arXiv:2609.10464v1 Announce Type: cross Abstract: Joint-Embedding Predictive Architecture (JEPA) world models learn a compact latent representation of the…
Category: AI
Beyond One-Size-Fits-All: Sample-Adaptive Strategy Routing for Vision Token Pruning in MLLMs
arXiv:2609.10346v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) process hundreds or thousands of visual tokens per image,…
PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving
arXiv:2609.10372v2 Announce Type: cross Abstract: We present the PACE, a framework for retrieval-augmented dialogue serving that formalizes Perceived…
OmniMed-FL: A Robust Multimodal Federated Learning Framework for Clinical Diagnosis
arXiv:2609.10364v1 Announce Type: cross Abstract: Simultaneous assessment of medical imaging and patient records is often required in clinical diagnosis.…
MOONWALK: Mediating Operations with Intent-Evidence-Action Alignment Across Junior-Supervisor Review Workflows in Animation/VFX Pre-Production
arXiv:2609.10385v1 Announce Type: cross Abstract: Animation and VFX pre-production review requires teams to translate loosely specified creative…
Ex-Deepmind VP Vinyals says AI self-improvement is coming but won’t trigger an intelligence explosion
Oriol Vinyals, until recently head of research at Google DeepMind, thinks a sudden AI intelligence explosion through recursive self-improvement is…
Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization
arXiv:2609.10410v1 Announce Type: cross Abstract: The growing complexity of content moderation policies presents a critical challenge for their consistent…
DiSCo: A Distribution-First Steering and Cultural Prior Evaluation Framework for Measuring Cultural Preference Bias in LLMs
arXiv:2609.10253v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in globally used assistants, yet their default…
Learning Intrusion Response Strategies for OT Systems
arXiv:2609.10298v1 Announce Type: cross Abstract: Cyberattacks against Operational Technology (OT) systems, which monitor and control industrial…
RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding
arXiv:2609.10305v1 Announce Type: cross Abstract: Language models under one million parameters matter for edge deployment, domain adaptation, and…