Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling
cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Sources
- Power-SMC: Low-Latency Sequence-Level Power Sampling for Training-Free LLM Reasoning
- Evaluating Large Language Models Trained on Code
- Post-training Large Language Models for Diverse High-Quality Responses
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Recipes for Steering and Scaling LLMs via Sampling
- Measuring Mathematical Problem Solving With the MATH Dataset
- Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- Sampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlo
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation
- On the Effect of Sampling Diversity in Scaling LLM Inference
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks