Summary of Length-induced Embedding Collapse in Transformer-based Models, by Yuqi Zhou et al.
Length-Induced Embedding Collapse in Transformer-based Modelsby Yuqi Zhou, Sunhao Dai, Zhanshuo Cao, Xiao Zhang, Jun…
Summary of Vl-cache: Sparsity and Modality-aware Kv Cache Compression For Vision-language Model Inference Acceleration, by Dezhan Tu et al.
VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Accelerationby Dezhan Tu, Danylo…
Summary of Kernel Looping: Eliminating Synchronization Boundaries For Peak Inference Performance, by David Koeplinger et al.
Kernel Looping: Eliminating Synchronization Boundaries for Peak Inference Performanceby David Koeplinger, Darshan Gandhi, Pushkar Nandkar,…
Summary of Edt: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching, By Xinwang Chen and Ning Liu and Yichen Zhu and Feifei Feng and Jian Tang
EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketchingby Xinwang Chen, Ning Liu, Yichen…
Summary of Larp: Tokenizing Videos with a Learned Autoregressive Generative Prior, by Hanyu Wang et al.
LARP: Tokenizing Videos with a Learned Autoregressive Generative Priorby Hanyu Wang, Saksham Suri, Yixuan Ren,…
Summary of Relation-based Counterfactual Data Augmentation and Contrastive Learning For Robustifying Natural Language Inference Models, by Heerin Yang et al.
Relation-based Counterfactual Data Augmentation and Contrastive Learning for Robustifying Natural Language Inference Modelsby Heerin Yang,…
Summary of Timesuite: Improving Mllms For Long Video Understanding Via Grounded Tuning, by Xiangyu Zeng et al.
TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuningby Xiangyu Zeng, Kunchang Li, Chenting…
Summary of Meaning Typed Prompting: a Technique For Efficient, Reliable Structured Output Generation, by Chandra Irugalbandara
Meaning Typed Prompting: A Technique for Efficient, Reliable Structured Output Generationby Chandra IrugalbandaraFirst submitted to…
Summary of Expertflow: Optimized Expert Activation and Token Allocation For Efficient Mixture-of-experts Inference, by Xin He et al.
ExpertFlow: Optimized Expert Activation and Token Allocation for Efficient Mixture-of-Experts Inferenceby Xin He, Shunkang Zhang,…
Summary of Benchmarking Foundation Models on Exceptional Cases: Dataset Creation and Validation, by Suho Kang et al.
Benchmarking Foundation Models on Exceptional Cases: Dataset Creation and Validationby Suho Kang, Jungyang Park, Joonseo…