From the 1 of 7 linked papers with an AI index.
7 papers
MemeMind: Reference-Guided Trace Construction for Offline Context Optimization
Run Yang, Weihang Wang, Boheng Sheng +7
Offline context optimization improves an agent by revising its instructions and examples while keeping the model frozen. This approach learns from rollouts on an adaptation set, bu…
MemeBench: What LVLMs Miss When Interpreting Culture-Dependent Memes
Weihang Wang, Kainan Tu, Jielei Zhang +9
The paper presents MemeBench, a diagnostic benchmark of 1,253 Chinese and English memes that evaluates how large vision‑language models handle cultural and background knowledge, an…
Scaling Multi-Hop Training Data via Graph-Constrained Path Selection
Pengyu Chen, Yonggang Zhang, Mingming Chen +3
Endowing large language models with compositional reasoning over specialized documents requires multi-hop training data at scale, where such data rarely exists outside of curated b…
TextFlux: An OCR-Free DiT Model for High-Fidelity Multilingual Scene Text Synthesis
Yu Xie, Jielei Zhang, Pengyu Chen +5
Diffusion-based scene text synthesis has progressed rapidly, yet existing methods commonly rely on additional visual conditioning modules and require large-scale annotated data to…
RED-F: Reconstruction-Elimination based Dual-stream Contrastive Forecasting for Multivariate Time Series Anomaly Prediction
PengYu Chen, Xiaohou Shi, Yuan Chang +2
Anomaly prediction (AP) in multivariate time series (MTS) is crucial to ensure system dependability. Existing methods either focus solely on whether an anomaly is imminent without…
Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025
Zonghao Ying, Siyang Wu, Run Hao +44
Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks…