arXiv:2607.28935v1 Announce Type: new Abstract: Recently, 3D semantic occupancy prediction has garnered increasing attention for understanding the indoor scene. However, unlike structured outdoor environments, indoor scenes…
arXiv:2607.28670v1 Announce Type: new Abstract: A stochastic Gumbel-Top-$K$ router defines, for every token of a mixture-of-experts (MoE) model, a emph{routing law}: a distribution over ordered expert…
arXiv:2607.29116v1 Announce Type: new Abstract: Genetic Programming Symbolic Regression (GPSR) generates mathematical expressions to model input-output relationships using an evolutionary process. A significant challenge in GPSR…
arXiv:2607.28861v1 Announce Type: cross Abstract: The parametric score test assesses a hypothesis through derivatives of the log-likelihood, whose expectation vanishes under the null. When the parameter…
arXiv:2607.28677v1 Announce Type: new Abstract: LLM now pass medical licensing examinations and, in curated cases, can rival physicians at diagnostic reasoning. These developments have accelerated the…
arXiv:2607.28641v1 Announce Type: new Abstract: We introduce the textit{Agentic Formalism Trap} and the Evaluative Dissonance Index ($D_E$), quantifying how LLM-as-a-Judge systems conflate structural proceduralism with semantic…
arXiv:2508.13187v5 Announce Type: replace-cross Abstract: Homelessness is a persistent social challenge, impacting millions worldwide. Over 876,000 people experiencing homelessness (PEH) were recorded in the U.S. in…
arXiv:2607.23855v2 Announce Type: replace-cross Abstract: Recent generative models are moving beyond silent video or standalone audio synthesis toward the joint generation of synchronized audio and video.…
arXiv:2607.28669v1 Announce Type: new Abstract: We present LARA (Lightweight Additive Residual Adaptation), a method for efficient adaptation that operates in the residual stream of a frozen…
arXiv:2607.28663v1 Announce Type: new Abstract: Artificial Intelligence (AI) systems often perform well on isolated tasks but struggle under continual learning conditions, where training on new tasks…
arXiv:2211.11278v3 Announce Type: replace Abstract: Nearest neighbour classification is attractive for tabular data, but its performance can deteriorate when a fixed query centred neighbourhood does not…
arXiv:2607.29491v1 Announce Type: cross Abstract: Reinforcement-learning-based quantum architecture search (RL-QAS) repeatedly optimizes a variational quantum eigensolver (VQE) after extending a circuit, although circuit construction and action…
arXiv:2607.28658v1 Announce Type: new Abstract: Federated pre-training offers a way to train foundation models on private or distributed data without centralizing the underlying datasets. However, evaluating…
arXiv:2602.03811v3 Announce Type: replace Abstract: A key challenge in autoregressive image generation is to efficiently sample independent locations in parallel, while still modeling mutual dependencies with…
arXiv:2607.28936v1 Announce Type: new Abstract: Facial biometric identification relies on the distinctiveness of user attributes within a high-dimensional embedding space. However, the decision boundaries of deep…
arXiv:2607.28667v1 Announce Type: new Abstract: Recent work has shown that classifying large language models (LLMs)' responses can be distinguished by modeling token embeddings as trajectories of…
arXiv:2510.11711v3 Announce Type: replace-cross Abstract: This paper proposes a synergy of amortised and particle-based methods for sampling from distributions defined by unnormalised density functions. We state…
arXiv:2607.28894v1 Announce Type: cross Abstract: Computational cognitive modeling seeks to infer latent cognitive mechanisms underlying observed behavior. Bayesian inverse planning provides a principled framework for such…
arXiv:2605.06938v2 Announce Type: replace-cross Abstract: Recently Brown et al. [2025] established a singular value decomposition (SVD) for maps (especially nonlinear) satisfying certain norm conditions. We prove…
arXiv:2607.28678v1 Announce Type: new Abstract: Multimodal agents operating in long-horizon environments must build and continually update multimedia memories to support entity-consistent, temporally grounded reasoning. However, existing…
arXiv:2607.28639v1 Announce Type: new Abstract: We show that knowledge distillation in small instruction-tuned language models has asymmetric effects on bias. On unambiguous tasks (BBQ-disambig), response-based distillation…
arXiv:2603.23413v2 Announce Type: replace Abstract: Despite remarkable progress in video generation, maintaining long-term scene consistency upon revisiting previously explored areas remains challenging. Existing solutions rely either…
arXiv:2607.28855v1 Announce Type: cross Abstract: Dense 3D sensors in various real-world fields produce point clouds that are geometrically redundant for real-time processing. In this paper, we…
arXiv:2607.29462v1 Announce Type: cross Abstract: Adapting deep learning models to profound clinical heterogeneity typically relies on parameter-efficient fine-tuning (PEFT) to avoid the severe overfitting associated with…