Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes

↘ Related papers

• When Can LLMs Learn to Reason with Weak Supervision?
  Salman Rahman62% match
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
  Zhenwen Liang60% match
• MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
  Shaden Alshammari42% match
• Universally Empowering Zeroth-Order Optimization via Adaptive Layer-wise Sampling
  Fei Wang41% match
• Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts
  Jacob Morrison40% match