AIBullisharXiv – CS AI · Jun 107/10
🧠Researchers introduce Entropy-Guided Power Sampling (EGPS), a novel training-free sampling method that accelerates reasoning in base language models by targeting high-entropy decision points rather than uniformly sampling across sequences. The technique achieves up to 12.6x speedup on mathematical and coding benchmarks while maintaining or improving accuracy, addressing fundamental inefficiencies in existing MCMC sampling approaches.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduce Entropy-Cut Metropolis-Hastings, an algorithm that improves sampling from power distributions in language models by identifying key decision points using entropy analysis rather than random sampling positions. The method achieves stronger reasoning performance across multiple benchmarks without requiring additional training or reinforcement learning.
AIBullisharXiv – CS AI · May 277/10
🧠Researchers demonstrate that stochasticity in discrete diffusion models provides an error-correcting mechanism that improves the speed-quality tradeoff in generative AI. They propose Discrete Churn and Restart Sampling (DCRS), which achieves up to 10x faster sampling on images while maintaining quality by strategically injecting controlled randomness into the inference process.
AIBullisharXiv – CS AI · May 277/10
🧠Researchers introduce Qrita, an efficient algorithm for Top-k and Top-p sampling in large language models that uses pivot-based truncation instead of sorting. The method achieves 1.4x throughput improvements with 50% less memory usage while maintaining identical output to traditional sorting approaches, and has been adopted as the default sampler in vLLM.
AINeutralarXiv – CS AI · Jun 116/10
🧠Researchers formalize test-time training (TTT) as a theoretical framework for sampling from complex probability distributions, proving that the Jerrum-Sinclair random walk approach is query-optimal with a quadratic lower bound. The work bridges generative AI sampling efficiency with classical algorithmic theory, establishing foundational principles for adapting language models during inference.
AIBullisharXiv – CS AI · Jun 106/10
🧠Researchers propose ADAS, a training-free reranking algorithm that improves parallel token decoding in masked diffusion language models by using attention weights as soft penalties to avoid committing to correlated predictions simultaneously. The method achieves 9-10 percentage point improvements on benchmarks like GSM8K and HumanEval with minimal computational overhead, advancing the efficiency of faster language model inference.
AINeutralarXiv – CS AI · Jun 56/10
🧠Researchers establish a mathematical correspondence between score-based diffusion models and quantum adiabatic transport, revealing that sampling performance is fundamentally limited by the ratio of score-matching error to spectral gap. This theoretical breakthrough provides new bounds for density reconstruction and principled methods for designing annealing schedules in generative AI systems.
