No article text was recorded for this version.
parameter interference
Version 2 of 2550 papers738 conceptsfrozen 2026-10-04
Papers in this version
- Blog: TIES-Merging: Resolving Interference When Merging Models
- Blog: Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts
- Blog: Subspace-Boosted Model Merging
- Blog: Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts
- Blog: Training-free LLM Merging for Multi-task Learning
- Blog: TIES-Merging: Resolving Interference When Merging Models
- Blog: Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
- Blog: DPPA: Pruning Method for Large Language Model to Model Merging
- Blog: EMR-Merging: Tuning-Free High-Performance Model Merging
- Blog: When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging
- Blog: Effective and Parameter-Efficient Reusing Fine-Tuned Models
- Blog: Model merging with SVD to tie the Knots
- Blog: Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning
- Blog: Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks
- Blog: LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging
- Blog: Octo-planner: On-device Language Model for Planner-Action Agents
- Blog: Merging Continual Pretraining Models for Domain-Specialized LLMs: A Case Study in Finance
- Blog: Unifying Multimodal Large Language Model Capabilities and Modalities via Model Merging
- Blog: Multi-Task Model Merging via Adaptive Weight Disentanglement
- Blog: Task Singular Vectors: Reducing Task Interference in Model Merging
- Blog: Modular Customization of Diffusion Models via Blockwise-Parameterized Low-Rank Adaptation
- Blog: CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging
- Blog: Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning
- Blog: Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge
- Blog: From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging
- Blog: LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation
- Blog: Multi-Task Model Merging via Adaptive Weight Disentanglement
- Blog: Post-Hoc Merging is Not Enough: Many-Shot Model Merging with Loss-Gap Balancing
- Blog: CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging
- Blog: A Systematic Study of Model Merging Techniques in Large Language Models
- Blog: STAR: Spectral Truncation and Rescale for Model Merging
- Blog: Localizing Task Information for Improved Model Merging and Compression
- Blog: Rare Word Recognition and Translation Without Fine-Tuning via Task Vector in Speech Models
- Blog: Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic
- Blog: FroM: Frobenius Norm-Based Data-Free Adaptive Model Merging
- Blog: Parameter Competition Balancing for Model Merging
- Blog: Resolving Interference When Merging Models
- Blog: MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agent
- Blog: Parameter Competition Balancing for Model Merging
- Blog: Superpose Singular Features for Model Merging
- Blog: Understanding Model Merging: A Unified Generalization Framework for Heterogeneous Experts
- Blog: Localizing Task Information for Improved Model Merging and Compression
- Blog: Less is More: Undertraining Experts Improves Model Upcycling
- Blog: Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging
- Blog: Directional Reasoning Injection for Fine-Tuning MLLMs
- Blog: Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts
- Blog: Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging
- Blog: Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?
- Blog: No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
- Blog: Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing
- Blog: LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint
- Blog: BYOM: Building Your Own Multi-Task Model For Free
- Blog: CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging
- Blog: Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
- Blog: Black-box Model Merging for Language-Model-as-a-Service with Massive Model Repositories
- Blog: Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
- Blog: Efficient Model Editing with Task-Localized Sparse Fine-tuning
- Blog: Demystifying Mergeability: Interpretable Properties to Predict Model Merging Success
- Blog: Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling
- Blog: Harnessing Optimization Dynamics for Curvature-Informed Model Merging
Showing 60 of 550 papers.
History & citation
Current · Permanent link
- Spectral Calibration for Balanced Model Merging merged into this direction (100% overlap)
- Correcting Representation Bias in Merged Models merged into this direction (50% overlap)
- Task Arithmetic in Orthogonal Parameter Subspaces merged into this direction (52% overlap)
- Model Merging via Parameter and Representation Alignment merged into this direction (55% overlap)
- Closed-Form Analytical Model Merging merged into this direction (53% overlap)
- Spectral Model Merging via Task Singular Vectors merged into this direction (65% overlap)
- parameter conflict resolution split from this direction (76% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_parameter_interference_86919955,
title = {parameter interference},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/parameter-interference/rdr_869199558d8b4d94a6f99e1f64a2ba95},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_parameter_interference_86919955_v2,
title = {parameter interference},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/parameter-interference/rdr_869199558d8b4d94a6f99e1f64a2ba95/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}