2 papers
cs.LG2026
MSDformer: Multi-scale Discrete Transformer For Time Series Generation
Shibo Feng, Zhicheng Chen, Xi Xiao +4
Discrete Token Modeling (DTM), which employs vector quantization techniques, has demonstrated remarkable success in modeling non-natural language modalities, particularly in time s…
cs.CV2025
Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models
Fushuo Huo, Wenchao Xu, Zhong Zhang +3
While Large Vision-Language Models (LVLMs) have rapidly advanced in recent years, the prevalent issue known as the `hallucination' problem has emerged as a significant bottleneck,…