Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM

• URL: http://arxiv.org/abs/2403.07816v1
• Date: Tue, 12 Mar 2024 16:54:58 GMT
• Title: Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
• Abstract summary: We investigate efficient methods for training Large Language Models (LLMs) to possess capabilities in multiple specialized domains. Our method, named Branch-Train-MiX (BTX), starts from a seed model, which is branched to train experts in embarrassingly parallel fashion. BTX generalizes two special cases, the Branch-Train-Merge method, which does not have the MoE finetuning stage to learn routing, and sparse upcycling, which omits the stage of training experts asynchronously.
• Score: 81.18305296110853
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We investigate efficient methods for training Large Language Models (LLMs) to possess capabilities in multiple specialized domains, such as coding, math reasoning and world knowledge. Our method, named Branch-Train-MiX (BTX), starts from a seed model, which is branched to train experts in embarrassingly parallel fashion with high throughput and reduced communication cost. After individual experts are asynchronously trained, BTX brings together their feedforward parameters as experts in Mixture-of-Expert (MoE) layers and averages the remaining parameters, followed by an MoE-finetuning stage to learn token-level routing. BTX generalizes two special cases, the Branch-Train-Merge method, which does not have the MoE finetuning stage to learn routing, and sparse upcycling, which omits the stage of training experts asynchronously. Compared to alternative approaches, BTX achieves the best accuracy-efficiency tradeoff.

