Efficient Computing

NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes NeurIPS 2024 Neural Search Space in Gboard Decoder EMNLP 2024 NeuroPrune: A Neuro-inspired Topological Sparse Training Algorithm for Large Language Models ACL 2024 Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers NeurIPS 2024 Normalized Narrow Jump To Conclusions: Normalized Narrow Shortcuts for Parameter Efficient Early Exit Transformer Prediction EMNLP 2024 Offline and Online Optical Flow Enhancement for Deep Video Compression AAAI 2024 OneBit: Towards Extremely Low-bit Large Language Models NeurIPS 2024 On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and Reasoning EMNLP 2024 On the Effect of (Near) Duplicate Subwords in Language Modelling ACL 2024 On the token distance modeling ability of higher RoPE attention dimension EMNLP 2024 Optical Diffusion Models for Image Generation NeurIPS 2024 Optimal and Approximate Adaptive Stochastic Quantization NeurIPS 2024 Optimistic Verifiable Training by Controlling Hardware Nondeterminism NeurIPS 2024 Optimized Speculative Sampling for GPU Hardware Accelerators EMNLP 2024 Optimize & Reduce: A Top-Down Approach for Image Vectorization AAAI 2024 Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs EMNLP 2024 Order of Magnitude Speedups for LLM Membership Inference EMNLP 2024 OSFFNet: Omni-Stage Feature Fusion Network for Lightweight Image Super-Resolution AAAI 2024 Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding EMNLP 2024 Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers NeurIPS 2024 Pick-or-Mix: Dynamic Channel Sampling for ConvNets CVPR 2024 PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks CVPR 2024 Pipeline Parallelism with Controllable Memory NeurIPS 2024 PocketLLM: Enabling On-Device Fine-Tuning for Personalized LLMs ACL 2024 PointBeV: A Sparse Approach for BeV Predictions CVPR 2024