Skip to content

Papers 5621 stories

arXiv cs.AI Papers

Atmospheric Diffusion-Guided Spatio-Temporal Transformer for Nuclear Radiation Forecasting

arXiv:2607.24774v1 Announce Type: new Abstract: Nuclear radiation, the energy released during atomic decay, poses persistent risks to public health and the environment, and concerns have only…

arXiv cs.CL Papers

Neuromorphic Diffusion Language Models: Addressing Compute and Memory Bottlenecks via Sparsity and Block Denoising

arXiv:2607.24841v1 Announce Type: new Abstract: Autoregressive (AR) large language models (LLMs) are inherently inefficient at inference time because each generated token requires accessing the full set…

arXiv cs.CV Papers

Desktop-Delta Bench: Do Computer-Use Models Understand Desktop GUI Transitions?

arXiv:2607.26041v1 Announce Type: cross Abstract: Computer-use agents (CUAs) increasingly act through desktop GUIs to complete long-horizon tasks. Current benchmarks primarily measure end-task success or single-frame grounding.…

arXiv cs.CV Papers

Reasoning with Memory: A Temporal Granularity-Adaptive Framework for Training-Free Long Video Understanding

arXiv:2607.24794v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) demonstrate superior generalization in fundamental video tasks, restricted context windows limit their long video understanding.…

arXiv stat.ML Papers

Generative Distributionally Robust Optimization

arXiv:2607.24983v1 Announce Type: cross Abstract: Generative models are increasingly adopted in distributionally robust optimization (DRO), but existing approaches trade off model compatibility and adversarial structure: methods…

arXiv cs.AI Papers

Token Factory: Efficiently Integrating Diverse Signals into Large Recommendation Models

arXiv:2606.19635v3 Announce Type: replace-cross Abstract: Large Recommendation Models (LRMs) have demonstrated promising capabilities in industry-scale recommendation tasks. However, holistically integrating traditional signals into these transformer-based architectures…

arXiv cs.AI Papers

Laplace-PSN-IRT: Uncertainty Quantification for Neural Item Response Theory Models of LLM Benchmarks

arXiv:2607.25257v1 Announce Type: cross Abstract: Item Response Theory (IRT) has recently been proposed as a framework for evaluating large language model (LLM) benchmarks by separating a…

arXiv cs.CL Papers

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

arXiv:2607.24904v1 Announce Type: cross Abstract: Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning but struggle with simple streaming perception…

arXiv cs.CV Papers

ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding

arXiv:2607.24743v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) hold immense potential to revolutionize clinical practice, yet deploying them in the medical domain is fundamentally…

arXiv cs.CV Papers

LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos

arXiv:2607.25125v1 Announce Type: new Abstract: Despite rapid progress in Multi-modal Large Language Models (MLLMs), understanding long-form videos is still bottlenecked by limited context windows. While recent…

arXiv stat.ML Papers

Multiclass Classification without Labels via Posterior Simplex Geometry

arXiv:2607.24943v1 Announce Type: cross Abstract: In many classification problems, reliable instance-level labels are unavailable. However, it is often possible to construct weakly enriched unlabeled samples: datasets…

arXiv cs.AI Papers

LLM Scheming Inversely Scales with Pretraining Language Coverage

arXiv:2607.24769v1 Announce Type: new Abstract: With the growing capabilities of frontier models, AI alignment becomes increasingly critical in high-risk deployment settings. While recent work has empirically…

arXiv cs.AI Papers

Steering topology distributions for unified generative design of architected metamaterials

arXiv:2607.24777v1 Announce Type: new Abstract: Architected metamaterials derive their functions from structure, creating vast opportunities to program physical responses through topology design. However, existing design methods…

arXiv cs.CL Papers

TabRank: Chain-of-Thought Distillation for Table Re-Rankers

arXiv:2607.25182v1 Announce Type: new Abstract: The ability to retrieve relevant tables for answering questions is a key task for structured information retrieval. Multi-stage retrieval systems rely…

arXiv cs.CV Papers

VetClaw: An Edge-Cloud Multimodal Agentic System for Veterinary Disease Screening

arXiv:2607.26042v1 Announce Type: new Abstract: We present VetClaw, an edge-cloud multimodal agentic system for early veterinary disease screening. VetClaw uses a camera module as an edge…

arXiv cs.CV Papers

OrthKD: Extracting Generalized Clinical Knowledge from Heterogeneous Teachers for Lightweight Deployment

arXiv:2607.25545v1 Announce Type: cross Abstract: Deploying diabetic retinopathy (DR) screening models in primary care requires edge-efficient systems that remain accurate, safe, and reliable under domain shift.…

arXiv stat.ML Papers

A Generalized Tangent Approximation based Variational Inference Framework for Strongly Super-Gaussian Likelihoods

arXiv:2504.05431v3 Announce Type: cross Abstract: Variational inference, as an alternative to Markov chain Monte Carlo sampling, has played a transformative role in enabling scalable computation for…

arXiv cs.AI Papers

ProcAgent: An Agentic Framework for Procedural Task Guidance on Edge with Human-in-the-Loop

arXiv:2607.24770v1 Announce Type: new Abstract: Procedural tasks such as furniture assembly and home repair impose substantial cognitive demands because users must interpret instructions, track task progress,…

arXiv cs.AI Papers

Rethinking Likelihood distributions: Student's t Likelihood Boosts Bayesian Neural Network Performance

arXiv:2607.25376v1 Announce Type: cross Abstract: In Bayesian neural networks (BNNs), variational inference is a widely adopted framework for modeling uncertainty in a distributional way, with the…

arXiv cs.CL Papers

CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition

arXiv:2607.25294v1 Announce Type: cross Abstract: Real-world tasks often require models to learn from task-specific context rather than relying only on pre-trained knowledge. While recent work has…

arXiv cs.CV Papers

Unifying Active Learning and Semi-Supervised Learning for Medical Image Segmentation

arXiv:2607.25014v1 Announce Type: new Abstract: In practical settings, medical image segmentation models are often developed with limited annotated data rather than fully labeled datasets. Training frequently…

arXiv cs.CV Papers

FIDAC: An Easy-to-use Pipeline to Extract and Interpret Interpersonal Distance From Video

arXiv:2607.25146v1 Announce Type: new Abstract: The distance between persons reveals significant information about their perception of each other. However, such information is not easily extractable and…

arXiv stat.ML Papers

Can Deep Generative Models Reproduce Non-Stationary Gaussian Random Fields?

arXiv:2607.25929v1 Announce Type: new Abstract: Deep generative models (DGMs) are widely used for complex high-dimensional data and increasingly applied to spatial and spatio-temporal modeling. Their generated…

arXiv cs.AI Papers

Crystalis: Progressive Nucleation and Semantic Annealing for Coordinated Multi-View Visualization Generation

arXiv:2607.24766v1 Announce Type: new Abstract: Large language models (LLMs) can generate individual charts, but coordinated multi-view visualizations (CMVs), where views share data flows and cross-view interactions,…