FlashSampling: Fast and Memory-Efficient Exact Sampling
cs.LG, cs.AI, cs.CL
Submitted: 2026-03-16
Updated: 2026-09-25
Code: https://github.com/FlashSampling/FlashSampling
Terminology
Sources
- Entropy-Aligned Decoding of LMs for Better Writing and Reasoning
- Robust benchmarking in noisy environments
- Training Verifiers to Solve Math Word Problems
- From Projection to Prediction: Beyond Logits for Scalable Language Models
- The Llama 3 Herd of Models
- The Curious Case of Neural Text Degeneration
- Approximate Top-$k$ for Increased Parallelism
- Online normalizer calculation for softmax
- FlashFormer: Whole-Model Kernels for Efficient Low-Batch Inference
- Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
- Qwen3 Technical Report
- Deep Kernel Fusion for Transformers
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks