34 papers
Agent Safety Should Be a Runtime Contract
Albus W. Ng, Yi Han, Jusheng Zhang +1
The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitutional AI. We argue this is structurally insufficient for auton…
Kolmogorov-Arnold Fourier Networks
Jusheng Zhang, Yijia Fan, Kaitong Cai +2
Although Kolmogorov-Arnold-based interpretable networks (KANs) possess strong theoretical expressiveness, they suffer from severe parameter explosion and limited ability to capture…
3DAlign-DAER: Dynamic Attention Policy and Efficient Retrieval Strategy for Fine-grained 3D-Text Alignment at Scale
Yijia Fan, Jusheng Zhang, Kaitong Cai +3
Despite recent advancements in 3D-text cross-modal alignment, existing state-of-the-art methods still struggle to align fine-grained textual semantics with detailed geometric struc…
Cost-Effective Communication: An Auction-based Method for Language Agent Interaction
Yijia Fan, Jusheng Zhang, Kaitong Cai +4
Multi-agent systems (MAS) built on large language models (LLMs) often suffer from inefficient "free-for-all" communication, leading to exponential token costs and low signal-to-noi…
The Fourth Challenge on Image Super-Resolution (4) at NTIRE 2026: Benchmark Results and Method Overview
Zheng Chen, Kai Liu, Jingkai Wang +150
This paper presents the NTIRE 2026 image super-resolution (4) challenge, one of the associated competitions of the NTIRE 2026 Workshop at CVPR 2026. The challenge aims to r…
Aligning Multimodal Sequential Recommendations via Robust Direct Preference Optimization with Sparse MoE
Hejin Huang, Jusheng Zhang, Kaitong Cai +2
Preference-based alignment objectives have been widely adopted, from RLHF-style pairwise learning in large language models to emerging applications in recommender systems. Yet, exi…