Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation
Research
Research News
New papers, breakthroughs and academic AI research
Local Prototype Reconstruction for Text-Compatible Speech-to-LLM Bridge Pretraining
Research
BeliefScope: Diagnosing Evidence-Driven Revision and Pressure-Induced Shifts in Large Language Models
Research
Refine Connections, Close the Gap: A Reliable Enhancement Framework for Driving Scene Topology
Research
No Distillation Needed: Single-Pass Real-Time Talking Heads via Acausal Noise Shaping
Research
LadderEdit: Edit-Level Residual Compression for Memory-Efficient Lifelong Editing of LLMs
Research
When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better
Research
The "10th Juror": Open-Set Standpoint Screening for Bureaucratic Bias Detection
Research
Gated Memory: Admission-Controlled Memory Formation for Conversational AI
Research
KDFP: A first-principles approach to knowledge distillation in large language models
Research
Adaptive Multi-Discriminator WGAN Framework for Resource-Constrained Internet of Vehicles Using Reinforcement Learning and Game Theory
Research
BridgeGuard: Explicit Safety Drift for Diffusion-based Autonomous Driving
Research