arXiv:2609.11519v1 Announce Type: cross Abstract: In this paper, we address the problem of graphic design template creation, which generates a background…
Structural priors for data-efficient language learning
arXiv:2609.11505v1 Announce Type: cross Abstract: Efficient language learning requires methods to reduce the reliance on large data and computational…
AI News Brief Hourly Summary 2026-09-12 20h : 13 posts
13 posts published in the last hour 17:32Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attacks 17:32VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents 17:32SWRouter: Similarity-Contractive Window Routing for Multi-Turn Large Language Model Conversations 17:32Buyer Artificial Intelligence-Enabled Environmental Governance and Supplier…
Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attacks
arXiv:2609.11404v1 Announce Type: cross Abstract: This paper presents DF-CAPTCHA, an active defense against real-time deepfake impersonation in voice and…
VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents
arXiv:2609.11390v1 Announce Type: cross Abstract: State-of-the-art retrieval-augmented generation (RAG) methods exploit document structures to acquire…
SWRouter: Similarity-Contractive Window Routing for Multi-Turn Large Language Model Conversations
arXiv:2609.11414v1 Announce Type: cross Abstract: Large language models exhibit complementary strengths, motivating routing methods that dispatch each…
Buyer Artificial Intelligence-Enabled Environmental Governance and Supplier Environmental Controversies: An Organizational Information Processing and Signaling
arXiv:2609.11391v1 Announce Type: cross Abstract: Environmental controversies in global supply chains pose significant risks for global buyers. This study…
Altman Says OpenAI Will Match Anthropic’s Embedded Evaluator Pledge
OpenAI chief executive Sam Altman committed his company on September 12, 2026, to having independent evaluators with employee-like access, endorsing…
X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation
arXiv:2609.11412v1 Announce Type: cross Abstract: Reducing audio-encoder depth lowers the inference cost of speech large language models, but removing…
Characterizing Bluesky Content Moderation Service: From Automation of Service to Landscape of Harms
arXiv:2609.11373v1 Announce Type: cross Abstract: Empirical research on content moderation is fundamentally constrained by the opaque deployment of…
E-CONAN (Entailment, CONtradition And Neutral) Benchmarks: Arabic Textual Entailment and Natural Inference Datasets
arXiv:2609.11334v1 Announce Type: cross Abstract: Natural Language Inference processes pairs of sentences to extract their semantic relations. NLI has…
Reification as a Transferable Vocabulary: Zero-Shot Link Prediction with Vanilla GNNs
arXiv:2609.11347v1 Announce Type: cross Abstract: Knowledge graph foundation models such as ULTRA achieve zero-shot link prediction on unseen graphs…
Agent-Integrated Software: Interaction Contracts and Continuous Assurance
arXiv:2609.11381v1 Announce Type: cross Abstract: Embedding an intelligent agent in an existing application creates a persistent coordination problem:…
Roundtables: Could AI really kill us all?
Employees at the world’s leading AI labs are saying there’s a real possibility that advanced AI could destroy humanity. Are they right? Or is this more…
On the Impact of Anonymization on the Performance of Large Language Models
arXiv:2609.11335v1 Announce Type: cross Abstract: As large language models are increasingly deployed in sensitive domains, anonymizing input data to…
AI News Brief Hourly Summary 2026-09-12 19h : 14 posts
14 posts published in the last hour 16:32Your Model Already Knows Don’t Teach It, Learn to Ask It: Soft Prompting for Few-Shot Adaptation of Vision-Language Models 16:322AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation 16:32The…
Your Model Already Knows Don’t Teach It, Learn to Ask It: Soft Prompting for Few-Shot Adaptation of Vision-Language Models
arXiv:2609.11310v1 Announce Type: cross Abstract: We address few-shot object detection with vision-language models (VLMs) in out-of-domain settings such…
2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation
arXiv:2609.11308v1 Announce Type: cross Abstract: Long-horizon robot manipulation requires memory, but not necessarily inside the action policy. To…