Summary of Zoom and Shift Are All You Need, by Jiahao Qin
Zoom and Shift are All You Needby Jiahao QinFirst submitted to arxiv on: 13 Jun…
Summary of Magpie: Alignment Data Synthesis From Scratch by Prompting Aligned Llms with Nothing, By Zhangchen Xu et al.
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothingby Zhangchen Xu, Fengqing…
Summary of Legend: Leveraging Representation Engineering to Annotate Safety Margin For Preference Datasets, by Duanyu Feng et al.
Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasetsby Duanyu Feng, Bowen Qin,…
Summary of Learning Reward and Policy Jointly From Demonstration and Preference Improves Alignment, by Chenliang Li et al.
Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignmentby Chenliang Li, Siliang Zeng,…
Summary of Paying More Attention to Source Context: Mitigating Unfaithful Translations From Large Language Model, by Hongbin Zhang et al.
Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Modelby Hongbin Zhang,…
Summary of Patenteval: Understanding Errors in Patent Generation, by You Zuo (almanach) et al.
PatentEval: Understanding Errors in Patent Generationby You Zuo, Kim Gerdes, Eric Villemonte de La Clergerie,…
Summary of Exploring Human-ai Perception Alignment in Sensory Experiences: Do Llms Understand Textile Hand?, by Shu Zhong et al.
Exploring Human-AI Perception Alignment in Sensory Experiences: Do LLMs Understand Textile Hand?by Shu Zhong, Elia…
Summary of Utilizing Graph Generation For Enhanced Domain Adaptive Object Detection, by Mu Wang
Utilizing Graph Generation for Enhanced Domain Adaptive Object Detectionby Mu WangFirst submitted to arxiv on:…
Summary of How Alignment and Jailbreak Work: Explain Llm Safety Through Intermediate Hidden States, by Zhenhong Zhou et al.
How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden Statesby Zhenhong Zhou, Haiyang…
Summary of Tlcm: Training-efficient Latent Consistency Model For Image Generation with 2-8 Steps, by Qingsong Xie et al.
TLCM: Training-efficient Latent Consistency Model for Image Generation with 2-8 Stepsby Qingsong Xie, Zhenyi Liao,…