arXiv:2607.26203v1 Announce Type: new Abstract: Video shadow removal in the wild remains challenging due to complex illumination, diverse shadow appearances, and limited training data. Despite its…
arXiv:2607.26654v1 Announce Type: cross Abstract: Post-training alignment is often shallow, eroding under fine-tuning. Whether midtraining interventions, cleanly isolated from post-training, can produce durable alignment remains untested.…
arXiv:2607.26278v1 Announce Type: new Abstract: It is common for two-dimensional embeddings of high-dimensional data to be read far beyond what they can support. Distances in and…
arXiv:2504.19621v2 Announce Type: replace-cross Abstract: Machine learning (ML) systems for medical imaging have demonstrated remarkable diagnostic capabilities, but their susceptibility to biases poses significant risks, since…
arXiv:2607.26285v1 Announce Type: cross Abstract: Two central challenges in diffusion-based sampling are the theoretical one of understanding their remarkable effectiveness even in high-dimensional settings, and the…
arXiv:2607.20833v2 Announce Type: replace Abstract: Large Language Models (LLMs) increasingly leverage long-form reasoning to solve complex tasks, yet their reasoning processes can deviate from the provided…
arXiv:2106.16038v3 Announce Type: replace Abstract: Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant syntax…
arXiv:2607.26170v1 Announce Type: new Abstract: This study developed a hybrid computer vision method to quantify exposed skin from images for dermal exposure assessment. Using 170 indoor-painting…
arXiv:2607.24237v2 Announce Type: replace Abstract: Many existing clustering methods are designed based on a set-oriented definition---a cluster is a set of similar points---relying a point-to-point similarity…
arXiv:2603.10046v2 Announce Type: replace Abstract: Wearable sensors in Internet of Things (IoT) ecosystems increasingly support applications such as remote health monitoring, elderly care, and smart home…
arXiv:2601.07687v3 Announce Type: replace-cross Abstract: Recent advances in nonlinear shrinkage yield asymptotically optimal cleaners for large covariance matrices and have been extended to empirical cross-covariances via…
arXiv:2605.16836v2 Announce Type: replace Abstract: Hypergraphs provide a principled framework for modeling polyadic interactions, with applications in recommendation systems, social networks, and molecular modeling. Hypergraph generation…
arXiv:2510.08543v2 Announce Type: replace-cross Abstract: As Video Large Language Models (VideoLLMs) are deployed globally, it is important to assess their ability to reason across cultural contexts.…
arXiv:2607.26355v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly embedded in everyday life and widely used for information seeking, raising concerns about their potential…
arXiv:2607.26165v1 Announce Type: new Abstract: Safe autonomous navigation requires a holistic understanding of dynamic environments, necessitating the simultaneous estimation of metric depth, semantic segmentation, and instance…
arXiv:2603.05710v2 Announce Type: replace-cross Abstract: AI development's current trajectory risks automating and amplifying the North-South divide in the global climate information system. Frontier models are built…
arXiv:2607.26298v1 Announce Type: new Abstract: We built and evaluated a self-serve entity resolution (ER) system on six benchmarks spanning 864 to 5M records, and three lessons…
arXiv:2605.09075v2 Announce Type: replace Abstract: Although the Laplace approximation offers a simple route to uncertainty quantification in deep neural networks, its reliance on inverting large Hessian…
arXiv:2607.26309v1 Announce Type: cross Abstract: Estimating causal effects of linguistic properties from observational text is difficult because the same document can contain both the treatment of…
arXiv:2603.06114v2 Announce Type: replace Abstract: Real-world arguments in text and dialogues are normally enthymemes (i.e. some of their premises and/or claims are implicit). Natural language processing…
arXiv:2512.24149v2 Announce Type: replace Abstract: The world is governed by both physical laws and affective dynamics. Physical laws govern state transitions, while affective dynamics shape human…
arXiv:2607.26107v1 Announce Type: new Abstract: Dense vision-language understanding, including object localization, region recognition, and open-vocabulary semantic segmentation, requires associating language concepts with spatially grounded visual regions.…
arXiv:2509.05130v2 Announce Type: replace Abstract: In classification problems, models are trained to predict a class label based on the input data features. However, class labels are…
arXiv:2607.20656v3 Announce Type: replace Abstract: Effective decision-making in complex and changing environments requires balancing short-term and long-term consequences. In reinforcement learning (RL), this trade-off is typically…