Summary of Grounding Large Language Models in Embodied Environment with Imperfect World Models, by Haolan Liu et al.
Grounding Large Language Models In Embodied Environment With Imperfect World Modelsby Haolan Liu, Jishen ZhaoFirst…
Summary of Revisit Large-scale Image-caption Data in Pre-training Multimodal Foundation Models, by Zhengfeng Lai et al.
Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Modelsby Zhengfeng Lai, Vasileios Saveris, Chen Chen,…
Summary of Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization, by Lei Xu et al.
Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarizationby Lei Xu, Mohammed Asad Karim,…
Summary of Neutral Residues: Revisiting Adapters For Model Extension, by Franck Signe Talla and Herve Jegou and Edouard Grave
Neutral residues: revisiting adapters for model extensionby Franck Signe Talla, Herve Jegou, Edouard GraveFirst submitted…
Summary of Contrastive Localized Language-image Pre-training, by Hong-you Chen et al.
Contrastive Localized Language-Image Pre-Trainingby Hong-You Chen, Zhengfeng Lai, Haotian Zhang, Xinze Wang, Marcin Eichner, Keen…
Summary of Crispo: Multi-aspect Critique-suggestion-guided Automatic Prompt Optimization For Text Generation, by Han He et al.
CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generationby Han He, Qianchu Liu, Lei Xu,…
Summary of Training Language Models on Synthetic Edit Sequences Improves Code Synthesis, by Ulyana Piterbarg and Lerrel Pinto and Rob Fergus
Training Language Models on Synthetic Edit Sequences Improves Code Synthesisby Ulyana Piterbarg, Lerrel Pinto, Rob…
Summary of An Online Automatic Modulation Classification Scheme Based on Isolation Distributional Kernel, by Xinpeng Li et al.
An Online Automatic Modulation Classification Scheme Based on Isolation Distributional Kernelby Xinpeng Li, Zile Jiang,…
Summary of Relic: a Recipe For 64k Steps Of In-context Reinforcement Learning For Embodied Ai, by Ahmad Elawady et al.
ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AIby Ahmad Elawady,…
Summary of Gpt-4o As the Gold Standard: a Scalable and General Purpose Approach to Filter Language Model Pretraining Data, by Jifan Zhang et al.
GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model…