arXiv:2608.14172v1 Announce Type: cross Abstract: Text-to-image diffusion models have two major drawbacks that severely limit their practical utility: (1)…
Training Fair Tabular Foundation Models
arXiv:2608.14211v1 Announce Type: cross Abstract: Tabular Foundation Models (TFMs) have emerged as leading methods for tabular predictive tasks,…
How Much Do Legal RAG Systems Still Hallucinate?
arXiv:2608.14210v1 Announce Type: cross Abstract: Hallucination is a major challenge for retrieval-augmented generation (RAG) systems in the legal domain,…
Structure-Guided Spatiotemporal Attention Graph Neural Network for Traffic Flow Prediction
arXiv:2608.14177v1 Announce Type: cross Abstract: Deep spatiotemporal models integrating graph convolutions and attention mechanisms have demonstrated…
HiCo-GS: Hierarchical Context Aggregation and Geometric Consistency for Octree Gaussian Splatting
arXiv:2608.14136v1 Announce Type: cross Abstract: Octree-based anchor Gaussian Splatting has emerged as a scalable representation for city-scale novel…
SPARGen: Unifying Spatial Perception and Reasoning through Native Multimodal Generation
arXiv:2608.14138v1 Announce Type: cross Abstract: Spatial perception and reasoning from visual observations require recovering geometric structure,…
Act2Intention: A Benchmark For Developing Active Mobile Agents Through Inferring User Intention from GUI Actions
arXiv:2608.14132v1 Announce Type: cross Abstract: Mobile GUI Agents powered by multimodal large language models (MLLMs) show promise in human-computer…
Self-Supervised Visual On-Policy Distillation
arXiv:2608.14144v1 Announce Type: cross Abstract: Visual on-policy distillation relies heavily on an informative teacher-student asymmetry, through either…
MiniMax Releases MiniMax-Music3: An Open-Weights Music Model Generating Complete Five-Minute Songs From Lyrics and a Structured Caption
MiniMax released MiniMax-Music3, an open-weights text-to-music model. Given lyrics with section tags and a structured caption, it generates a complete…
AlignFace: Human-Aligned Face Similarity Metric with Interpretable Concept Relations
arXiv:2608.14130v1 Announce Type: cross Abstract: Computer vision models for generated facial content, such as face editing and privacy protection,…
AI News Brief Hourly Summary 2026-08-17 21h : 13 posts
13 posts published in the last hour 18:32Forecast Collapse in Time-Series Foundation Models 18:32Fixed-Budget Gaussian Volume Encoding with Structure-Aware Allocation 18:32BGA: A noise-immune neural distillation framework for malicious signature extraction in high-entropy encrypted flows 18:32Overcoming Shortcut Learning in Graph Neural…
Forecast Collapse in Time-Series Foundation Models
arXiv:2608.14106v1 Announce Type: cross Abstract: When forecasting hourly returns for 1,000 US equities, we observe an unexpected phenomenon: predictions…
Fixed-Budget Gaussian Volume Encoding with Structure-Aware Allocation
arXiv:2608.14112v1 Announce Type: cross Abstract: Scientific simulations often produce scalar volumes faster than they can be stored, transferred, and…
BGA: A noise-immune neural distillation framework for malicious signature extraction in high-entropy encrypted flows
arXiv:2608.14126v1 Announce Type: cross Abstract: To mitigate attention dilution in high-entropy TLS 1.3 flows, we propose BGA, a noise-immune neural…
Overcoming Shortcut Learning in Graph Neural Networks through Active Explanation Guidance
arXiv:2608.14121v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) can solve prediction tasks by unintentionally exploiting shortcuts—that…
NVIDIA Nemotron 3.5 Lightning now available in Amazon SageMaker JumpStart
NVIDIA Nemotron 3.5 Lightning, an open model built for high-volume agentic workloads, is now available in Amazon SageMaker JumpStart. This post shows how…
From Fixed Grids to Moving Particles:A Transferable Latent Operator for Fluid Dynamics
arXiv:2608.14120v1 Announce Type: cross Abstract: Lagrangian modeling is vital to fluid dynamics, as it characterizes particle transport and complements…
Rewrite Once, Validate Anywhere: Producing OWL-Aware SHACL Constraints (Extended Version)
arXiv:2608.14104v1 Announce Type: cross Abstract: The Shapes Constraint Language (SHACL) is a W3C recommendation to express syntactic constraints, called…