AI News

⚡ 6 minutes ago
1
1
Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape (arxiv.org)
2
1
Repair Before Veto, When Repair Is Hidden: Quantum-Accessible Features for Repair-Augmented Constraint Learning (arxiv.org)
3
1
IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment (arxiv.org)
4
1
GVC-Seg: Training-Free 3D Instance Segmentation via Geometric Visual Correspondence (arxiv.org)
5
1
Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine Translation (arxiv.org)
6
1
Summarization is Not Dead Yet (arxiv.org)
7
1
CATPO: Critique-Augmented Tree Policy Optimization (arxiv.org)
8
1
Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook (arxiv.org)
9
1
Multi-planar 2D-U-Net Segmentation of 3D-CT Abdominal Organs augmented by Spatial Occurrence Maps (arxiv.org)
10
1
Targeting World Models to Compromise Robot Learning Pipelines (arxiv.org)
11
1
Context-Aware Deep Learning for Defect Classification in Atomic-Resolution STEM (arxiv.org)
12
1
Harness Engineering for Physical AI: Robot Middleware Is the Harness Layer (arxiv.org)
13
1
AI Assurance in UK Defence: Challenges in Operationalising JSP 936 (arxiv.org)
14
1
Deep reinforcement learning for process design: Review and perspective (arxiv.org)
15
1
TAMUNA: Doubly Accelerated Distributed Optimization under Partial Participation (arxiv.org)
16
1
Echo-Memory: A Controlled Study of Memory in Action World Models (arxiv.org)
17
1
Discovering Functionally Selective Brain Regions with a Deep Topographic Multimodal Model (arxiv.org)
18
1
Data Synthesis and Parameter-Efficient Fine-Tuning for Low-Resource NMT: A Case Study on Q'eqchi' Mayan (arxiv.org)
19
1
Can Data Work be Reparative? (arxiv.org)
20
1
PACT: Learning Diverse Diagnostic Strategies via Privileged Synthesis and Branch Consensus (arxiv.org)
21
1
Report on CHIIR 2026 Workshop on Generative AI and Academic Search (GAI&AS) (arxiv.org)
22
1
From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing (arxiv.org)
23
1
SpectraLDS: Provable Distillation for Linear Dynamical Systems (arxiv.org)
24
1
Learning from flowsheets: A generative transformer model for autocompletion of flowsheets (arxiv.org)
25
1
Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models (arxiv.org)
26
1
Hybrid Robustness Verification for Spatio-Temporal Neural Networks (arxiv.org)
27
1
Adaptive directional gradients for parameterised quantum circuits (arxiv.org)
28
1
PolyBuild: An End-to-End Method for Polygonal Building Contour Extraction from High-Resolution Remote Sensing Images (arxiv.org)
29
1
Failure-Aware Refinement of Vision-Language Model for Lithography Defect Detection (arxiv.org)
30
1
Few-shot Class-variable Incremental Audio Classification via Prototype Adaptation and Pseudo Class-variable Training (arxiv.org)
31
1
A multi-agent system for spine MRI report generation from multi-sequence imaging (arxiv.org)
32
1
Benchmarking Vision-Language-Action Models on SO-101: Failure and Recovery Analysis (arxiv.org)
33
1
Difference-Aware Retrieval Policies for Imitation Learning (arxiv.org)
34
1
What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks (arxiv.org)
35
1
End-to-End Context Compression at Scale (arxiv.org)
36
1
Do Video Foundation Models Understand Intuitive Physics? A Layerwise Probing Analysis (arxiv.org)
37
1
FMplex: Model Virtualization for Serving Extensible Foundation Models (arxiv.org)
38
1
Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO (arxiv.org)
39
1
ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action Policies (arxiv.org)
40
1
Code Is More Than Text: Uncertainty Estimation for Code Generation (arxiv.org)
41
1
Integrating gene regulatory priors into Transformer attention with scTransformer for interpretable scRNA-seq analysis (arxiv.org)
42
1
Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur? (arxiv.org)
43
1
Intelligent Character Recognition of Handwritten Forms with Deep Neural Networks (arxiv.org)
44
1
BLM-SGAN: Bidirectional Language Modeling for Semantic-Spatial Text-to-Image Generation (arxiv.org)
45
1
Governance Controls for AI-Generated Test Artifacts in Autonomous Software Testing (arxiv.org)
46
1
AI-Augmented Closed-Loop Quality Engineering: A Reference Architecture for Continuous Software Quality Intelligence (arxiv.org)
47
1
Evaluating AI Investment Strategies (arxiv.org)
48
1
See More, Think Deeper: Query-Expanded Visual Evidence and Answer-Clue Guided Reflection for Long Video Understanding (arxiv.org)
49
1
Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks (arxiv.org)
50
1
RadOT-Eval: Auditable Structured-Evidence Transport for Radiology Report Evaluation (arxiv.org)