Recent video super-resolution (VSR) models achieve efficient one-step generation through diffusion distillation. However, high-resolution inference remains costly, and distilled models are difficult to align with human preferences. These challenges call for improvements in both model architecture and training strategy....
Ru-Chang Yao, Shi Guo, Junhao Zhuang et al.· 1 citation
Thought templates, skill libraries, agent memories and caches turn many reasoning steps into one. We call this reasoning contraction. A contracted memory saves reasoning steps and errors until its facts change, then quietly answers wrong. Most systems trust memories by counting successes and failures. We prove that suc...
Jiang-Hong Zhou, Hao-Yan Rong, Chen-Ying Lin et al.· 0 citations
Safety verification of a Markov decision process (MDP) asks whether the probabilities of reaching several failure states jointly lie in a convex safe region under every scheduler. Watanabe and Unno (2026) prove safety by refining an outer approximation of the failure probabilities, where each query bounds a nonnegative...
Han Bao, Shinsaku Sakaue, Kazuki Watanabe· 0 citations
While it is known that quantization of large language models (LLMs) reduces memory usage via lower-bit weights, studies quantifying the resulting impact on energy usage and carbon intensity are scarce. We present the first unified evaluation of weight-only quantization strategies for LLM inference across varying input/...
P. Basta· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
World action models (WAMs) are a category of policy models that ex- plicitly predict both actions and future world states. They have been shown to outperform action-only models across various robotic manipulation tasks. How- ever, representing the future with full-frame video prediction can be computation- ally expensi...
Qin-Xi Yu, Wen-Zhou Ding, Gloria X. Wang et al.· 0 citations
With recent developments in Artificial Intelligence (AI), the adoption of distributed learning paradigms such as Federated Learning (FL) has emerged. In simple terms, FL enables multiple entities to collaboratively train AI models without sharing local data. The FL paradigm is particularly valuable in privacy-sensitive...
Maria Ivan, O. Ermis, Ruxandra F. Olimid· 0 citations
Evaluating VLA policies on real robots is costly, time-consuming, and difficult to reproduce, making real-to-sim simulation essential for scalable evaluation. While 3D Gaussian Splatting (3DGS) enables rapid real-to-sim scene generation, the reconstruction quality required for reliable policy evaluation remains unquant...
Hiroki Nishizawa, Takehiko Ohkawa, Nicola Scianca et al.· 0 citations
Event logs are ubiquitous across real-world domains, including business processes, manufacturing workflows, healthcare, and many other operational systems. Yet event logs can differ substantially in their event semantics, label spaces, interaction patterns, and temporal scales, making it difficult to build a single fou...
F. Spaeh, Sean Jaffe, Shan-Dian Zhe et al.· 0 citations
Financial Artificial Intelligence (AI) governance and model risk management (MRM) emphasize independent validation, transparency, and effective challenge of AI-generated computations. Text-to-SQL translates natural-language questions into Structured Query Language (SQL), but queries that agree on one database can still...
Piyush Jha, Cruise Song, Zhengyu Li et al.· 0 citations
Social media platforms generate vast volumes of user-generated content that often obscure meaningful discourse, a phenomenon conceptualized as social noise. While existing misinformation detection methods primarily focus on factual verification, they largely overlook the role of social noise in amplifying misinformatio...
Language models are often evaluated alone but increasingly deployed together, routed between, made to debate, ensembled, or collaboratively trained. For a model inside a system, what matters most is not how well it performs on its own, but how much the system gains from its presence. We call this a model's compositiona...
Shangbin Feng, Yulia Tsvetkov, Jan Kautz et al.· 0 citations
Language model (LM) agents can fail for different reasons, requiring different explanations and interventions. We study how state beliefs, action values, and action preferences interact as LM agents reason and commit to decisions in text-rendered grid worlds. We estimate task-relevant beliefs using report-based and rep...
A. S. Okcu, Wei-Sheng Wang, Tong-Meng Xie et al.· 0 citations
