Simulating economic responses at society scale requires agents whose decisions reflect household circumstances and the effects of earlier actions. We introduce S$^2$-MAS, a society-scale multi-agent simulation framework built on 500 million synthetic household personas grounded in real-survey data. Its Genese engine se...
Yang Li, Yi-Ke Wang, Diane Wan et al.· 0 citations
Large language models (LLMs) are increasingly used as judgment assistants and as stand-in participants in psychology experiments, yet little is known about how much their probability estimates move in response to a single new piece of information. We pair premise-hypothesis items from $\delta$-SNLI with one strengthene...
Learned barrier certificates provide a principled mechanism for establishing safety of stochastic systems, but their validity may deteriorate during deployment when the underlying dynamics differ from those used for training. We propose an anytime-valid runtime monitor that audits a learned barrier certificate using ob...
Zhi-Peng Cao, Tao-Ran Wu, Wei-Ru Cui et al.· 0 citations
World2HOSI is introduced, a multi-expert orchestration harness that generates continuous HOSI data from 3D Gaussian Splatting scenes and natural language instructions and achieves the best task completion and interaction quality on the evaluated HOSI tasks, while generating more diverse data.
Jiu-Shu Li, Hao-Ran Wang, Yu-Meng Liu et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Feed-forward 3D Gaussian Splatting (FF3DGS) reconstructs 3D scenes from images in a single forward pass, making it well-suited to applications that must operate within limited resource budgets. To further improve its practicality, recent budget-controllable FF3DGS methods allow the number of Gaussians to be adjusted at...
Injae Kim, Minseok Joo, Jihwan Park et al.· 0 citations
Large language models are expected to estimate their own uncertainty, with confidence signals used to guide retrieval, adaptive compute allocation, routing, and selective abstention. We investigate whether confidence signals measured at different temporal stages of problem solving encode distinct forms of epistemic inf...
Sahil Kale· Proceedings of the 10th Wide...· 0 citations
Vision-language-action (VLA) models transfer knowledge from large-scale pretraining into robot control, but their manipulation performance remains sensitive to changes in observation conditions, which recent work addresses by fine-tuning the visual module on target-domain data. However, it remains unclear how such adap...
Borui Xu, Han Chen, Bingsheng He et al.· 0 citations
In object goal navigation (ObjectNav), an embodied agent must find a target object (e.g., "find a bed") in a previously unseen environment, relying on spatial commonsense such as object co-occurrence. Large Language Models (LLMs) encode this commonsense, but deploying them on robots exposes a trade-off between reasonin...
Pengying Wu, Zhejia Wen, Kang Ding et al.· 0 citations
Deep neural networks often fail at small-sample regression, collapsing to low-variance predictions that miss individual differences. Here, we introduce a pairwise comparison framework that reframes regression as aggregated relative rankings. This method improves data efficiency across model architectures and dataset si...
Robert Bain, Marjan Rashidi, Elizabeth Chrastil· 0 citations
Watermarking has emerged as a key tool for identifying text generated by large language models (LLMs), with current schemes embedding statistical signals into the generation process to enable later detection. In this work, we identify a shared weakness across a broad class of popular LLM watermarking methods, including...
Romina Omidi, Nima Naderloui, Yuan Hong et al.· 0 citations
This work ablate a production pipeline that turns conference speech into question-answer pairs, and finds that more than a third of its pairs carry knowledge that neither of two frontier models produces on its own.
Temperature scaling is typically applied as a post-hoc transformation of model probabilities. In posterior-induced flow language models, this creates two mismatches. First, posterior tempering implicitly changes both the endpoint distribution and the distribution of intermediate noisy states, while the denoiser remains...
