PACT preserves load-bearing wall dimensions from pre-trained weights inside task vectors to reduce conflicts and improve merged model performance.
Localizing task information for improved model merging and compres- sion,
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
DiDi-Merging achieves dynamic model merging performance matching or exceeding prior methods while using only 1.24x to 1.4x the parameters of a single fine-tuned model.
SEAT preserves epistemic abstention in LLMs during knowledge adaptation via sparse tuning and entity-perturbed KL regularization, yielding 18-101% better abstention on unknown queries while retaining near-perfect knowledge acquisition.
Merging task vectors extracted from fine-tuned OVAR models yields superior zero-shot generalization in out-of-distribution settings compared to the pre-trained base model.
citing papers explorer
-
PACT: Preserving Anchored Cores in Task-vectors for Model Merging
PACT preserves load-bearing wall dimensions from pre-trained weights inside task vectors to reduce conflicts and improve merged model performance.
-
Dynamic Model Merging Made Slim
DiDi-Merging achieves dynamic model merging performance matching or exceeding prior methods while using only 1.24x to 1.4x the parameters of a single fine-tuned model.
-
SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention
SEAT preserves epistemic abstention in LLMs during knowledge adaptation via sparse tuning and entity-perturbed KL regularization, yielding 18-101% better abstention on unknown queries while retaining near-perfect knowledge acquisition.
-
Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic
Merging task vectors extracted from fine-tuned OVAR models yields superior zero-shot generalization in out-of-distribution settings compared to the pre-trained base model.