7 papers
A Benchmark Dataset for MLLM-Generated Image Detection: GPT Image2 & Nano Banana2
Zirui Zhang, Yinbo Yu, Donghai Guan +3
The realism of images generated by multimodal large language models (MLLMs), such as GPT Image2 and Nano Banana2, has improved rapidly in recent years. Compared with early generati…
SSD: Spatially Speculative Decoding Accelerates Autoregressive Image Generation
Shilong Xiang, Zirui Zhang, Lijun Yu +1
Autoregressive models excel in visual generation by treating images as 1D sequences of discrete tokens, mirroring language modeling. However, this flattening discards the intrinsic…
R-C2: Cycle-Consistent Reinforcement Learning Improves Multimodal Reasoning
Zirui Zhang, Haoyu Dong, Kexin Pei +1
Robust perception and reasoning require consistency across sensory modalities. Yet current multimodal models often violate this principle, yielding contradictory predictions for vi…
Reactivation: Empirical NTK Dynamics Under Task Shifts
Yuzhi Liu, Zixuan Chen, Zirui Zhang +2
The Neural Tangent Kernel (NTK) offers a powerful tool to study the functional dynamics of neural networks. In the so-called lazy, or kernel regime, the NTK remains static during t…
Yi-Lightning Technical Report
Alan Wake, Bei Chen, C. X. Lv +41
This technical report presents Yi-Lightning, our latest flagship large language model (LLM). It achieves exceptional performance, ranking 6th overall on Chatbot Arena, with particu…
I Can Hear You: Selective Robust Training for Deepfake Audio Detection
Zirui Zhang, Wei Hao, Aroon Sankoh +4
Recent advances in AI-generated voices have intensified the challenge of detecting deepfake audio, posing risks for scams and the spread of disinformation. To tackle this issue, we…