3 citations · 6 across the 8 of their papers we have counts for
8 papers
Search or Chat? Comparing How We Learn About Debated Topics
Ran Yu, Alisa Rieger, Rabia Karatoprak Ersen +1
As large language models (LLMs) become more integrated into everyday information platforms, chat-based systems are emerging as a popular alternative to traditional web searches, es…
MissClick: Execution-Aware Adversarial Attacks on Coordinate Generation in GUI Grounding Models
Yu Ran, Wentao Zhao, Xin Zhang +1
Recent GUI visual grounding models generate screen coordinates as digit-token sequences that are parsed into numerical values and mapped to executable clicks. This generation-to-ex…
ERNIE 5.0 Technical Report
Haifeng Wang, Hua Wu, Tian Wu +432
In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio…
Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality
Junliang Li, Yucheng Wang, Yan Chen +5
Hallucination in large language models (LLMs) during long-form generation remains difficult to address under existing reinforcement learning from human feedback (RLHF) frameworks,…
Secure Video Quality Assessment Resisting Adversarial Attacks
Ao-Xiang Zhang, Yuan-Gen Wang, Yu Ran +3
The exponential surge in video traffic has intensified the imperative for Video Quality Assessment (VQA). Leveraging cutting-edge architectures, current VQA models have achieved hu…
Black-box Adversarial Attacks Against Image Quality Assessment Models
Yu Ran, Ao-Xiang Zhang, Mingjie Li +2
The goal of No-Reference Image Quality Assessment (NR-IQA) is to predict the perceptual quality of an image in line with its subjective evaluation. To put the NR-IQA models into pr…
Vulnerabilities in Video Quality Assessment Models: The Challenge of Adversarial Attacks
Ao-Xiang Zhang, Yu Ran, Weixuan Tang +1
No-Reference Video Quality Assessment (NR-VQA) plays an essential role in improving the viewing experience of end-users. Driven by deep learning, recent NR-VQA models based on Conv…
JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs
Pei Ke, Haozhe Ji, Yu Ran +5
Existing pre-trained models for knowledge-graph-to-text (KG-to-text) generation simply fine-tune text-to-text pre-trained models such as BART or T5 on KG-to-text datasets, which la…