Knowledge catalogue
arXiv:2609.34985v1 Announce Type: new Abstract: Multi-reward policy optimization requires a joint update that reflects both the learning signals and the intended relationships among objectives. We int
arXiv:2609.33194v1 Announce Type: new Abstract: Matrix-valued optimizers such as Muon exploit the spectral structure of neural network updates through Newton--Schulz orthogonalization, but their near-
arXiv:2609.33543v1 Announce Type: cross Abstract: Coupled rollouts can reduce the noise of counterfactual action comparisons, but two issues prevent standard common-random-number constructions from se
Our Secure Intelligence Institute works with researchers at Stanford, CMU, Duke, Columbia, Ohio State, and UVA. We’re also working with NVIDIA and the Open Secure AI Alliance, and sharing tools and fi
arXiv:2609.35579v1 Announce Type: new Abstract: Residual stream pruning methods reduce inference cost by shrinking the model's hidden dimension, but existing approaches typically choose these dimensio
arXiv:2609.32832v1 Announce Type: new Abstract: Over-the-air computation has emerged as a scalable and efficient solution for deploying federated learning algorithms in wireless networks by exploiting
arXiv:2609.32270v1 Announce Type: cross Abstract: We study the generalization of spectral gradient descent (SpecGD) in overparameterized matrix classification with corrupted labels. Each input combine
arXiv:2603.21877v4 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) enhances Large Language Model (LLM) reasoning but is suffer from advantage collapse: when all
arXiv:2609.34391v1 Announce Type: cross Abstract: AIVC (AI Virtual Cell) is a learned simulator of cellular behavior across conditions. Predicting how a cell population responds transcriptionally to a
arXiv:2609.34867v1 Announce Type: new Abstract: Vision language models have achieved strong performance across a wide range of multimodal applications, yet their substantial computational and memory c
arXiv:2609.34487v1 Announce Type: new Abstract: Radiology report generation (RRG) increasingly incorporates heterogeneous clinical evidence, such as multi-view radiographs and previous reports, whose
arXiv:2512.18291v3 Announce Type: replace Abstract: Object detection in aerial imagery is challenging because targets are often small, backgrounds are cluttered, and imaging conditions vary substantia
arXiv:2609.31651v1 Announce Type: new Abstract: Historical manuscripts remain largely absent from modern vision-language benchmarks, leaving open how well multimodal large language models (MLLMs) hand
arXiv:2609.31717v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies have shown promising performance in language-conditioned robotic manipulation. However, most existing VLA systems
arXiv:2609.31780v1 Announce Type: new Abstract: Modern text-to-image models produce high-fidelity images but still struggle with compositional prompts that require instance identity, attribute ownersh
arXiv:2609.34759v1 Announce Type: new Abstract: Recent vision-language models (VLMs) have advanced vision-and-language navigation (VLN), enabling models to predict navigation actions from visual obser
arXiv:2609.31716v1 Announce Type: new Abstract: Persistent semantic occupancy mapping is essential for embodied scene understanding. However, perspective-based systems provide limited spatial coverage
arXiv:2609.33077v1 Announce Type: new Abstract: Three-dimensional dense convolutional networks are the strongest performers on volumetric medical image segmentation, but their parameter counts scale p
arXiv:2609.33236v1 Announce Type: new Abstract: Training-free online video anomaly detection (VAD) with frozen multimodal language models faces two coupled challenges: extracting reliable current-wind
arXiv:2509.23235v2 Announce Type: replace Abstract: Model inversion is a widely adopted technique in data-free learning that reconstructs synthetic inputs from a pretrained model through iterative opt
arXiv:2609.31803v1 Announce Type: new Abstract: Autonomous navigation in dynamic environments is a critical challenge, particularly when spaces are shared with other mobile agents whose future traject
arXiv:2603.15688v2 Announce Type: replace-cross Abstract: Background: Lung-sound classifiers are usually evaluated on recording- or event-level splits, although each child contributes many recordings.