Related papers

• Tying the Loop -- Tied Expert Layers in Mixture-of-Experts Language Models [50.34585122347149]
  We introduce Expert Tying, an architectural modification that shares expert parameters across consecutive transformer layers.<n>We evaluate this approach across common, state-of-the-art architectures, including OLMoE, Qwen3, and DeepSeek-style MoEs.
  arXiv  Detail & Related papers  (2026-06-15T15:08:09Z)
• Mix-MoE: Improving Multilingual Machine Translation of Large Language Models through Mixed MoEs [58.06302309139978]
  Large Language Models (LLMs) have shown great promise in multilingual machine translation (MT)<n>We propose Mix-MoE, a mixed Mixture-of-Experts framework designed to train LLMs for multilingual MT.<n>Our framework operates in two distinct stages: (1) post-pretraining with MoE on monolingual corpora, and (2) post-pretraining with MoE on parallel corpora.
  arXiv  Detail & Related papers  (2026-05-23T17:35:43Z)
• LAER-MoE: Load-Adaptive Expert Re-layout for Efficient Mixture-of-Experts Training [27.022187489292467]
  In this paper, we introduce LAER-MoE, an efficient MoE training framework.<n>The core of LAER-MoE is a novel parallel paradigm, Fully Sharded Expert Parallel (FSEP), which fully partitions each expert parameter by the number of devices.<n>We perform experiments on an A100 cluster, and the results indicate that our system achieves up to 1.69x acceleration compared to the current state-of-the-art training systems.
  arXiv  Detail & Related papers  (2026-02-12T08:08:03Z)
• Rollout-Training Co-Design for Efficient LLM-Based Multi-Agent Reinforcement Learning [21.32826098306222]
  Existing training frameworks fail to address the unique system-level challenges of multi-agent reinforcement learning.<n>We propose FlexMARL, the first end-to-end training framework that holistically optimize rollout, training, and their orchestration.<n>We show that FlexMARL achieves up to 7.3x speedup and improves hardware utilization by up to 5.6x compared to existing frameworks.
  arXiv  Detail & Related papers  (2026-02-10T09:27:03Z)
• MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language Models [28.87682703032017]
  Mixture-of-Experts (MoE) models scale large language models efficiently by sparsely activating experts, but once an expert is selected, it is executed fully.<n>We propose Mixture of Slimmable Experts (MoSE), an MoE architecture in which each expert has a nested, slimmable structure that can be executed at variable widths.
  arXiv  Detail & Related papers  (2026-02-05T19:48:41Z)
• SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning [83.66308307152808]
  We propose StAbilized Mixture-of-Experts (SAME) for Multimodal Continual Instruction Tuning (MCIT)<n>SAME stabilizes expert selection by decomposing routing dynamics into subspaces and updating only task-relevant directions.<n>It also introduces adaptive expert activation to freeze selected experts during training, reducing redundant and cross-task interference.
  arXiv  Detail & Related papers  (2026-02-02T11:47:06Z)
• Token-Level LLM Collaboration via FusionRoute [60.72307345997823]
  FusionRoute is a token-level multi-LLM collaboration framework.<n>It selects the most suitable expert at each decoding step and contributes a complementary logit that refines or corrects the selected expert's next-token distribution.<n>It outperforms both sequence- and token-level collaboration, model merging, and direct fine-tuning.
  arXiv  Detail & Related papers  (2026-01-08T16:53:16Z)
• Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning [49.90176890917986]
  Mixture-of-Experts (MoE) has emerged as a powerful framework for multi-task learning (MTL)<n>Existing MoE-MTL methods often rely on single-task pretrained backbones and suffer from redundant adaptation and inefficient knowledge sharing.<n>We propose adaptive shared experts (ASE) within a low-rank adaptation (LoRA) based MoE, where shared experts are assigned router-computed gating weights jointly normalized with sparse experts.
  arXiv  Detail & Related papers  (2025-10-01T06:49:19Z)
• Symbolic Mixture-of-Experts: Adaptive Skill-based Routing for Heterogeneous Reasoning [76.10639521319382]
  We propose Symbolic-MoE, a symbolic, text-based, and gradient-free Mixture-of-Experts framework. We show that Symbolic-MoE's instance-level expert selection improves performance by a large margin but -- when implemented naively -- can introduce a high computational overhead.
  arXiv  Detail & Related papers  (2025-03-07T18:03:13Z)
• BTS: Harmonizing Specialized Experts into a Generalist LLM [52.026293450944635]
  Branch-Train-Stitch (BTS) is an efficient training algorithm for combining independently trained large language model (LLM) experts into a single, capable generalist model. Compared to alternative model merging approaches, BTS yields the best generalist performance on a variety of downstream tasks.
  arXiv  Detail & Related papers  (2025-01-31T07:54:34Z)
• Ada-K Routing: Boosting the Efficiency of MoE-based LLMs [6.954735360168147]
  We propose a novel Ada-K routing strategy that dynamically adjusts the number of activated experts for each token. Our strategy incorporates learnable and lightweight allocator modules that decide customized expert resource allocation tailored to the contextual needs for each token.
  arXiv  Detail & Related papers  (2024-10-14T12:50:04Z)
• Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging [36.0133566024214]
  Upcycling Instruction Tuning (UpIT) is a data-efficient approach for tuning a dense pre-trained model into a MoE instruction model. To ensure each specialized expert in the MoE model works as expected, we select a small amount of seed data that each expert excels to pre-optimize the router.
  arXiv  Detail & Related papers  (2024-10-02T14:48:22Z)
• BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts [41.83123857437985]
  Training MoEs from scratch in a large-scale regime is prohibitively expensive. We propose BAM (Branch-Attend-Mix), a simple yet effective method that addresses this shortcoming. Our experiments on seed models ranging from 590 million to 2 billion parameters demonstrate that BAM surpasses baselines in both perplexity and downstream task performance.
  arXiv  Detail & Related papers  (2024-08-15T17:19:12Z)
• Layerwise Recurrent Router for Mixture-of-Experts [42.36093735411238]
  Mixture-of-Experts (MoE) architecture stands out for its ability to scale model size without significantly increasing training costs. Current MoE models often display parameter inefficiency. We introduce the Layerwise Recurrent Router for Mixture-of-Experts (RMoE)
  arXiv  Detail & Related papers  (2024-08-13T10:25:13Z)
• Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts [54.529880848937104]
  We develop a unified MLLM with the MoE architecture, named Uni-MoE, that can handle a wide array of modalities. Specifically, it features modality-specific encoders with connectors for a unified multimodal representation. We evaluate the instruction-tuned Uni-MoE on a comprehensive set of multimodal datasets.
  arXiv  Detail & Related papers  (2024-05-18T12:16:01Z)
• T-REX: Mixture-of-Rank-One-Experts with Semantic-aware Intuition for Multi-task Large Language Model Finetuning [31.276142111455847]
  Large language models (LLMs) encounter significant adaptation challenges in diverse multitask finetuning.<n>We design a novel framework, mixunderlinetextbfTureunderlinetextbf-of-underlinetextbfRank-onunderlinetextbfE-eunderlinetextbfXper ts (textttT-REX)<n>Rank-1 experts enable a mix-and-match mechanism to quadratically expand the vector subspace of experts with linear parameter overheads, achieving approximate error reduction with optimal
  arXiv  Detail & Related papers  (2024-04-13T12:14:58Z)
• Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model Inference [3.217776693788795]
  We propose a lightweight optimization technique called ExFlow to largely accelerate the inference of pre-trained MoE models. By exploiting the inter-layer expert affinity, our solution can be directly applied to pre-trained MoE models without any fine-tuning or accuracy degradation. Our solution beats the cutting-edge MoE implementations with experts from 8 to 64, with up to 2.2x improvement in inference throughput.
  arXiv  Detail & Related papers  (2024-01-16T14:16:47Z)
• Adapted Multimodal BERT with Layer-wise Fusion for Sentiment Analysis [84.12658971655253]
  We propose Adapted Multimodal BERT, a BERT-based architecture for multimodal tasks. adapter adjusts the pretrained language model for the task at hand, while the fusion layers perform task-specific, layer-wise fusion of audio-visual information with textual BERT representations. In our ablations we see that this approach leads to efficient models, that can outperform their fine-tuned counterparts and are robust to input noise.
  arXiv  Detail & Related papers  (2022-12-01T17:31:42Z)
• Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models [106.65127123304842]
  Branch-Train-Merge (BTM) is an efficient algorithm for parallel training of large language models (LLMs) BTM learns a set of independent expert LMs (ELMs), each specialized to a different textual domain. Experiments show that BTM improves in- and out-of-domain perplexities as compared to GPT-style Transformer LMs.
  arXiv  Detail & Related papers  (2022-08-05T17:46:38Z)
• StableMoE: Stable Routing Strategy for Mixture of Experts [109.0602120199226]
  Mixture-of-Experts (MoE) technique can scale up the model size of Transformers with an affordable computational overhead. We propose StableMoE with two training stages to address the routing fluctuation problem. Results show that StableMoE outperforms existing MoE methods in terms of both convergence speed and performance.
  arXiv  Detail & Related papers  (2022-04-18T16:48:19Z)
• Taming Sparsely Activated Transformer with Stochastic Experts [76.0711573018493]
  Sparsely activated models (SAMs) can easily scale to have outrageously large amounts of parameters without significant increase in computational cost. In this paper, we propose a new expert-based model, THOR (Transformer witH StOchastic ExpeRts) Unlike classic expert-based models, such as the Switch Transformer, experts in THOR are randomly activated for each input during training and inference.
  arXiv  Detail & Related papers  (2021-10-08T17:15:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.