VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models
Paper
•
2509.19803
•
Published
•
119
Chuzhan HAO
Chuzhan
AI & ML interests
NLP, LLM, Agentic Reasoning, Question Answering
Organizations
None yet
authored
6
papers
3 months ago
Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models
Paper
•
2403.03432
•
Published
•
1
AirRAG: Activating Intrinsic Reasoning for Retrieval Augmented Generation via Tree-based Search
Paper
•
2501.10053
•
Published
RASD: Retrieval-Augmented Speculative Decoding
Paper
•
2503.03434
•
Published
•
1
FlowKV: A Disaggregated Inference Framework with Low-Latency KV Cache Transfer and Load-Aware Scheduling
Paper
•
2504.03775
•
Published
PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning
Paper
•
2508.21104
•
Published
•
35