arXiv:2603.21877v3 Announce Type: replace-cross
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) enhances Large Language Model (LLM) reasoning but suffers from advantage collapse on “hard samples” where all rollouts fail. This lack of…
arXiv:2604.06269v2 Announce Type: replace-cross
Abstract: Automated single-cell annotation is difficult when the most abundant genes are not the most discriminative ones, or when a target state is poorly covered by a fixed reference atlas. GPTCelltype…
arXiv:2605.05460v1 Announce Type: new
Abstract: The development of accurate exchange-correlation (XC) functionals remains a longstanding challenge in density functional theory (DFT). The vast majority of XC functionals have been hand designed by human…
arXiv:2605.06055v1 Announce Type: cross
Abstract: Mixture-of-Experts (MoE) inference requires large-scale token exchange across devices, making dispatch and combine major bottlenecks in both prefill and decode. Beyond network transfer, routing-driven …
arXiv:2604.26799v2 Announce Type: replace
Abstract: 3D Gaussian Splatting (3DGS) achieves high-quality novel view synthesis with real-time rendering, but its storage cost remains prohibitive for practical deployment. Existing post-training compression…
arXiv:2605.06460v1 Announce Type: new
Abstract: Visual document retrieval has become essential for accessing information in visually rich documents. Existing approaches fall into two camps. Late-interaction retrievers achieve strong quality through fi…
arXiv:2605.05957v1 Announce Type: new
Abstract: LLMs reliably correct false claims when presented in isolation, yet when the same claims are embedded in task-oriented requests, they often comply rather than correct. We term this failure mode \emph{cor…
arXiv:2605.06667v1 Announce Type: cross
Abstract: For artistic applications, video generation requires fine-grained control over both performance and cinematography, i.e., the actor’s motion and the camera trajectory. We present ActCam, a zero-shot me…
arXiv:2605.06130v1 Announce Type: new
Abstract: A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant skill, ut…
arXiv:2605.06407v1 Announce Type: cross
Abstract: Integrating speech understanding and generation is a pivotal step toward building unified speech models. However, the different representations required for these two tasks currently pose significant c…