arXiv:2601.22132v2 Announce Type: replace Abstract: Large Language Models (LLMs) deliver state-of-the-art performance on complex reasoning tasks, but their inference costs limit deployment at scale. S
arXiv:2609.35768v1 Announce Type: new Abstract: Modern video diffusion models require tens of denoising evaluations over long spatiotemporal token sequences. Distribution Matching Distillation (DMD) r
arXiv:2609.31742v1 Announce Type: new Abstract: Normal-inverse-gamma (NIG) regression is not identifiable from its marginal Student-t likelihood: three combinations of four NIG parameters are determin
arXiv:2609.35054v1 Announce Type: cross Abstract: Contemporary deep speech enhancement (SE) models are often trained with specific auxiliary terms in the loss function as a way to improve their perfor
arXiv:2609.32094v1 Announce Type: cross Abstract: Temporal dynamics in learning behavior can be revealed through period segmentation in Transition Network Analysis (TNA). Cristea et al. demonstrated t
arXiv:2609.32833v1 Announce Type: new Abstract: A trained neural network can be represented by a parameter vector in high dimensions. Learning distributions over these vectors enables the generation o
arXiv:2609.35402v1 Announce Type: new Abstract: When pricing agents meet repeatedly on a platform, the platform decides who faces whom. We ask whether that choice moves the prices the agents learn, an
arXiv:2609.33171v1 Announce Type: cross Abstract: Latent diffusion models serve as powerful priors for solving inverse problems in image restoration, such as deblurring, inpainting, and super-resoluti
arXiv:2601.04692v2 Announce Type: replace-cross Abstract: In this work, we examine hateful memes from three complementary angles - how to detect them, how to explain their content and how to intervene
arXiv:2609.32634v1 Announce Type: new Abstract: Reinforcement Fine-Tuning~(RFT) has emerged as a promising paradigm for improving Vision-Language-Action~(VLA) policies, yet sparse task-level outcomes
arXiv:2609.33558v1 Announce Type: new Abstract: 3D Visual Query Localization (3DVQL) retrieves the latest contiguous occurrence of a queried object in an RGB--point-cloud sequence and predicts a 9-DoF
arXiv:2609.32319v1 Announce Type: new Abstract: We circumvent the Sanford-Hsu-Telgarsky (SHT) single-layer induction obstruction within a linear, one-step, causal, bilinear, symplectically consistent
arXiv:2609.32928v1 Announce Type: new Abstract: Millimeter-wave (mmWave) radar and RGB-D cameras can record cardiac and respiratory waveforms continuously and without contact, but labeled recordings r
arXiv:2609.31855v1 Announce Type: new Abstract: Human demonstrations provide dense policy-level information but sometimes lack local precision. Human feedback presents accurate local critiques, but of
arXiv:2609.34804v1 Announce Type: cross Abstract: Federated learning enables industrial operators to train shared intrusion detection models without disclosing proprietary operational telemetry. Howev
arXiv:2609.35499v1 Announce Type: new Abstract: As the world moves towards sustainable energy sources, hydrogen (H2) can be treated as an eco-friendly alternative to fossil fuels due to its high energ
arXiv:2609.34795v1 Announce Type: new Abstract: Underwater image enhancement is crucial for improving visual perception in marine applications. Existing underwater image enhancement studies mainly foc
arXiv:2609.34916v1 Announce Type: cross Abstract: Accurate prediction of avalanche motion is essential for hazard assessment in mountainous terrain. This study develops and evaluates a physics-informe
arXiv:2603.02231v2 Announce Type: replace Abstract: Large-scale wave field reconstruction requires precise solutions but faces challenges with computational efficiency and accuracy. The physics-based
arXiv:2609.34466v1 Announce Type: new Abstract: Physiological foundation models encode how a signal was recorded alongside the physiology it reflects. When recording conditions are associated with dia
arXiv:2609.33857v1 Announce Type: new Abstract: Recovering hidden transport mechanisms from sparse spatiotemporal observations is a fundamental inverse problem in scientific machine learning. In brain
arXiv:2609.33318v1 Announce Type: new Abstract: Underwater image enhancement (UIE) aims to restore visibility, color fidelity, and structural detail from images degraded by wavelength-dependent attenu
arXiv:2609.32685v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) provide a learning-based framework for solving partial differential equations (PDEs), yet their training beha
arXiv:2609.35303v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) via Group-Relative Policy Optimization (GRPO) is widely used for multi-turn VLM agent training, ye
arXiv:2609.32732v1 Announce Type: cross Abstract: Human mobility generation aims to synthesize realistic point-of-interest (POI) visitation trajectories and has become an important tool for travel beh
arXiv:2609.32801v1 Announce Type: cross Abstract: Embodied task planners may produce multi-step plans whose subtask dependencies and interactions with the environment create physical risks during exec
arXiv:2609.32146v1 Announce Type: new Abstract: A quadrilateral block decomposition of a planar domain is judged by whether it is complete, whether its elements are well shaped, and how many of its ve
arXiv:2609.34314v1 Announce Type: new Abstract: Video-language models are increasingly used as judges of video understanding, both for evaluating model outputs and for training reward models. Whether
arXiv:2609.34605v1 Announce Type: new Abstract: Multi-teacher on-policy distillation (MOPD) has emerged as a popular post-training paradigm for integrating specialized capabilities in frontier languag
arXiv:2609.33127v1 Announce Type: new Abstract: Offline-to-Online Reinforcement Learning (O2O RL) has emerged as a practical paradigm that pre-trains the policy using static offline datasets and subse
arXiv:2602.02422v2 Announce Type: replace Abstract: The self-attention mechanism, at the heart of the Transformer model, is able to effectively model pairwise interactions between tokens. However, num
arXiv:2609.34812v1 Announce Type: new Abstract: We study Nash regret minimization in unknown finite matrix games with bandit payoff feedback and observed opponent actions. We develop Optimistic Payoff
arXiv:2609.32465v1 Announce Type: new Abstract: Decision-focused learning (DFL) trains predictors for downstream decision quality, but often relies on optimal reference decisions that are expensive to
arXiv:2609.32856v1 Announce Type: new Abstract: Vector polygon generation converts visual inputs, e.g., remote sensing (RS) images, into vectorized polygonal geometries, supporting applications such a
arXiv:2609.33258v1 Announce Type: cross Abstract: Recent task-driven and just-in-time 3D Scene Graph (3DSG) methods reduce per-task representations by constructing or activating only task-relevant inf
arXiv:2609.34021v1 Announce Type: new Abstract: Test-Time Training (TTT) adapts models to incoming test samples (e.g. out-of-distribution, (OOD)) when conventional fine-tuning is infeasible. Existing
arXiv:2609.33759v1 Announce Type: cross Abstract: When a fact changes, how should a language model update the history stored in its key-value (KV) cache? Hiding the old record is cheap, but it may sti
arXiv:2609.34031v1 Announce Type: new Abstract: We present a three-tier progression of Hidden Markov Models: maximum-likelihood (Baum-Welch), variational Bayesian (VBEM), and a neural variational exte