RL记得更牢，SFT更健忘？普林斯顿陈丹琦团队改写后训练认知
"数据分布" 相关文章
RL记得更牢，SFT更健忘？普林斯顿陈丹琦团队改写后训练认知
Remarks on Bayesian studies from 1963
Can GRPO Help LLMs Transcend Their Pretraining Origin?
Can GRPO Help LLMs Transcend Their Pretraining Origin?
ZeroCard: Cardinality Estimation with Zero Dependence on Target Databases -- No Data, No Query, No Retraining
Investigating Neural Scaling Laws Emerging from Deep Data Structure
RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts
Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation
Review of Hallucination Understanding in Large Language and Vision Models
VeriFlow: Modeling Distributions for Neural Network Verification
Context and Diversity Matter: The Emergence of In-Context Learning in World Models
Consistent Hashing 101: How Modern Systems Handle Growth and Failure
Explaining Concept Drift through the Evolution of Group Counterfactuals
FBFL: A Field-Based Coordination Approach for Data Heterogeneity in Federated Learning
每周AI论文速递（250804-250808）
Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension
Optimal Transport for Domain Adaptation through Gaussian Mixture Models
Model Compression using Progressive Channel Pruning
