Summary of Dynamic Depth Decoding: Faster Speculative Decoding For Llms, by Oscar Brown et al.
Dynamic Depth Decoding: Faster Speculative Decoding for LLMsby Oscar Brown, Zhengjie Wang, Andrea Do, Nikhil…
Summary of Llms Hallucinate Graphs Too: a Structural Perspective, by Erwan Le Merrer and Gilles Tredan
LLMs hallucinate graphs too: a structural perspectiveby Erwan Le Merrer, Gilles TredanFirst submitted to arxiv…
Summary of Sequence to Sequence Reward Modeling: Improving Rlhf by Language Feedback, By Jiayi Zhou et al.
Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedbackby Jiayi Zhou, Jiaming Ji, Juntao…
Summary of Transient Fault Tolerant Semantic Segmentation For Autonomous Driving, by Leonardo Iurada et al.
Transient Fault Tolerant Semantic Segmentation for Autonomous Drivingby Leonardo Iurada, Niccolò Cavagnero, Fernando Fernandes Dos…
Summary of Memlong: Memory-augmented Retrieval For Long Text Modeling, by Weijie Liu et al.
MemLong: Memory-Augmented Retrieval for Long Text Modelingby Weijie Liu, Zecheng Tang, Juntao Li, Kehai Chen,…
Summary of Beyond Preferences in Ai Alignment, by Tan Zhi-xuan et al.
Beyond Preferences in AI Alignmentby Tan Zhi-Xuan, Micah Carroll, Matija Franklin, Hal AshtonFirst submitted to…
Summary of Reasoning Aware Self-consistency: Leveraging Reasoning Paths For Efficient Llm Sampling, by Guangya Wan et al.
Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Samplingby Guangya Wan, Yuqi Wu, Jie…
Summary of Strategic Arms with Side Communication Prevail Over Low-regret Mab Algorithms, by Ahmed Ben Yahmed (crest et al.
Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithmsby Ahmed Ben Yahmed, Clément Calauzènes,…
Summary of Vq4dit: Efficient Post-training Vector Quantization For Diffusion Transformers, by Juncan Deng et al.
VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformersby Juncan Deng, Shuaiting Li, Zeyu Wang, Hong…
Summary of Look, Compare, Decide: Alleviating Hallucination in Large Vision-language Models Via Multi-view Multi-path Reasoning, by Xiaoye Qu et al.
Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoningby Xiaoye Qu,…