arXiv:2603.10101v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capacity of Large Language Models (LLMs). However, RLVR solely relies on final answers as outcome rewards, neglecting the correctness of intermediate reasoning steps. Training…
arXiv:2603.11042v1 Announce Type: cross Abstract: Generating music that temporally aligns with video events is challenging for existing text-to-music models, which lack fine-grained temporal control. We introduce V2M-Zero, a zero-pair video-to-music generation approach that outputs time-aligned music for video. Our method…
arXiv:2603.10123v1 Announce Type: new Abstract: The “Lost in the Middle” phenomenon — a U-shaped performance curve where LLMs retrieve well from the beginning and end of a context but fail in the middle — is widely attributed to learned Softmax…
arXiv:2410.02113v3 Announce Type: replace Abstract: Partial differential equations (PDEs) are widely used to model complex physical systems, but solving them efficiently remains a significant challenge. Recently, Transformers have emerged as the preferred architecture for PDEs due to their ability to…
MIT astronomers are developing a new way to detect, monitor, and mitigate the threats posed by smaller asteroids to our critical space infrastructure.
arXiv:2410.08727v2 Announce Type: replace-cross Abstract: Diffusion models power leading generative AI, but when and how they memorize training data, especially on low-dimensional manifolds, remains unclear. We find memorization emerges gradually, not abruptly: as data become scarce, diffusion models experience a…
arXiv:2510.23914v2 Announce Type: replace Abstract: While Value Iteration (VI) is one of the most fundamental algorithms in Reinforcement Learning, its theoretical convergence guarantees still exhibit a persistent mismatch with empirical behavior. In the discounted-reward case, classical theory guarantees geometric convergence…
arXiv:2602.09375v3 Announce Type: replace Abstract: We propose LaPha, a method for training AlphaZero-like LLM agents in a Poincar’e latent space. Under LaPha, the search process can be visualized as a tree rooted at the prompt and growing outward from the…
arXiv:2603.10886v1 Announce Type: cross Abstract: We propose novel kernel-based tests for assessing the equivalence between distributions. Traditional goodness-of-fit testing is inappropriate for concluding the absence of distributional differences, because failure to reject the null hypothesis may simply be a result…
arXiv:2504.04371v3 Announce Type: replace Abstract: Traditional Support Vector Machine (SVM) classification is carried out by finding the max-margin classifier for the training data that divides the margin space into two equal sub-spaces. This study demonstrates limitations of performing Support Vector…
