Generative Verifiers: Reward Modeling as Next-Token Prediction
Lunjun Zhang, Arian Hosseini, Hritik Bansal, Mehran Kazemi, Aviral Kumar, Rishabh Agarwal
Who it is from
- University of California, Los Angelesaffiliation declared by the authors, according to OpenAlex
- University of Torontoaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- AI models collapse when trained on recursively generated dataUniversity of Toronto · 2,565 citations
- Mastering diverse control tasks through world modelsUniversity of Toronto · 2,495 citations
- PixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D ReconstructionMassachusetts Institute of Technology · 966 citations
- $τ^2$-Bench: Evaluating Conversational Agents in a Dual-Control EnvironmentUniversity of Toronto · 862 citations
- ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and PlanningUnited States Army Combat Capabilities Development Command · 834 citations
- Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature FieldsUnited States Army Combat Capabilities Development Command · 607 citations