JoVox: joint flow matching yields 8x training throughput, 1/15 FLOPs
KAUST · hf · 2026-11-10
KAUST researchers proposed JoVox, a discrete flow matching framework for lightweight voxel generation that learns the joint distribution of all hierarchy levels instead of per-level distributions, letting finer cells inform coarse-cell predictions. A two-level prediction halves the processed levels, plus an unmasking strategy revisits early decisions. Versus SOTA TRELLIS.2: 8x higher training throughput, 1/15 forward FLOPs, training on 4 vs 32 GPUs, and 11% lower Chamfer distance.
More from Multimodal
- Generating game music with Fable 5.2 in just 3 prompts — petergyang · 2026-11-10
- Video-Coder trains a coding agent for video generation, gaining 24+ points on PhyGenBench — HuaxiuYaoML · 2026-11-10
- Open-H3-Regenerate-2K: open 3-step video refinement up to 4K, 5x faster than MiniMax API — songhan_mit · 2026-11-10
- Open-source Gemini Flash Image MCP Server adds text-to-image and editing to agents — modelcontextprotocol · 2026-11-10
- Agent draws an oriole's nest stroke by stroke: Fable 5.2's first hand-drawn piece uses 30,000 marks — RileyRalmuto · 2026-11-10
- One-shot WW2 shooter with destructible environments wows users as Spawn adopts Fable 5.2 — TAbrodi · 2026-11-10