会员服务
Does Weak-to-strong Generalization Happen under Spurious Correlations?
Arxiv
0+阅读 · 9月28日
Quantifying Knowledge Distillation Using Partial Information Decomposition
Arxiv
0+阅读 · 4月4日
Model Diffusion for Certifiable Few-shot Transfer Learning
Arxiv
0+阅读 · 5月28日
Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine
Arxiv
0+阅读 · 7月17日
Subasa -- Adapting Language Models for Low-resourced Offensive Language Detection in Sinhala
Subasa -- Adapting Language Models for Low-resourced Offensive Language Detection in Sinhala
Arxiv
0+阅读 · 4月2日
Multi-Task Neural Architecture Search Using Architecture Embedding and Transfer Rank
Multi-Task Neural Architecture Search Using Architecture Embedding and Transfer Rank
Arxiv
0+阅读 · 4月1日
A Context-Aware Approach for Enhancing Data Imputation with Pre-trained Language Models
A Context-Aware Approach for Enhancing Data Imputation with Pre-trained Language Models
Arxiv
0+阅读 · 3月27日
TwinTURBO: Semi-Supervised Fine-Tuning of Foundation Models via Mutual Information Decompositions for Downstream Task and Latent Spaces
Arxiv
0+阅读 · 3月10日
Understanding and Improving Information Preservation in Prompt Compression for LLMs
Arxiv
0+阅读 · 3月24日
Mutual Information-Empowered Task-Oriented Communication: Principles, Applications and Challenges
Arxiv
0+阅读 · 3月26日
RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression
Arxiv
0+阅读 · 3月25日
Triple Phase Transitions: Understanding the Learning Dynamics of Large Language Models from a Neuroscience Perspective
Arxiv
0+阅读 · 2月28日
Conterfactual Generative Zero-Shot Semantic Segmentation
Arxiv
0+阅读 · 1月28日
Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting
Arxiv
0+阅读 · 2月5日
Differentially Private In-context Learning via Sampling Few-shot Mixed with Zero-shot Outputs
Arxiv
0+阅读 · 1月31日
参考链接
微信扫码咨询专知VIP会员
Top