We are excited to share that five papers from our group have been accepted by NeurIPS 2026:
- Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
- Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models
- Tool Verification for Test-Time Reinforcement Learning
- Evaluating Uncertainty Calibration in Probabilistic Time Series Foundation Models
- How to Train a Surgeon? Benchmarking Generalist Agents in Surgical Scene Understanding (Evaluations and Datasets Track)