This paper presents HiMA-Ecom, a hierarchical multi-agent benchmark for e-commerce assistants with 22.8K instances, and presents HiMA-R1, a hierarchical multi-agent benchmark for e-commerce assistants, pairing agent-specific supervised fine-tuning data with system-level supervision for end-to-end multi-agent reinforcem...
Jun-Xing Hu, Ai Han, Haolan Zhan et al.· 8 citations· ⚡1
Estimation error in machine learning prognostic models can propagate into poor maintenance decisions. We study a data-driven predictive maintenance problem coupling health-condition estimation with a joint ordering-replacement model. We show that the conventional Estimate-Then-Optimize (ETO) approach yields inconsisten...
Identifying the effects of causes and causes of effects is vital in virtually every scientific field. Often, however, the needed probabilities may not be fully identifiable from the available data sources. This paper shows how approximate identifiability is still possible for several probabilities of causation. We term...
Ang Li, Scott Mueller, Xin Shu et al.· 0 citations
Novel view synthesis and 3D reconstruction have advanced rapidly with radiance fields and splatting, yet their memory and computational demands limit their use in resource-constrained settings. We introduce Hexels: novel planar hexagonal surface elements with a first-order spatial color field for efficient 3D scene and...
Prakhar Kaushik, Soumava Paul, Alan Yuille· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Vision-Language-Action (VLA) models have made substantial progress in robotic manipulation, but their generalization remains constrained by the diversity and coverage of action-labeled robot demonstrations. Human videos provide much broader behavioral and environmental experience, while learning from them faces a funda...
Chaehyun Kim, Chi-Pin Huang, Jisoo Kim et al.· 0 citations
Relations compose through the entity they share - Alice is Bob's mother and Bob is Carol's father, so Alice is Carol's grandmother - and the order matters, since a father's mother is not a mother's father; verifying a composed relation means closing the loop. We show that if each entity's coordinate frame may be rotate...
Scientific discovery often begins with an unexpected observation that prompts a new research question. In a world with altered physical laws, can large language models (LLMs) notice unexpected behavior, such as heavier objects falling more slowly, and discover the law through experiments without being told what to inve...
Zhen Yang, Wen Wang, Xander Xu et al.· 0 citations
Weight decay and explicit weight-norm constraints improve optimizer performance in language model pretraining, yet a unified understanding of why such control helps and how much is needed remains incomplete. We analyze norm control in Muon over the entire training trajectory using the \emph{accumulated effective learni...
Chain-of-thought reasoning has substantially advanced video understanding in multimodal large language models (MLLMs). However, language-based reasoning traces do not provide a reliable mechanism for models to revisit relevant visual evidence, leading to visual forgetting and impairing their ability to reason over vide...
Shi-Long Li, Xing-Yuan Bu, Hao Shi et al.· 0 citations
This protocol tests how model answers respond to local changes in event class, comparing matched same-class and different-class replacements of a queried event.
Yu-Nuo Wang, Mao-Yuan Chen, Yuan-Jin Huang et al.· 0 citations
Developing on-device image models requires considering practical user needs, task types and device resource constraints. However, existing benchmarks provide limited guidance on identifying capability gaps between on-device models and server-side models. We introduce MoI-Bench, a benchmark grounded in mobile user needs...
Kailai Feng, Haoxiang Rao, Yuxiang Wei et al.· 0 citations
Traffic forecasting requires modeling complex temporal dynamics and the spatial dependencies imposed by road topology. Supervised graph-based models achieve strong performance, but are often trained for a particular dataset and sensor graph, making deployment to new or evolving networks costly. Prior-Data Fitted Networ...
Joseph Natter, Long Vu, Yi-Fan Zhang et al.· 0 citations
