Pith. sign in

REVIEW 15 cited by

TIES-Merging: Resolving Interference When Merging Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2306.01708 v2 pith:UB2PI5Y5 submitted 2023-06-02 cs.LG cs.AIcs.CLcs.CV

TIES-Merging: Resolving Interference When Merging Models

classification cs.LG cs.AIcs.CLcs.CV
keywords mergingmodelsinterferencemodelsignparametersties-mergingfine-tuning
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Transfer learning - i.e., further fine-tuning a pre-trained model on a downstream task - can confer significant advantages, including improved downstream performance, faster convergence, and better sample efficiency. These advantages have led to a proliferation of task-specific fine-tuned models, which typically can only perform a single task and do not benefit from one another. Recently, model merging techniques have emerged as a solution to combine multiple task-specific models into a single multitask model without performing additional training. However, existing merging methods often ignore the interference between parameters of different models, resulting in large performance drops when merging multiple models. In this paper, we demonstrate that prior merging techniques inadvertently lose valuable information due to two major sources of interference: (a) interference due to redundant parameter values and (b) disagreement on the sign of a given parameter's values across models. To address this, we propose our method, TRIM, ELECT SIGN & MERGE (TIES-Merging), which introduces three novel steps when merging models: (1) resetting parameters that only changed a small amount during fine-tuning, (2) resolving sign conflicts, and (3) merging only the parameters that are in alignment with the final agreed-upon sign. We find that TIES-Merging outperforms several existing methods in diverse settings covering a range of modalities, domains, number of tasks, model sizes, architectures, and fine-tuning settings. We further analyze the impact of different types of interference on model parameters, and highlight the importance of resolving sign interference. Our code is available at https://github.com/prateeky2806/ties-merging

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 15 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Emergent Misalignment Recruits a Pre-existing Persona Subspace

    cs.LG 2026-07 conditional novelty 7.0

    Fine-tuning on narrow bad data recruits a low-rank persona subspace already present in a frozen instruction-tuned model; holding that subspace out of activations prevents broad misalignment, and injecting it into the ...

  2. modelDNA: Calibrated Lineage Verification and Merge Decomposition from Sampled Weight Fingerprints

    cs.LG 2026-07 conditional novelty 6.5

    Sampled weight fingerprints recover LLM parentage with AUROC 1.0 and zero false positives, and recover published mergekit mixture weights without full downloads.

  3. Spectral Rewiring for Exploration, Purification, and Model Merging

    cs.LG 2026-07 conditional novelty 6.5

    Subspace-Aligned Rewiring projects RL weight updates onto the base model’s SVD basis, retaining a compact rewiring matrix that preserves reasoning and improves exploration and multi-domain merging.

  4. Athena-Brain Technical Report: An Efficient Robot Brain for General Intelligence and Embodied Interaction

    cs.AI 2026-07 conditional novelty 6.0

    An 8B LLM post-trained with SFT, RL, embodied-expert training, and model merging reaches high in-domain embodied-task success with very short responses.

  5. Recoverable but Not Stationary:Local Linear Structures in Weights and Activations

    cs.LG 2026-06 unverdicted novelty 6.0

    Local low-rank task-gradient structures exist in weights and activations but are non-stationary, with initial recovery updates forming a basis capturing 77% of LoRA displacement and parameter steps aligning 0.58 cosin...

  6. Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining

    cs.LG 2026-05 unverdicted novelty 6.0

    DG-Hard uses Donoho-Gavish hard thresholding on the fine-tuning weight delta to separate task-aligned signal from noise-like residual, recovering damaged capabilities while preserving target-task gains.

  7. Unlocking the Potential of Continual Model Merging: An ODE Perspective

    cs.LG 2026-05 unverdicted novelty 6.0

    Introduces ODE-M, an ODE-based merging method for continual model merging that follows low-loss connecting paths to mitigate catastrophic forgetting.

  8. Unlocking the Potential of Continual Model Merging: An ODE Perspective

    cs.LG 2026-05 unverdicted novelty 6.0

    ODE-M formulates continual model merging as a barrier-aware ODE trajectory in parameter space, using first-order feedback and a utility-aware schedule to balance retained knowledge and new task performance.

  9. Unlocking the Potential of Continual Model Merging: An ODE Perspective

    cs.LG 2026-05 unverdicted novelty 6.0

    ODE-M traces low-loss connecting paths via time-dependent velocity fields and barrier constraints to improve controllability and reduce forgetting in continual model merging.

  10. Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts

    cs.LG 2026-04 unverdicted novelty 6.0

    BAR trains independent domain experts via separate mid-training, SFT, and RL pipelines then composes them with a MoE router to match monolithic retraining performance at lower cost and without catastrophic forgetting.

  11. Zero-Shot Synthetic-to-Real Handwritten Text Recognition via Task Analogies

    cs.CV 2026-04 unverdicted novelty 6.0

    A method learns synthetic-to-real parameter corrections from source languages and transfers them to target languages without any real target data, improving HTR across five languages and six models.

  12. Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective

    cs.AI 2026-07 conditional novelty 5.0

    After truncating or expanding checkpoints to a shared shape, small-ratio weight averaging slightly improves average benchmark scores over strong Qwen sources, but headline gains are inflated by per-task best-ratio selection.

  13. First-Order Predictable but Pairwise Fragile: Local Task Adaptation in Trained Transformers

    cs.LG 2026-07 conditional novelty 5.0

    Single task-vector perturbations around a multitask LoRA point are first-order linear to 1e-2, but pairwise update-order sensitivity is set by a per-pair Lie bracket and can appear inside that window.

  14. DeltaMerge-LowRes: Composing Language and Task Deltas for Low-Resource Adaptation

    cs.CL 2026-07 conditional novelty 5.0

    A TIES-style merge across language-delta and task-delta axes (cross-axis TIES) beats additive and task-only composition on low-resource summarisation and QA.

  15. Black-Box Optimization of Mixed Binary-Continuous Variables: Challenges and Opportunities in Evolutionary Model Merging

    cs.NE 2026-05 unverdicted novelty 5.0

    Data flow space model merging is formalized as a mixed binary-continuous black-box optimization problem, where a structured approach respecting variable dependencies achieves 6.7% higher accuracy and 51.4% smaller sea...