会员服务
Improving $(α, f)$-Byzantine Resilience in Federated Learning via layerwise aggregation and cosine distance
Arxiv
0+阅读 · 3月27日
Frequency-Controlled Diffusion Model for Versatile Text-Guided Image-to-Image Translation
Arxiv
0+阅读 · 3月27日
Quantization-aware Matrix Factorization for Low Bit Rate Image Compression
Arxiv
0+阅读 · 3月27日
Rerouting Connection: Hybrid Computer Vision Analysis Reveals Visual Similarity Between Indus and Tibetan-Yi Corridor Writing Systems
Arxiv
0+阅读 · 3月27日
Statistical Advantages of Perturbing Cosine Router in Mixture of Experts
Arxiv
0+阅读 · 3月5日
Improving LSH via Tensorized Random Projection
Arxiv
0+阅读 · 3月2日
SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging
Arxiv
0+阅读 · 3月21日
Collaborative Speculative Inference for Efficient LLM Inference Serving
Arxiv
0+阅读 · 3月13日
Unmasking Implicit Bias: Evaluating Persona-Prompted LLM Responses in Power-Disparate Social Scenarios
Arxiv
0+阅读 · 3月3日
LLMs in the Classroom: Outcomes and Perceptions of Questions Written with the Aid of AI
Arxiv
0+阅读 · 3月23日
Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training
Arxiv
0+阅读 · 3月4日
Encrypted Vector Similarity Computations Using Partially Homomorphic Encryption: Applications and Performance Analysis
Arxiv
0+阅读 · 3月7日
Post-hoc Probabilistic Vision-Language Models
Arxiv
0+阅读 · 3月19日
Faster and Space Efficient Indexing for Locality Sensitive Hashing
Arxiv
0+阅读 · 3月9日
A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules
Arxiv
0+阅读 · 3月17日
参考链接
微信扫码咨询专知VIP会员
Top