VPG is a training-free inference-time guidance technique that improves autoregressive image and video generation by contrasting model outputs under generated versus corrupted prefixes to strengthen next-step support for the prefix.
author Feng, Y
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
LANG combines language-adaptive hint guidance, progressive decay, and difficulty-tailored learning horizons in RL to boost non-English reasoning performance while preserving language consistency.
Combines GRPO with teacher-guided on-policy distillation and introduces LongBlocks dataset to yield more stable long-context reasoning than either method alone.
DiffGap introduces adaptive alignment of denoising steps and temperature annealing in diffusion models for 3D molecule generation, reporting better docking scores and binding affinity than prior methods on CrossDocked2020.
citing papers explorer
-
VPG: Visual Prefix Guidance for Autoregressive Image and Video Generation
VPG is a training-free inference-time guidance technique that improves autoregressive image and video generation by contrasting model outputs under generated versus corrupted prefixes to strengthen next-step support for the prefix.
-
LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance
LANG combines language-adaptive hint guidance, progressive decay, and difficulty-tailored learning horizons in RL to boost non-English reasoning performance while preserving language consistency.
-
A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation
Combines GRPO with teacher-guided on-policy distillation and introduces LongBlocks dataset to yield more stable long-context reasoning than either method alone.
-
Bridging the Gap between Learning and Inference for Diffusion-Based Molecule Generation
DiffGap introduces adaptive alignment of denoising steps and temperature annealing in diffusion models for 3D molecule generation, reporting better docking scores and binding affinity than prior methods on CrossDocked2020.