Summary of Competition Dynamics Shape Algorithmic Phases Of In-context Learning, by Core Francisco Park et al.
Competition Dynamics Shape Algorithmic Phases of In-Context Learningby Core Francisco Park, Ekdeep Singh Lubana, Itamar…
Summary of A Comprehensive Guide to Explainable Ai: From Classical Models to Llms, by Weiche Hsieh et al.
A Comprehensive Guide to Explainable AI: From Classical Models to LLMsby Weiche Hsieh, Ziqian Bi,…
Summary of Dynamic-llava: Efficient Multimodal Large Language Models Via Dynamic Vision-language Context Sparsification, by Wenxuan Huang et al.
Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsificationby Wenxuan Huang, Zijie Zhai,…
Summary of Quantifying Perturbation Impacts For Large Language Models, by Paulius Rauba et al.
Quantifying perturbation impacts for large language modelsby Paulius Rauba, Qiyao Wei, Mihaela van der SchaarFirst…
Summary of Visual Modality Prompt For Adapting Vision-language Object Detectors, by Heitor R. Medeiros et al.
Visual Modality Prompt for Adapting Vision-Language Object Detectorsby Heitor R. Medeiros, Atif Belal, Srikanth Muralidharan,…
Summary of Quake: Speeding Up Model Inference Using Quick and Approximate Kernels For Exponential Non-linearities, by Sai Kiran Narayanaswami and Gopalakrishnan Srinivasan and Balaraman Ravindran
QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearitiesby Sai Kiran…
Summary of Unleashing the Power Of Data Synthesis in Visual Localization, by Sihang Li et al.
Unleashing the Power of Data Synthesis in Visual Localizationby Sihang Li, Siqi Tan, Bowen Chang,…
Summary of Step: Enhancing Video-llms’ Compositional Reasoning by Spatio-temporal Graph-guided Self-training, By Haiyi Qiu et al.
STEP: Enhancing Video-LLMs’ Compositional Reasoning by Spatio-Temporal Graph-guided Self-Trainingby Haiyi Qiu, Minghe Gao, Long Qian,…
Summary of Speculative Decoding with Ctc-based Draft Model For Llm Inference Acceleration, by Zhuofan Wen et al.
Speculative Decoding with CTC-based Draft Model for LLM Inference Accelerationby Zhuofan Wen, Shangtong Gui, Yang…
Summary of Condense, Don’t Just Prune: Enhancing Efficiency and Performance in Moe Layer Pruning, by Mingyu Cao et al.
Condense, Don’t Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruningby Mingyu Cao, Gen…