Multi-source transfer learning incurs an intrinsic adaptation cost that can exceed one, with phase transitions separating regimes where bias-agnostic estimators match oracle performance from those where they cannot.
hub
K., Hayase, J., and Srinivasa, S
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Task vectors from weight differences allow arithmetic operations to edit pre-trained models, improving multiple tasks simultaneously and enabling analogical inference on unseen tasks.
Fine-tuning neural PDE operators to regime endpoints reveals a physical direction in weight space that CCM uses to compose accurate merged models for new or extrapolated regimes from metadata or short prefixes.
Neural loss landscapes contain flat channels to infinity along which gradient flow leads pairs of neurons to implement gated linear units.
CDS-trained BabyLMs show earlier and more appropriate production in a new frame-completion task while FineWeb-edu models lead on comprehension benchmarks, indicating current tests underestimate CDS benefits.
PivotMerge merges heterogeneous multimodal pre-trained models via shared-space decomposition to filter conflicts and layer-wise weights based on alignment contributions, outperforming baselines on multimodal benchmarks.
A functional similarity metric for ReLU networks uses normalized activation region signatures and MinHash to overcome parametric symmetries like neuron permutation and scaling.
Continual learning robots form a significantly more stable invariant subnetwork than constant-task controls, and preserving it improves adaptation while damaging it hurts performance.
SAGE reframes adversarial scenario generation as multi-objective preference alignment, using hierarchical group-based optimization and test-time linear interpolation of two expert policies to enable steerable control over adversariality-realism trade-offs.
HiP-LoRA decomposes LoRA updates into principal and residual spectral channels with a singular-value-weighted stability budget to reduce forgetting and interference during foundation model adaptation.
MOMO merges sensor-specific models from three Mars orbital instruments at matched validation loss stages to form a foundation model that outperforms ImageNet, Earth observation, sensor-specific, and supervised baselines on nine Mars-Bench tasks.
Representations learned by large AI models are converging toward a shared statistical model of reality.
citing papers explorer
-
PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging
PivotMerge merges heterogeneous multimodal pre-trained models via shared-space decomposition to filter conflicts and layer-wise weights based on alignment contributions, outperforming baselines on multimodal benchmarks.
-
MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications
MOMO merges sensor-specific models from three Mars orbital instruments at matched validation loss stages to form a foundation model that outperforms ImageNet, Earth observation, sensor-specific, and supervised baselines on nine Mars-Bench tasks.