Search Results for author:
Found 12 papers, 6 papers with code
Fast Hardware-Aware Neural Architecture Search
Unlike previous approaches that apply search algorithms on a small, human-designed search space without considering hardware diversity, we propose HURRICANE that explores the automatic hardware-aware search over a much larger search space and a two-stage search algorithm, to efficiently generate tailored models for different types of hardware.
Hardware Aware Neural Architecture Search
Neural Architecture Search
Learning to Rank Ace Neural Architectures via Normalized Discounted Cumulative Gain
One of the key challenges in Neural Architecture Search (NAS) is to efficiently rank the performances of architectures.
Boosting Mobile CNN Inference through Semantic Memory
Human brains are known to be capable of speeding up visual recognition of repeatedly presented objects through faster memory encoding and accessing procedures on activated neurons.
SwiftPruner: Reinforced Evolutionary Pruning for Efficient Ad Relevance
Remarkably, under our latency requirement of 1900us on CPU, SwiftPruner achieves a 0. 86% higher AUC than the state-of-the-art uniform sparse baseline for BERT-Mini on a large scale real-world dataset.
LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup
On-device Deep Neural Network (DNN) inference consumes significant computing resources and development efforts.
SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference
The combination of Neural Architecture Search (NAS) and quantization has proven successful in automatically designing low-FLOPs INT8 quantized neural networks (QNN).
ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices
However, prior supernet training methods that rely on uniform sampling suffer from the gradient conflict issue: the sampled subnets can have vastly different model sizes (e. g., 50M vs. 2G FLOPs), leading to different optimization directions and inferior performance.
Accurate and Structured Pruning for Efficient Automatic Speech Recognition
In this paper, we propose a novel compression strategy that leverages structured pruning and knowledge distillation to reduce the model size and inference cost of the Conformer model while preserving high recognition performance.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference
Deploying pre-trained transformer models like BERT on downstream tasks in resource-constrained scenarios is challenging due to their high inference cost, which grows rapidly with input sequence length.
Compresso: Structured Pruning with Collaborative Prompting Learns Compact Large Language Models
To this end, Compresso prunes LLaMA-7B to 5. 4B, maintaining original performance and even surpassing LLaMA-7B in reading comprehension by 2. 62%.
Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning
In this work, we propose CoT-Influx, a novel approach that pushes the boundary of few-shot Chain-of-Thoughts (CoT) learning to improve LLM mathematical reasoning.
Ranked #105 on
Arithmetic Reasoning
on GSM8K
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
This is achieved by three key innovations: (i) we identify and exploit two forms of non-uniformities in positional interpolation through an efficient search, providing a better initialization for fine-tuning and enabling an 8x extension in non-fine-tuning scenarios; (ii) we introduce a progressive extension strategy that first fine-tunes a 256k length LLM and then conducts a second positional interpolation on the fine-tuned extended LLM to achieve a 2048k context window; (iii) we readjust LongRoPE on 8k length to recover the short context window performance.
