VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision
"优化框架" 相关文章
How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptation
软件所提出基于信息论的大模型强化学习微调框架
Graph Unlearning Meets Influence-aware Negative Preference Optimization
Graph Unlearning Meets Influence-aware Negative Preference Optimization
DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping
Optimized Layerwise Approximation for Efficient Private Inference on Fully Homomorphic Encryption
网络瓦解领域概览丨附5篇领域必读文献·周二直播
Improving Chain-of-Thought Efficiency for Autoregressive Image Generation
FocusMed: A Large Language Model-based Framework for Enhancing Medical Question Summarization with Focus Identification
Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning
Scalable Ground Station Selection for Large LEO Constellations
Scalable Ground Station Selection for Large LEO Constellations
UniPruning: Unifying Local Metric and Global Feedback for Scalable Sparse LLMs
AIM: Adaptive Intervention for Deep Multi-task Learning of Molecular Properties
Towards Size-invariant Salient Object Detection: A Generic Evaluation and Optimization Approach
AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models
Tri-Accel: Curvature-Aware Precision-Adaptive and Memory-Elastic Optimization for Efficient GPU Usage
Privacy-Utility Trade-off in Data Publication: A Bilevel Optimization Framework with Curvature-Guided Perturbation
SSPO: Self-traced Step-wise Preference Optimization for Process Supervision and Reasoning Compression
