OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies Paper • 2607.03723 • Published 25 days ago • 5
Skip a Layer or Loop It? Learning Program-of-Layers in LLMs Paper • 2606.06574 • Published Jun 4 • 25
Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning Paper • 2606.01682 • Published Jun 1 • 7
Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing Paper • 2602.03845 • Published Feb 3 • 27
TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models Paper • 2601.18744 • Published Jan 26 • 11