BrainLoRA adapts backbones up to 104B parameters for brain encoding
An ensemble of more than 200 LoRA adapters ranks first on the public Algonauts post-challenge leaderboard.
Stories per day · 30 days
4 stories, newest first · one card per story
Stories tagged #peft
BrainLoRA fine-tunes up to 104B-parameter models for brain encoding
An ensemble of more than 200 adapted models leads the public Algonauts post-challenge leaderboard as of the paper's writing.
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.
Not All Ranks Are Equal: Budget-Aware LoRA Merging Across Tasks
Net Utility allocates LoRA merge rank by utility and interference, beating uniform budgets on vision and language.