Reflections and Fragments: Securing LLMs Against Sequential Mosaic Attacks
Research
Research News
New papers, breakthroughs and academic AI research
COPEX: Benchmarking LLM Robustness to Adversarial Context Across Model Context Protocol Layers
Research
Can LLM Agents Automate Reinforcement Learning for Text-to-Speech?
Research
Adaptive Operator Selection in Bilevel Large Neighborhood Search for Electric Autonomous Dial-a-Ride Problem under Uncertainty
Research
Compact set-valued deep ensembling in multi-class classification
Research
DP-ES: Differentially Private Evolution Strategies for Prompt Optimization
Research
Steering by Influence: Curvature Aware Data Weighting for Activation Steering
Research
System One Models for Wireless Decision-Making:Applications and Performance Evaluation
Research
Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts
Research
Benchmarking Psychological Dynamics in Generative Agents
Research
Green-Routed Neural Operators:\\Physics Determines Where the Network Reads
Research
On Semi-Markov Suboptimality in Hierarchical Reinforcement Learning
Research