Low-Rank Adapters
PulseAugur coverage of Low-Rank Adapters — every cluster mentioning Low-Rank Adapters across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New framework enables real-time, one-shot emotion-controllable portrait animation
Researchers have developed a new framework called Proxy Avatar Meets Low-Rank Caching for real-time, one-shot portrait animation driven by audio and emotion. This method utilizes a Gaussian-based emotion proxy avatar to…
-
K-Merge offers efficient on-device LLM adapter merging
Researchers have introduced K-Merge, a novel strategy for efficiently merging multiple Low-Rank Adapters (LoRAs) for on-device large language models (LLMs). This method addresses the challenge of incrementally adding ne…
-
TreeLoRA offers efficient continual learning for large models
Researchers have introduced TreeLoRA, a novel approach for efficient continual learning in large pre-trained models. This method utilizes layer-wise Low-Rank Adapters organized by a hierarchical gradient-similarity tree…
-
LoREnc framework secures foundation models and adapters without retraining
Researchers have introduced LoREnc, a novel framework designed to protect foundation models and their associated low-rank adapters from unauthorized access and recovery attacks. This training-free method utilizes spectr…
-
LoREnc framework secures foundation models via spectral truncation
Researchers have developed LoREnc, a novel framework designed to protect foundation models and their associated low-rank adapters from unauthorized recovery and intellectual property leakage. This training-free method e…