arXiv:2609.13076v1 Announce Type: cross Abstract: Conversational voice agents have advanced significantly, offering increasingly natural human-machine interactions through both cascaded and end-to-end architectures. However, while recent benchmarks…
arXiv:2609.13072v1 Announce Type: cross Abstract: Fine-grained control of language model behaviors (e.g., steering) is among the more actionable outcomes of interpretability research. For binary concepts such as refusal, a single direction in…
arXiv:2609.13071v1 Announce Type: cross Abstract: Enterprise Digital Twins (EDTs) promise data-driven decision support at organizational scale, but realizing them requires navigating siloed departments, tacit knowledge, and high-stakes decisions…
arXiv:2609.13053v1 Announce Type: cross Abstract: Visual goal and dynamics prediction can provide language-conditioned robot policies with both a target outcome and a representation of action-dependent scene changes. We bring these predictions into…
arXiv:2609.13043v1 Announce Type: cross Abstract: Robust medical image segmentation across imaging modalities is challenging because of large differences in appearance and intensity distributions. Models trained on a single modality often show…
arXiv:2609.13042v1 Announce Type: cross Abstract: Deep learning models for dynamic survival analysis (DSA) achieve strong predictive performance by incorporating longitudinal patient data, but their black box nature limits clinical trust and…
arXiv:2609.13035v1 Announce Type: cross Abstract: Symmetries play a central role in reducing the complexity of reinforcement learning problems, yet most existing approaches rely on fixed group actions or predefined state abstractions. Classical…
arXiv:2609.13031v1 Announce Type: cross Abstract: With the recent rise and adoption of tabular foundation models, optimizing their inference performance becomes an emerging field for efficiency research. While the models are architecturally similar…
arXiv:2609.13024v1 Announce Type: cross Abstract: As a key model compression technique, knowledge distillation aims to transfer knowledge from a high-capacity teacher model to a lightweight student model for enhancing the latter's performance. In…
arXiv:2609.13013v1 Announce Type: cross Abstract: Flat roofs are among the most influential components of the building envelope, governing both structural performance and thermal efficiency, and thereby contributing directly to household energy…
arXiv:2609.13011v1 Announce Type: cross Abstract: Data-driven driving simulators command accelerations and steering rates from a fixed grid without constraining the realized accelerations and jerks. As a result, reinforcement-learning policies…
arXiv:2609.13005v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved strong performance on a wide range of natural language tasks, and recent benchmarks suggest that they are increasingly adept at multi-hop reasoning…
arXiv:2609.12978v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) creates a structural advantage for offloading: only a small fraction of activated experts need to reside in device memory, and if they can be loaded in time for computation…
arXiv:2609.12965v1 Announce Type: cross Abstract: Text-based person search (TBPS) aims to retrieve images of a target person from a large image gallery based on a given natural language description. Most existing methods rely on supervised learning…
arXiv:2609.12932v1 Announce Type: cross Abstract: Proposed governance framework for autonomous robotic systems, introducing a three-layer compliance architecture (ARC) instantiated through model safety validation, cognitive certification…
arXiv:2609.12915v1 Announce Type: cross Abstract: Large-scale multi-label text classification assigns a small subset of relevant labels to each document from a vocabulary containing thousands or tens of thousands of candidate labels. Although…
arXiv:2609.12898v1 Announce Type: cross Abstract: Fine-grained robotic manipulation depends on understanding parts, not only whole objects. Existing 3D foundation models tend to be either generalized but object-aware, or part-aware but limited to…
arXiv:2609.12896v1 Announce Type: cross Abstract: LLM-based agents rely on heterogeneous interaction capabilities to accomplish complex tasks. Existing approaches often distribute these capabilities across multiple LoRA adapters, which increases…
arXiv:2609.12890v1 Announce Type: cross Abstract: In autoregressive forecasting, long prediction rollouts provide distant supervision, but backpropagation through time (BPTT) carries gradients from those losses through many autoregressive steps…
arXiv:2609.12871v1 Announce Type: cross Abstract: Datasets are a crucial element in the development of perception algorithms. They relate sensor measurement data to annotated reference information and allow for the deduction of sensor and object…
arXiv:2609.12860v1 Announce Type: cross Abstract: Computed tomography (CT) and positron emission tomography (PET) provide complementary anatomical and functional information for cancer diagnosis and treatment planning. However, the widespread use…
arXiv:2609.12841v1 Announce Type: cross Abstract: Mapping observed system behavior to standardized frameworks like MITRE ATT&CK is essential for threat-informed defense, but remains largely manual. Existing automated methods depend on Cyber Threat…
arXiv:2609.12839v1 Announce Type: cross Abstract: The proliferation of highly capable open-weight Small Language Models (SLMs) democratizes access to advanced cybersecurity capabilities, posing a escalating risk as these models can bypass…
arXiv:2609.12818v1 Announce Type: cross Abstract: Long video understanding often behaves like a visual needle-in-a-haystack problem: query-relevant evidence is sparsely distributed across long temporal spans, while packing dense frames into a…
Pick what should wake you up. We only push stories the AI rates as genuinely urgent.