Can humans and artificial intelligence cooperate such that their combination yields greater accuracy than either agent alone? This result, termed \emph{synergy} or \emph{complementarity}, is notoriously difficult to achieve, even when both agents possess significant independent accuracy. In this paper, we present a for...
Andrea Campagner, Federico Cabitza, Vincenzo Crupi· 0 citations
Recent advances in large (vision) language models have enabled computer-use agents that automate digital workflows via fine-grained keyboard and mouse operations. However, such agents remain fragile in long-horizon settings, where errors accumulate and executed actions leave unintended side effects, making the ability...
Byeonghun Bang, Sangwoo Park, Jinheon Baek et al.· 0 citations
AI-assisted dementia detection usually requires multimodal fusion of diverse data, such as clinical tabular assessments and neuroimaging data. However, most existing approaches perform feature fusion in Euclidean space. This overlooks the geometric structure of representation, including hierarchical organization in cli...
Jianfei Xu, Huizhi Liang, Judith Harrison et al.· 0 citations
Vehicle routing in delivery and logistics remains challenging as the number of clients varies. Classical approaches based on mixed-integer programming and heuristics can scale poorly or require problem-specific design, motivating learning-based alternatives. Reinforcement learning is particularly promising, provided a...
Sofiene Lassoued, D. Tertia, Stefan Lier et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
A single observation can admit several plausible futures, making uncertainty an essential part of world modelling. However, quantum generative models remain underexplored for this task. We introduce Quantum-JEPA, a latent-action JEPA framework that learns distributions of future representations using a conditional quan...
Model compression makes large language models deployable, but today's evaluation tells an incomplete story. Standard practice measures retained task performance and stops there. This misses a critical fact: compression perturbs the distributed knowledge embedded across billions of weights, and task scores alone cannot...
Jia-Hui Ning, Liang Chen, Yu-Chen Liang et al.· 0 citations
Enterprise agents answer questions over workplace records that evolve through team collaboration. As information is shared, corrected, and revised across documents, chats, and figures, multiple versions of the same information accumulate in the workspace. Reliable question answering therefore requires agents to reason...
Seohyun Lee, Jongha Kim, Dohwan Ko et al.· 0 citations
Staged post-training of multimodal foundation models chains vision-language alignment, reasoning distillation, and domain tuning, yet how each phase trades capabilities against the others remains under-characterised. Tracking an 8.4B-parameter model from an un-fine-tuned baseline through three training phases on Japane...
Approximate solutions of partial differential equations (PDEs) on unstructured grids can be represented on a graph. Numerical optimization involving stiff evolutionary and static PDEs often requires solving a large system of equations, which can be treated as a constraint. In this work, we present a fully differentiabl...
Nikolay Yavich, Alexander Ryabov, Viacheslav Naumov et al.· 0 citations
Experiments show that POC-VLM consistently outperforms representative data-driven, multimodal and domain-specific diagnostic methods, while demonstrating robust performance under varying sampling rates, noise levels and observation durations.
Yu Sha, Jun-Qi Tao, De-Yu Wang et al.· 0 citations
Step-Advantage Policy Distillation (SAPD) is proposed, a method for learning from offline trajectories using relative step advantages, allowing the student to generate responses conditioned on recorded histories, and introduces relative step advantage signals to stabilize training.
Jun-Cheng Diao, Hai-Bin Wang, Wei Shi et al.· 0 citations
Compass, an agentic router in which an LLM follows a routing recipe, gathers performance and cost evidence through tools, and optionally inspects candidate answers before selecting a model, is proposed and shown to improve accuracy and lower model-call cost relative to specialized and trained routing baselines.
