arXiv:2605.25303v3 Announce Type: replace-cross Abstract: The $2 rightarrow q$ norm of a matrix $X in mathbb{R}^{n times d}$ is defined as $lVert X rVert_{2 rightarrow q}…
arXiv:2608.02691v1 Announce Type: new Abstract: The key-value (KV) cache has become a major memory and bandwidth bottleneck in long-context large language model inference, making ultra-low-bit quantization…
arXiv:2510.10350v3 Announce Type: replace-cross Abstract: Operator learning provides a data-driven approach to approximating solution operators of partial differential equations, but its effectiveness depends strongly on how…
arXiv:2608.02632v1 Announce Type: new Abstract: Circuit tracing is an exciting technique for revealing the internal computation of language models, but it requires a time-intensive manual step…
arXiv:2608.02633v1 Announce Type: new Abstract: Regional surveillance data reflect local transmission, reporting, seeding, and external infection pressure, which are difficult to identify separately. We introduce GeoID-PINN,…
arXiv:2608.02662v1 Announce Type: new Abstract: Reliable forecasting of nonlinear physical systems underpins scientific discovery and engineering decision-making. Yet high-fidelity simulations are prohibitively costly, and machine-learning surrogates…
arXiv:2608.02668v1 Announce Type: new Abstract: Residual connections are the de facto mechanism for training deep neural networks stably. Geodesic Normalization (GeoNorm) recasts them on a Riemannian…
arXiv:2608.02663v1 Announce Type: new Abstract: Accurate ICU mortality prediction requires modeling irregular clinical observations across heterogeneous entity types. Existing sequence models handle irregular sampling but ignore…
arXiv:2608.02690v1 Announce Type: new Abstract: On-device training of deep neural networks is fundamentally constrained by the computational and memory costs of large-scale datasets. Coreset selection offers…
arXiv:2608.02688v1 Announce Type: new Abstract: Phenotypic drug discovery enables the discovery of functional relationships between molecular structures and cellular responses. However, existing multimodal representation learning methods…
arXiv:2608.03566v1 Announce Type: cross Abstract: The drift diffusion model (DDM) is a cornerstone of cognitive decision-making research. Although numerous estimation methods exist, researchers continue to seek…
arXiv:2607.23258v2 Announce Type: replace-cross Abstract: Large-scale calcium imaging has created an opportunity to build foundation-style models for neural population dynamics, but a central question remains unresolved:…
arXiv:2507.07754v3 Announce Type: replace Abstract: Machine unlearning is usually evaluated by what the classifier outputs: forget-set accuracy, confidence, membership-inference scores. We show that this is not…
arXiv:2608.03874v1 Announce Type: cross Abstract: Modern agent frameworks equip large language models with external skill libraries to solve complex tasks. However, it remains unclear whether these…
arXiv:2606.05799v2 Announce Type: replace Abstract: Existing calibration methods for Large Language Models (LLMs) often overlook a critical dimension of trustworthiness: a model's behavioral robustness to irrelevant…
arXiv:2602.01997v3 Announce Type: replace Abstract: Recent work has shown that layer pruning can effectively compress large language models (LLMs) while retaining strong performance on classification benchmarks,…
arXiv:2607.27203v2 Announce Type: replace Abstract: Pre-training followed by fine-tuning has become the dominant recipe for learning performant policies, and in value-based reinforcement learning (RL) this raises…
arXiv:2607.26097v2 Announce Type: replace Abstract: Action recognition in complex scenes often involves multiple concurrent fine-grained actions, making it challenging to model internal action structures. Most existing…
arXiv:2608.02892v1 Announce Type: new Abstract: Scene Graph Generation (SGG) is fundamental to structured visual understanding, yet existing benchmarks focus mainly on daily life images and overlook…
arXiv:2604.27975v2 Announce Type: replace Abstract: Traditional Shot Boundary Detection (SBD) inherently struggles with complex transitions by formulating the task around isolated cut points, frequently yielding corrupted…
arXiv:2608.02883v1 Announce Type: new Abstract: 3D point cloud registration in laparoscopic surgery estimates the transformation between an intraoperative organ reconstructed from video and its preoperative mesh.…
arXiv:2512.23953v2 Announce Type: replace Abstract: The rapid evolution of Text-to-Video (T2V) diffusion models has driven remarkable advancements in generating high-quality, temporally coherent videos from natural language…
arXiv:2608.02841v1 Announce Type: new Abstract: Ask a commercial image editor to preview a cosmetic procedure and it will often change more of the face than the…
arXiv:2502.06606v3 Announce Type: replace Abstract: Manipulating the material appearance of objects in images is critical for applications like augmented reality, virtual prototyping, and digital content creation.…