[CL] Multipole Attention for Efficient Long Context Reasoning [UC Berkeley] https://arxiv.org/abs/2506.13059

[CL] Direct Reasoning Optimization：LLMs Can Reward And Refine Their Own Reasoning for Open-Ended Tasks [Microsoft] https://arxiv.org/abs/2506.13351

[LG] Verifying the Verifiers：Unveiling Pitfalls and Potentials in Fact Verifiers [Yonsei University & Stanford University & University of Washington] https://arxiv.org/abs/2506.13342

[CL] Refract ICL：Rethinking Example Selection in the Era of Million-Token Models [Google DeepMind] https://arxiv.org/abs/2506.12346

人生的智慧不在于追求一步到位的完美答案，而在于始终为自己保留更多的选择权和可能性。

[LG] Spectral Estimation with Free Decompression [UC Berkeley & University of Melbourne] https://arxiv.org/abs/2506.11994

[LG] TreeRL: LLM Reinforcement Learning with On-Policy Tree Search [Tsinghua University & California Institute of Technology] https://arxiv.org/abs/2506.11902

[CL] Large Language Models and Emergence: A Complex Systems Perspective [Santa Fe Institute] https://arxiv.org/abs/2506.11135

[LG] Tversky Neural Networks: Psychologically Plausible Deep Learning with Differentiable Tversky Similarity [Stanford University] https://arxiv.org/abs/2506.11035

[CL] You Only Fine-tune Once：Many-Shot In-Context Fine-Tuning for Large Language Model [Google & University of Florida] https://arxiv.org/abs/2506.11103

现代人的焦虑很大程度源于不断的比较。我们习惯用别人的成就来衡量自己，这种"比较"就像快乐的小偷，偷走了本该属于我们的幸福感。

[CL] Draft-based Approximate Inference for LLMs [FuriosaAI & UW-Madison] https://arxiv.org/abs/2506.08373