Financial document recognition is often assessed using character and word error rates, although these metrics do not express whether a system preserves the financial facts on which people and organisations act. This paper develops a human-centred, risk-constrained framework for evaluating financial document recognition...
Navigation world models predict future observations conditioned on navigation actions to support planning, but their generalization across real-world environments remains constrained by the limited coverage of action-labeled data. Action-free navigation videos provide diverse visual experience, yet lack the recorded ac...
Dujun Nie, Ruiqi Song, Zixuan Wang et al.· 0 citations
Diffusion-based vision-language-action (VLA) models cascade pretrained vision-language models (VLMs) with diffusion action experts, but typically restrict the VLM to providing static conditioning. This separation limits how much pretrained perception and reasoning can guide action generation, especially in out-of-distr...
Xicheng Gong, Wenxuan Song, Chengze Liu et al.· 0 citations
Does eliciting five weighted estimates within a single response consistently improve numerical judgments? We compare direct and multi-estimate elicitation across anchoring, hindsight, base-rate, conjunction, and status-quo/default tasks in six frozen configurations. Each configuration contributes 618 admitted developme...
An-Sheng Jhang· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
In the past few years, Vision Transformer (ViT) has achieved competitive performance in the field of computer vision. However, there still remain some problems. For instance, ViTs rely on large-scale training data since they simply contain a large number of trainable parameters, which slows down their learning efficien...
A taxonomy of AI slop grounded in a structured literature review is formalized and a roadmap for securing emerging AI-driven triage systems is provided, shifting evaluation from linguistic fluency to mathematical verifiability.
Junchen Ding, Jialiang Dong, Yi Zhu et al.· arXiv.org· 0 citations
Event-graph neural networks represent intensive care unit (ICU) records as typed entities linked by timestamped observations, and their gains are often attributed to relation-specific message passing. We tested which components matter once leakage is removed and validation is temporal and external. In 31,142 first ICU...
Invariants, the relations expected to hold among measured signals of a network, underpin applications from verification to traffic generation, telemetry imputation, and input validation. Yet, writing them by hand demands rare expertise in both formal logic and networking. Testing all possible combinations of telemetry...
Hongyu H\`e, Alexander Krentsel, Sylvia Ratnasamy et al.· 0 citations
Transformers use the same forward computation stream to both predict the next token and store useful state for future token predictions. We formulate the state-prediction separation hypothesis: disentangling the two roles yields better language modeling performance. We design a Transformer variant that uses separate co...
Giovanni Monea, Nathan Godey, Kiant\'e Brantley et al.· 0 citations
Language-model agent systems must map natural-language requests to one or more specialized agents before planning or tool execution. This decision is often treated as top-1 selection, although compositional requests can require several capabilities and unnecessary dispatch raises cost. We formulate fixed-catalog routin...
Ananto Nayan Bala, Faisal Muhammad Shah· 0 citations
Perceptive legged locomotion across discontinuous terrain requires shared locomotion knowledge, task-specific maneuvers, and smooth transitions between them. Existing approaches train specialized policies independently and either switch among them with a hierarchical selector or distill them into a monolithic policy. B...
Francisco Affonso, Matheus P. Angarola, Ana Luiza Mineiro et al.· 0 citations
Diffusion-based generative models usually perturb data through Markov processes driven by Brownian motion. Volterra processes allow more flexible temporal dependence, but their non-Markovian structure complicates score learning and reverse-time simulation. We develop Volterra generative models and provide Markovian app...
