DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
Dataless knowledge fusion by merging weights of language models
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 10roles
background 2polarities
background 2representative citing papers
Model merging is generalized as Fréchet averaging on symmetry-invariant manifolds, containing Fisher merging as a special case and offering a new approach for LoRA adapters.
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.
DeLock mitigates lock-in in low-data VLA post-training via visual grounding preservation and test-time contrastive prompt guidance, outperforming baselines across eight evaluations while matching data-heavy generalist policies.
ADR achieves theoretically zero-forgetting class-incremental graph learning by combining backpropagation adaptation with ridge-regression-based layer-wise merging of GNN linear transformations.
ACE-Merging estimates task input covariances from parameter differences to enable closed-form data-free merging that reduces interference and outperforms prior baselines on vision and language tasks.
Empirical scaling laws for LLM merging show a size-dependent floor and 1/k-like tail in cross-entropy loss that holds across architectures and merging methods.
ReLoRA reduces time-to-readiness for LoRA adapters on updated LLMs by up to 8.9x through adaptive Bayesian initialization and scheduled regularization while improving accuracy by up to 4.6%.
Post-processing via random selection or linear combination of differentially private models allows meeting arbitrary target privacy parameters without additional training.
MAny addresses dual-forgetting in multimodal continual instruction tuning via CPM and LPM merging strategies, delivering up to 8.57% accuracy gains on UCIT benchmarks without additional training.
citing papers explorer
-
Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
-
Generalizing the Geometry of Model Merging Through Frechet Averages
Model merging is generalized as Fréchet averaging on symmetry-invariant manifolds, containing Fisher merging as a special case and offering a new approach for LoRA adapters.
-
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.
-
Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training
DeLock mitigates lock-in in low-data VLA post-training via visual grounding preservation and test-time contrastive prompt guidance, outperforming baselines across eight evaluations while matching data-heavy generalist policies.
-
Analytic Drift Resister for Non-Exemplar Continual Graph Learning
ADR achieves theoretically zero-forgetting class-incremental graph learning by combining backpropagation adaptation with ridge-regression-based layer-wise merging of GNN linear transformations.
-
ACE-Merging: Data-Free Model Merging with Adaptive Covariance Estimation
ACE-Merging estimates task input covariances from parameter differences to enable closed-form data-free merging that reduces interference and outperforms prior baselines on vision and language tasks.
-
Model Merging Scaling Laws in Large Language Models
Empirical scaling laws for LLM merging show a size-dependent floor and 1/k-like tail in cross-entropy loss that holds across architectures and merging methods.
-
ReLoRA: Knowledge-Reusing Adaptation for Fast Rollout of Evolving LLM Services
ReLoRA reduces time-to-readiness for LoRA adapters on updated LLMs by up to 8.9x through adaptive Bayesian initialization and scheduled regularization while improving accuracy by up to 4.6%.
-
Differentially Private Model Merging
Post-processing via random selection or linear combination of differentially private models allows meeting arbitrary target privacy parameters without additional training.
-
MAny: Merge Anything for Multimodal Continual Instruction Tuning
MAny addresses dual-forgetting in multimodal continual instruction tuning via CPM and LPM merging strategies, delivering up to 8.57% accuracy gains on UCIT benchmarks without additional training.