potential to accelerate discovery in chemistry, materials science, and biology by bridging data-rich chemical domains and data-scarce biological contexts. However, existing generative approaches to atomistic modeling remain highly specialized to scientific disciplines (chemistry vs. b...
Miruna Cretu, Alex Abrudan, Antonia Panescu et al.· 0 citations
Large language models (LLMs) are increasingly deployed as coding agents that edit files, run builds and tests, inspect execution results, and repair software iteratively. Embedded firmware is a demanding target because correctness depends on closed-loop behavior under sensing, timing, and safety constraints, not only o...
Jorge Garc\'ia-Carrasco, Sergio Garc\'ia-Carrasco, Alejandro Mat\'e et al.· 0 citations
Multimodal brain tumor segmentation typically leverages multiple MRI modalities, yet incomplete modality acquisition is common in clinical practice due to protocol heterogeneity and scan failures. Although recent methods maintain segmentation accuracy under missing modality conditions, they frequently overlook predicti...
Sol Lee, Hyunji Kim, Sungrae Hong et al.· 0 citations
Vision-Language-Action (VLA) models have emerged as a prominent framework for complex robotic manipulation, building on the strong semantic understanding of pretrained Vision-Language Models (VLMs). However, such VLM backbones offer insufficient physical dynamics priors, which limits the generalization capabilities of...
Shuang Luo, Yilun Kong, Yunpeng Qing et al.· 0 citations
Symbolic regression combines structural search with numerical fitting, but aggregate fit scores do not describe how the remaining error varies across inputs. We introduce RISR, a residual-informed method that uses these error patterns to guide formula discovery and learn which corrections are worth fitting. A residual...
Haobo Li, Wenshuo Zhang, Wenxiao Zhao et al.· 0 citations
AI-generated image detectors are commonly trained on fixed generator domains and become difficult to maintain as new generative models emerge. Continual adaptation is challenging because replaying historical generated images is costly, whereas updating shared parameters with limited current-domain data can overwrite pr...
Zhiheng Peng, Wenwei Jin, Yangshi Ge et al.· 0 citations
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
