LRM早停换判据省26%token

重点关注

• Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models score 9
  入选 HF Daily Papers；HF 热度: 18 upvotes (+3)；有代码实现；关键词(5): lightweight, latency, code generation, reasoning, vision-language
• LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs score 9
  入选 HF Daily Papers；HF 热度: 19 upvotes (+3)；有代码实现；关键词(3): scaling, distillation, latency

也值得关注

• Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided Pruning score 4
  关键词(2): scaling, pruning；顶会接收: ICML
• Olivia: Harmonizing Time Series Foundation Models with Power Spectral Density score 4
  关键词(1): pretraining；顶会接收: ICML
• Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment score 4
  关键词(2): RLHF, synthetic data；顶会接收: ICML
• Beyond Detection: A Structure-Aware Framework for Scene Text Tracking score 3
  顶会接收: ICML
• A Hybrid Gaussian Process Regression Framework for Stable Volatility-Covariance Estimation: Evidence from Global Equity Indices score 3
  机构: Google
• UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models score 3
  顶会接收: ICLR