arXiv:2609.10084v1 Announce Type: cross Abstract: Generalized zero-shot learning (GZSL) has emerged as an important paradigm for visual recognition…
Tag: AI
Context operations to architecture modelling output from large language models and evaluation criteria for their use in systems engineering design
arXiv:2609.10132v1 Announce Type: cross Abstract: The development of generative artificial intelligence resources enables opportunities of speeding up…
Beyond Training: A Feasibility Taxonomy for Inference-Time AI Governance
arXiv:2609.10105v1 Announce Type: cross Abstract: Compute governance today is a governance of training: the thresholds, reporting requirements, and…
Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training
arXiv:2609.10052v1 Announce Type: cross Abstract: LLM agents for sequential decision tasks are often post-trained with trajectory-level outcome labels,…
MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes
arXiv:2609.10016v1 Announce Type: cross Abstract: We introduce MetroLLM-Bench, a 955-case benchmark for testing language models as the policy layer of a…
Elastoformer: Enabling Dynamic Adaptivity via Elastic Model Transformation
arXiv:2609.10018v1 Announce Type: cross Abstract: EdgeAI systems are increasingly employing computer vision applications to enable intelligent, on-device…
What Makes Adversarial Examples Transfer Across Deepfake Detectors?
arXiv:2609.10002v1 Announce Type: cross Abstract: Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples…
Reggie Scales, President and Head of Business Unit Applications at Vonage – Interview Series
Reggie Scales, President and Head of Business Unit Applications at Vonage, is a seasoned technology and communications executive with more than two…
NOPE-HYPE: A Structured Simulation Workflow for Robust Speech-to-Text Across Diverse Acoustic Environments
arXiv:2609.10058v1 Announce Type: cross Abstract: Robust speech-to-text translation systems should perform reliably across diverse acoustic conditions,…
The AI policy window is open. We need to act.
Chris Lehane argues that stronger AI capabilities require stronger safety evidence, shared standards, and durable policy action while the policy window…