Summary of Adaptive Inference-time Compute: Llms Can Predict If They Can Do Better, Even Mid-generation, by Rohin Manvi et al.
Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generationby Rohin Manvi,…
Summary of Three-in-one: Fast and Accurate Transducer For Hybrid-autoregressive Asr, by Hainan Xu et al.
Three-in-One: Fast and Accurate Transducer for Hybrid-Autoregressive ASRby Hainan Xu, Travis M. Bartley, Vladimir Bataev,…
Summary of Entp: Encoder-only Next Token Prediction, by Ethan Ewer et al.
ENTP: Encoder-only Next Token Predictionby Ethan Ewer, Daewon Chae, Thomas Zeng, Jinkyu Kim, Kangwook LeeFirst…
Summary of Learnable Expansion Of Graph Operators For Multi-modal Feature Fusion, by Dexuan Ding et al.
Learnable Expansion of Graph Operators for Multi-Modal Feature Fusionby Dexuan Ding, Lei Wang, Liyun Zhu,…
Summary of Attention Layers Provably Solve Single-location Regression, by Pierre Marion et al.
Attention layers provably solve single-location regressionby Pierre Marion, Raphaël Berthier, Gérard Biau, Claire BoyerFirst submitted…
Summary of Integrative Decoding: Improve Factuality Via Implicit Self-consistency, by Yi Cheng et al.
Integrative Decoding: Improve Factuality via Implicit Self-consistencyby Yi Cheng, Xiao Liang, Yeyun Gong, Wen Xiao,…
Summary of Sparse Attention Decomposition Applied to Circuit Tracing, by Gabriel Franco et al.
Sparse Attention Decomposition Applied to Circuit Tracingby Gabriel Franco, Mark CrovellaFirst submitted to arxiv on:…
Summary of Characterizing and Efficiently Accelerating Multimodal Generation Model Inference, by Yejin Lee et al.
Characterizing and Efficiently Accelerating Multimodal Generation Model Inferenceby Yejin Lee, Anna Sun, Basil Hosmer, Bilge…
Summary of Using Pretrained Graph Neural Networks with Token Mixers As Geometric Featurizers For Conformational Dynamics, by Zihan Pengmei et al.
Using pretrained graph neural networks with token mixers as geometric featurizers for conformational dynamicsby Zihan…
Summary of Sata: Spatial Autocorrelation Token Analysis For Enhancing the Robustness Of Vision Transformers, by Nick Nikzad et al.
SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformersby Nick Nikzad, Yi…