Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Modelsby Fushuo Huo, Wenchao Xu, Zhong Zhang, Haozhao…
SentenceVAE: Enable Next-sentence Prediction for Large Language Models with Faster Speed, Higher Accuracy and Longer…
QUITO: Accelerating Long-Context Reasoning through Query-Guided Context Compressionby Wenshan Wang, Yihang Wang, Yixing Fan, Huaming…
Why Misinformation is Created? Detecting them by Integrating Intent Featuresby Bing Wang, Ximing Li, Changchun…
AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answeringby Mahiro Ukai, Shuhei Kurita, Atsushi Hashimoto,…
High Efficiency Image Compression for Large Visual-Language Modelsby Binzhe Li, Shurun Wang, Shiqi Wang, Yan…
DOPRA: Decoding Over-accumulation Penalization and Re-allocation in Specific Weighting Layerby Jinfeng Wei, Xiaofeng ZhangFirst submitted…
Training-free Composite Scene Generation for Layout-to-Image Synthesisby Jiaqi Liu, Tao Huang, Chang XuFirst submitted to…
Aligning Model Evaluations with Human Preferences: Mitigating Token Count Bias in Language Model Assessmentsby Roland…