Sipeng Zhang
2 papers · Latest:
Artificial Intelligence
Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
ScaleLogic, a new framework, reveals RL-trained LLMs' compute scales with reasoning depth, with expressiveness impacting the scaling exponent.
2605.06638
Computer VisionAsset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation
Asset Harvester extracts complete 3D object assets from sparse autonomous driving logs, enabling scalable simulation for AV development.
2604.18468
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.