会员服务
DeepPrune: Parallel Scaling without Inter-trace Redundancy
Arxiv
0+阅读 · 10月9日
Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study
Arxiv
0+阅读 · 10月9日
Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be Recovered
Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be Recovered
Arxiv
0+阅读 · 10月9日
Continuous Subgraph Matching via Cost-Model-based Dynamic Vertex Dominance Embeddings (Technical Report)
Arxiv
0+阅读 · 10月9日
GNN-based Path Embeddings for Efficient and Exact Subgraph Matching (Technical Report)
Arxiv
0+阅读 · 10月9日
Fewer Weights, More Problems: A Practical Attack on LLM Pruning
Arxiv
0+阅读 · 10月9日
Exchangeability in Neural Network and its Application to Dynamic Pruning
Arxiv
0+阅读 · 10月7日
Adaptive Pruning for Increased Robustness and Reduced Computational Overhead in Gaussian Process Accelerated Saddle Point Searches
Arxiv
0+阅读 · 10月7日
Mixture of Neuron Experts
Arxiv
0+阅读 · 10月7日
Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow
Arxiv
0+阅读 · 10月7日
CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis
Arxiv
0+阅读 · 10月7日
OptiFLIDS: Optimized Federated Learning for Energy-Efficient Intrusion Detection in IoT
Arxiv
0+阅读 · 10月5日
Dual Pruning and Sorting-Free Overestimation for Average-Utility Sequential Pattern Mining
Arxiv
0+阅读 · 10月5日
Vector Trifference
Arxiv
0+阅读 · 10月5日
Enhancing Speaker Verification with w2v-BERT 2.0 and Knowledge Distillation guided Structured Pruning
Arxiv
0+阅读 · 10月5日
参考链接
微信扫码咨询专知VIP会员
Top