Full Slides Released for ECCV'26 Tutorial on Diffusion Model Post-Training and Alignment
CSProfKGD · x · 2026-10-08
The ANU team (Liang Zheng, Zhanhao Liang, Shuchen Xue, Jie Liu) released complete slides for their ECCV 2026 half-day tutorial on aligning diffusion models with human preferences. It covers four method families — direct reward gradient backpropagation, DPO-style preference optimization, GRPO-based online RL, and forward-process RL — with core formulations, representative methods, strengths/limitations, and open challenges. A solid systematic entry point for visual generation alignment research.
More from Research
- FractAL introduces soft acquisition-strategy selection for batch-mode active learning — anshulkundaje · 2026-10-08
- DeLM's decentralized multi-agent system runs 2.49x faster, but MAS evals pick wildly different metrics — jyangballin · 2026-10-08
- Study: RAG retrieval diversification helps only on redundant multi-evidence pools, paper proposes per-query rule — _reachsumit · 2026-10-08
- Quantize by Drift: label-free mixed-precision quantization for text embedders hits 0.911 Spearman — _reachsumit · 2026-10-08
- RunningTab: environment-side task ledger consistently beats in-model tracking across 3 benchmarks and 3 LLMs — RexDouglass · 2026-10-08
- ColPali-style visual document indices can be inverted: 47% of words recovered, source page ranked first 98.4% — _reachsumit · 2026-10-08