CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion
Research
Research News
New papers, breakthroughs and academic AI research
LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception
Research
Robust LassoNet: Enhancing Feature Selection in Neural Networks via Robust Loss Functions
Research
VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agents
Research
Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection
Research
Grounded World Model: Latent Planning with Language Goals
Research
One Adapter, Every Resolution: Gated Low-Rank Adaptation for Remote Sensing VLMs
Research
DySurface: Consistent 4D Surface Reconstruction via Bridging Explicit Gaussians and Implicit Functions
Research
Graph Residual Conjugate Diffusion: SNR-Equalized Heat Flow for Graph Signals
Research
Validity-Preserving Hierarchical RL for Joint Routing and Switch Placement in EDA
Research
Efficient Active Auditing of Multi-Group Fairness with Bias Probes
Research
Privacy in Personalized AI Is a System Property, Not Just a Model Property
Research