LCDD creates sparse carriers for SFT behaviors that SFT-Eraser can reverse, with ablations showing the sparse structure enables causal control.
Task arithmetic in the tangent space: Improved editing of pre-trained models.Advances in Neural Information Processing Systems, 36:66727–66754
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
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.
The paper introduces a dynamical model that decomposes alignment updates in LLM fine-tuning into rebound and driving forces and predicts a rehearsal priming effect.
EC-Net combines Poincare-ball hyperbolic embeddings, hypergraph fusion, and decoupled radial-angular contrastive learning to improve accuracy on multimodal emotion benchmarks especially under partial or noisy modalities.
citing papers explorer
-
Crafting Reversible SFT Behaviors in Large Language Models
LCDD creates sparse carriers for SFT behaviors that SFT-Eraser can reverse, with ablations showing the sparse structure enables causal control.
-
Discovering Physical Directions in Weight Space: Composing Neural PDE Experts
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.
-
Alignment Dynamics in LLM Fine-Tuning
The paper introduces a dynamical model that decomposes alignment updates in LLM fine-tuning into rebound and driving forces and predicts a rehearsal priming effect.
-
Emotion Collider: Dual Hyperbolic Mirror Manifolds for Sentiment Recovery via Anti Emotion Reflection
EC-Net combines Poincare-ball hyperbolic embeddings, hypergraph fusion, and decoupled radial-angular contrastive learning to improve accuracy on multimodal emotion benchmarks especially under partial or noisy modalities.