Repurposing Synthetic Data for Fine-grained Search Agent Supervision
"准确率提升" 相关文章
A Neural Model for Contextual Biasing Score Learning and Filtering
SAMOSA: Sharpness Aware Minimization for Open Set Active learning
LiteStage: Latency-aware Layer Skipping for Multi-stage Reasoning
LightSAE: Parameter-Efficient and Heterogeneity-Aware Embedding for IoT Multivariate Time Series Forecasting
SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
DualResearch: Entropy-Gated Dual-Graph Retrieval for Answer Reconstruction
VersionRAG: Version-Aware Retrieval-Augmented Generation for Evolving Documents
Active Confusion Expression in Large Language Models: Leveraging World Models toward Better Social Reasoning
Unlocking Dataset Distillation with Diffusion Models
TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture
GroundSight: Augmenting Vision-Language Models with Grounding Information and De-hallucination
Aligning LLMs for Multilingual Consistency in Enterprise Applications
S$^3$F-Net: A Multi-Modal Approach to Medical Image Classification via Spatial-Spectral Summarizer Fusion Network
TriSPrompt: A Hierarchical Soft Prompt Model for Multimodal Rumor Detection with Incomplete Modalities
Chart-CoCa: Self-Improving Chart Understanding of Vision LMs via Code-Driven Synthesis and Candidate-Conditioned Answering
Bringing Balance to Hand Shape Classification: Mitigating Data Imbalance Through Generative Models
Reinforcement Learning in hyperbolic space for multi-step reasoning
Hierarchical Budget Policy Optimization for Adaptive Reasoning
回答准确率从60%飙至95%！AI知识库救命方案
