Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening
-
Updated
May 18, 2025 - Python
Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening
[NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection
Stable Latent Reasoning --- Enhancing Inference in Large Language Models through Iterative Latent Space Refinement
Implemented a recurrent-depth LLM (PyTorch) based on arXiv:2502.05171. Demonstrated that scaling inference compute increased arithmetic reasoning accuracy from 8% to 100% without additional parameters.
ReasonForge — Interactive Test-Time Compute Laboratory. Live scaling curves, MCTS+PRM, Tree-of-Thoughts, Best-of-N verifier, Self-Refine reward-hacking — all on the Game-of-24 benchmark.
Deep Research capability with reasoning models, CoT prompting, and inference-time scaling
Add a description, image, and links to the inference-scaling topic page so that developers can more easily learn about it.
To associate your repository with the inference-scaling topic, visit your repo's landing page and select "manage topics."