Model Architecture

AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation NeurIPS 2024 A Sequential Learning-Based Approach for Monocular Human Performance Capture WACV 2024 A Simple Romance Between Multi-Exit Vision Transformer and Token Reduction ICLR 2024 A Single-Step, Sharpness-Aware Minimization is All You Need to Achieve Efficient and Accurate Sparse Training NeurIPS 2024 Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers EMNLP 2024 Attention-based Iterative Decomposition for Tensor Product Representation ICLR 2024 AttEXplore: Attribution for Explanation with model parameters eXploration ICLR 2024 AttNS: Attention-Inspired Numerical Solving For Limited Data Scenarios ICML 2024 Attribution Patching Outperforms Automated Circuit Discovery EMNLP 2024 A Unified Environmental Network for Pedestrian Trajectory Prediction AAAI 2024 AutoChunk: Automated Activation Chunk for Memory-Efficient Deep Learning Inference ICLR 2024 Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost ICLR 2024 AVIN-Chat: An Audio-Visual Interactive Chatbot System with Emotional State Tuning IJCAI 2024 AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search CVPR 2024 BadActs: A Universal Backdoor Defense in the Activation Space ACL 2024 Balancing Act: Constraining Disparate Impact in Sparse Models ICLR 2024 BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model CVPR 2024 Batched Low-Rank Adaptation of Foundation Models ICLR 2024 B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable NeurIPS 2024 Benchmarking Spurious Bias in Few-Shot Image Classifiers ECCV 2024 Benchmarking the Attribution Quality of Vision Models NeurIPS 2024 BERTground: A Transformer-Based Model of Background Spectra on the ISS-Based NICER Space Telescope AAAI 2024 Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable? NeurIPS 2024 Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enhancement Interspeech 2024 BiDM: Pushing the Limit of Quantization for Diffusion Models NeurIPS 2024