arXiv:2604.20329v2 Announce Type: replace-cross
Abstract: Recent works show that image and video generators exhibit zero-shot visual understanding behaviors, in a way reminiscent of how LLMs develop emergent capabilities of language understanding and …
arXiv:2605.14381v1 Announce Type: new
Abstract: Recent advancements in generative AI facilitate large-scale synthetic data generation for model evaluation. However, without targeted approaches, these datasets often lack the sociotechnical nuance requi…
arXiv:2605.14597v1 Announce Type: new
Abstract: Precipitation nowcasting is a vital spatio-temporal prediction task for meteorological applications but faces challenges due to the chaotic property of precipitation systems. Existing methods predominant…
arXiv:2601.02179v2 Announce Type: replace
Abstract: While confidence estimation is a promising direction for mitigating hallucinations in Large Language Models (LLMs), current research overwhelmingly focuses on single-turn settings. The dynamics of mo…
arXiv:2605.14907v1 Announce Type: new
Abstract: Knowledge graph (KG) foundation models aim to generalize across graphs with unseen entities and relations by learning transferable relational structure. However, most existing methods primarily emphasize…
arXiv:2605.01725v2 Announce Type: replace-cross
Abstract: Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential iterative deno…
arXiv:2605.12288v2 Announce Type: replace-cross
Abstract: Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences over full sequences even though generation…
arXiv:2604.18419v3 Announce Type: replace-cross
Abstract: LLMs utilizing chain-of-thought reasoning often waste substantial compute by producing long, incorrect responses. Abstention can mitigate this by withholding outputs unlikely to be correct. Whi…
arXiv:2605.14606v1 Announce Type: new
Abstract: Accurate precipitation nowcasting over extended horizons (0-3 hours) is essential for disaster mitigation and operational decision-making, yet remains a critical challenge in the field. Existing determin…
arXiv:2605.14061v1 Announce Type: new
Abstract: Current autoformalization benchmarks are largely focused on olympiad or undergraduate mathematics, while graduate and research-level mathematics remains underexplored. In this paper, we introduce MathAtl…