14 posts published in the last hour 18:32Profiling What Matters: Context-Aware Item Profiles from Large-Scale Metadata for LLM Recommenders 18:32Do SpeechLMs Hear Their Own Opinions? Diagnosing and Mitigating Previous-Belief Contamination in Streaming Emotion Understanding 18:32Fuzzy-MoE: Interpretable Regime-Conditioned Expert Routing for…
Author: script
Profiling What Matters: Context-Aware Item Profiles from Large-Scale Metadata for LLM Recommenders
arXiv:2608.20801v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have significantly advanced reranking in recommendation, effectively…
Do SpeechLMs Hear Their Own Opinions? Diagnosing and Mitigating Previous-Belief Contamination in Streaming Emotion Understanding
arXiv:2608.20769v1 Announce Type: cross Abstract: Streaming emotion understanding uses historical state while continuously interpreting current audio,…
Fuzzy-MoE: Interpretable Regime-Conditioned Expert Routing for Non-Stationary Multivariate Time Series Forecasting
arXiv:2608.20761v1 Announce Type: cross Abstract: In non-stationary multivariate time series, different variables and samples often exhibit heterogeneous…
Instinct’s powerful AI assistant is raising privacy and security concerns
Early testers are raving about what Instinct can do, but some say the AI assistant’s sweeping access, broad terms and ability to act on users’ behalf come…
CARD: Diagnosing Belief to Action Routing Failures in Vision Language Models
arXiv:2608.20763v1 Announce Type: cross Abstract: Linear probes and activation steering have uncovered that vision-language models (VLMs) internally…
Pew study confirms sharp rise of AI-written text on the web since ChatGPT’s launch
The Pew Research Center analyzed nearly half a million English-language web pages for AI-generated content. More than a third of pages published since…
CertVLA: Certified Defense against Physical Visual Attacks for Vision-Language-Action Models
arXiv:2608.20791v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies are vulnerable to localized physical perturbations, yet existing…
Vis-Poison: Poisoning Visual Knowledge in Multimodal Retrieval-Augmented Generation
arXiv:2608.20756v1 Announce Type: cross Abstract: While multimodal retrieval-augmented generation (RAG) systems increasingly rely on images as external…
Temporal Validity on Real Software Histories: Eliminating Stale-Fact Errors in Code-Assistant Memory over GitHub Fixes
arXiv:2608.20685v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) has no model of time: when a fact changes across a coding session -…