Pith. sign in

REVIEW 8 cited by

Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning

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 2312.12379 v5 pith:YEMOIGPT submitted 2023-12-19 cs.CV

classification cs.CV
keywords expertsinstructionmixturemocletasksvision-languagecluster-conditionaldifferent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Instruction tuning of Large Vision-language Models (LVLMs) has revolutionized the development of versatile models with zero-shot generalization across a wide range of downstream vision-language tasks. However, the diversity of training tasks of different sources and formats would lead to inevitable task conflicts, where different tasks conflict for the same set of model parameters, resulting in sub-optimal instruction-following abilities. To address that, we propose the Mixture of Cluster-conditional LoRA Experts (MoCLE), a novel Mixture of Experts (MoE) architecture designed to activate the task-customized model parameters based on the instruction clusters. A separate universal expert is further incorporated to improve generalization capabilities of MoCLE for novel instructions. Extensive experiments on InstructBLIP and LLaVA demonstrate the effectiveness of MoCLE.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Dynamic-DINO: Fine-Grained Mixture of Experts Tuning for Real-time Open-Vocabulary Object Detection

    cs.CV 2025-07 conditional novelty 7.0 of 10

    MoE fine-tuning with decomposed pre-trained FFN experts lets a real-time open-vocabulary detector beat a much larger-data baseline with similar active parameter count.

  2. MED-DSLC: Multi-Expert-Domain Classification via Domain Supervision and Logit Calibration

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Domain-supervised MoE routing plus per-domain temperature scaling restores global logit calibration when merging frozen LoRA experts, cutting cross-domain interference in multi-domain VLM classification.

  3. Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    Sleep-time Knowledge Seeding plus Dreaming lets LLMs expand capacity, distill fragile in-context memories into stable parameters, and self-improve without human labels.

  4. Cartridges: Lightweight and general-purpose long context representations via self-study

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A per-corpus trained KV cache, called a Cartridge, matches full-context in-context learning quality on long-document benchmarks while using up to 38.6x less serving memory.

  5. MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping

    cs.LG 2025-06 conditional novelty 5.0 of 10

    Grouping instruction-tuning datasets by redundancy, uniqueness, or synergy of text-image interaction improves vision-language model accuracy over single-task and unselective multi-task tuning.

  6. Mixpert: Mitigating Multimodal Learning Conflicts with Efficient Mixture-of-Vision-Experts

    cs.CV 2025-05 conditional novelty 5.0 of 10

    Splitting the vision encoder of an MLLM into domain-specific experts with a lightweight router yields small benchmark improvements at near-zero extra inference cost.

  7. ScatterPrism: convergence for generative simulation and inverse problems in particle and nuclear physics

    cs.LG 2026-04 unverdicted novelty 4.0 of 10

    Standard Conditional Flow Matching loss is a misleading early plateau; physics-informed metrics keep improving, so ScatterPrism and multi-metric diagnostics are needed for kinematic fidelity.

  8. ECCV 2024 W-CODA: 1st Workshop on Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving

    cs.CV 2025-07 unverdicted novelty 1.0 of 10

    A workshop report documenting the ECCV 2024 W-CODA event, its accepted papers, speakers, and the dual-track corner case understanding and generation challenge.

Pith tools