Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training
Vision-language models (VLMs) enable embodied agents to reason and act from visual observations and language instructions. Reinforcement learning (RL) post-training enhances these capabilities using task feedback, but current on-policy RL runtimes execute rollout, reference scoring, and actor training in strict serial phases. While effective for text-only RL, this phase-granular execution is wasteful for VLMs, where processing dense video inputs and prompt prefixes occupies a large fraction of each phase. Because prefix processing is independent of the generated response, it can be run alongsi
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%VioletVision-3B →
“Fuzzy title match (0.73): “Rollplex: Cross-Phase GPU Spatial Sharing for Vision Languag” ≈ “VioletVision-3B””
- FuzzySimilar title/name (fuzzy) · 84%pytorch/vision →
“Fuzzy title match (0.92): “Rollplex: Cross-Phase GPU Spatial Sharing for Vision Languag” ≈ “pytorch/vision””
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- LinkedLinked via arxiv author · 85%Hanfeng Lu →
“Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training”
- LinkedLinked via arxiv author · 85%Tianyu Feng →
“Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training”
- LinkedLinked via arxiv author · 85%Suyi Li →
“Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training”
- LinkedLinked via arxiv author · 85%Yuheng Zhao →
“Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training”