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
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.
Forward citations
Cited by 8 Pith papers
-
Dynamic-DINO: Fine-Grained Mixture of Experts Tuning for Real-time Open-Vocabulary Object Detection
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.
-
MED-DSLC: Multi-Expert-Domain Classification via Domain Supervision and Logit Calibration
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.
-
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
Sleep-time Knowledge Seeding plus Dreaming lets LLMs expand capacity, distill fragile in-context memories into stable parameters, and self-improve without human labels.
-
Cartridges: Lightweight and general-purpose long context representations via self-study
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.
-
MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping
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.
-
Mixpert: Mitigating Multimodal Learning Conflicts with Efficient Mixture-of-Vision-Experts
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.
-
ScatterPrism: convergence for generative simulation and inverse problems in particle and nuclear physics
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.
-
ECCV 2024 W-CODA: 1st Workshop on Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving
A workshop report documenting the ECCV 2024 W-CODA event, its accepted papers, speakers, and the dual-track corner case understanding and generation challenge.
Discussion (0). Sign in to comment.