NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Models
NestedVLA generates task-specific VLA parameters, beating model merging by 41 points across three robotics benchmarks.
Stories per day · 30 days
Relatedlora1malow1memory1model-merging1nestedvla1robotics1skill-consolidation1streaming-vlm1video-understanding1vla1
5 stories, newest first · one card per story
Stories tagged #hypernetwork
Memory as Weights: Internalizing Long-Term History for Streaming Videos
MaLoW stores streaming video history as LoRA weights, beating prior memory methods on OVO-Bench.
HyperErase: Scale-Calibrated Hypernetwork for Multi-Concept Erasure in Text-to-Image Models
HyperErase synthesizes prompt-specific LoRAs to erase multiple concepts from text-to-image models.
LoRA-generating hypernetworks for efficient on-device LLM generative personalization
A hypernetwork generates user-specific LoRA adapters on device for personalized long-form LLM generation.
Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models
HyperQ trains quantum residual branches in a frozen 1.1B diffusion model, beating the backbone by 4.71 points.