5 articles on SOTA Papers
A chemistry-focused extension to MinerU converts document regions into molecule and reaction records, outperforming the evaluated GPT-5.6-Sol comparison on a SMILES benchmark subset.
A 300-task procedural suite replaces preference-only judging with task-specific scorers, raising matched reinforcement-learning performance from 0.509 to 0.548.
VBVR pairs 200 curated reasoning tasks with rule-based, human-aligned evaluation to study whether video models generalize across spatiotemporal reasoning problems.
A shared feed-forward memory and iterative attention reasoners retain comparable downstream scores while reducing continual-pretrained 35B-model inference time by nearly 4×.
Long-horizon trajectories, domain teachers, and routed on-policy distillation produce 56.4 on SEAL-0 and 80.6 on IFBench.
