会员服务
Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training
Arxiv
0+阅读 · 11月1日
See the Speaker: Crafting High-Resolution Talking Faces from Speech with Prior Guidance and Region Refinement
Arxiv
0+阅读 · 10月28日
Dual-level Progressive Hardness-Aware Reweighting for Cross-View Geo-Localization
Arxiv
0+阅读 · 10月31日
Semantic Frame Aggregation-based Transformer for Live Video Comment Generation
Arxiv
0+阅读 · 10月30日
From Memorization to Reasoning in the Spectrum of Loss Curvature
Arxiv
0+阅读 · 10月31日
GACA-DiT: Diffusion-based Dance-to-Music Generation with Genre-Adaptive Rhythm and Context-Aware Alignment
Arxiv
0+阅读 · 10月28日
SAGS: Self-Adaptive Alias-Free Gaussian Splatting for Dynamic Surgical Endoscopic Reconstruction
Arxiv
0+阅读 · 10月31日
FedMuon: Accelerating Federated Learning with Matrix Orthogonalization
Arxiv
0+阅读 · 10月31日
TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control
Arxiv
0+阅读 · 10月31日
Balancing Knowledge Updates: Toward Unified Modular Editing in LLMs
Arxiv
0+阅读 · 10月31日
Exploiting heterogeneous delays for efficient computation in low-bit neural networks
Arxiv
0+阅读 · 10月31日
Dependence-Driven, Scalable Quantum Circuit Mapping with Affine Abstractions
Arxiv
0+阅读 · 10月31日
Weight Enumerators From Equivalence Relations and MacWilliams Identities
Arxiv
0+阅读 · 10月31日
HELIOS: Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving
Arxiv
0+阅读 · 10月31日
Robust Principal Components by Casewise and Cellwise Weighting
Robust Principal Components by Casewise and Cellwise Weighting
Arxiv
0+阅读 · 10月31日
参考链接
微信扫码咨询专知VIP会员
Top