Pith. sign in

REVIEW 13 cited by

TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones

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 2312.16862 v3 pith:P3CC5WS6 submitted 2023-12-28 cs.CV cs.CL

classification cs.CVcs.CL
keywords languagetinygpt-vmodelstrainingbackbonescomputationalefficientinference
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In recent years, multimodal large language models (MLLMs) such as GPT-4V have demonstrated remarkable advancements, excelling in a variety of vision-language tasks. Despite their prowess, the closed-source nature and computational demands of such models limit their accessibility and applicability. This study introduces TinyGPT-V, a novel open-source MLLM, designed for efficient training and inference across various vision-language tasks, including image captioning (IC) and visual question answering (VQA). Leveraging a compact yet powerful architecture, TinyGPT-V integrates the Phi-2 language model with pre-trained vision encoders, utilizing a unique mapping module for visual and linguistic information fusion. With a training regimen optimized for small backbones and employing a diverse dataset amalgam, TinyGPT-V requires significantly lower computational resources 24GB for training and as little as 8GB for inference without compromising on performance. Our experiments demonstrate that TinyGPT-V, with its language model 2.8 billion parameters, achieves comparable results in VQA and image inference tasks to its larger counterparts while being uniquely suited for deployment on resource-constrained devices through innovative quantization techniques. This work not only paves the way for more accessible and efficient MLLMs but also underscores the potential of smaller, optimized models in bridging the gap between high performance and computational efficiency in real-world applications. Additionally, this paper introduces a new approach to multimodal large language models using smaller backbones. Our code and training weights are available in the supplementary material.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 13 Pith papers

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

  1. Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Jointly optimizing visual-token retention and LLM depth/width under a shared FLOPs budget yields better accuracy-efficiency Pareto frontiers than optimizing either dimension alone.

  2. EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge

    cs.AR 2025-05 conditional novelty 6.0 of 10

    EdgeMM is a 22nm multi-core CPU that combines systolic-array and compute-in-memory coprocessors with adaptive activation-aware pruning, reported as 2.84x faster than a laptop RTX 3060 for multimodal LLMs.

  3. Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models

    cs.MM 2025-01 conditional novelty 6.0 of 10

    A tuning-free pipeline using frozen LLaMA-3, MiniGPT-v2, and Video-ChatGPT reports state-of-the-art zero-shot video moment retrieval on three benchmarks.

  4. Enhancing Multimodal Large Language Models Complex Reason via Similarity Computation

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Simignore improves multimodal LLM complex question answering on ScienceQA by masking image tokens whose embeddings have low cosine similarity to the text prompt.

  5. [CLS] Token Tells Everything Needed for Training-free Efficient MLLMs

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Using the CLIP [CLS] token's attention to prune image tokens before the LLM runs outperforms prior training-free pruning methods on LLaVA-1.5-7B and speeds up inference.

  6. Efficient Multi-modal Large Language Models via Visual Token Grouping

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A new grouping mechanism, VisToG, uses semantic tokens and isolated attention inside a pretrained CLIP vision encoder to compress visual tokens for MLLMs, retaining roughly 98% performance while cutting inference time...

  7. DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A training-free two-stage token compression method speeds up video language model inference by about 1.5x and cuts memory use, while keeping accuracy close to the uncompressed model.

  8. TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks

    cs.LG 2025-05 reject novelty 5.0 of 10

    TinyAlign improves lightweight VLMs by retrieving compressed image-text memory items to augment visual inputs, claiming large loss and data-efficiency gains, but the memory bank is sampled from the training captions, ...

  9. Task-Oriented Semantic Communication in Large Multimodal Models-based Vehicle Networks

    cs.AI 2025-05 conditional novelty 5.0 of 10

    A task-oriented semantic communication framework for LLaVA-based vehicle assistants that crops image slices matched to the user's question and allocates transmission power by fused objective and subjective attention, ...

  10. NanoVLMs: How small can we go and still make coherent Vision Language Models?

    cs.CV 2025-02 reject novelty 5.0 of 10

    NanoVLMs, 5M to 25M parameter vision-language models trained on simplified GPT-4o captions, are judged by GPT-4o as nearly as coherent as the 50x larger Kosmos-2 on a 25-sample test.

  11. Eve: Efficient Multimodal Vision Language Models with Elastic Visual Experts

    cs.CV 2025-01 conditional novelty 5.0 of 10

    A 1.8B-parameter vision-language model, Eve, uses elastic visual experts and type-aware token routing to reach a 68.87% average on six VLM benchmarks while preserving language performance.

  12. EvoMoE: Expert Evolution in Mixture of Experts for Multimodal Large Language Models

    cs.CL 2025-05 conditional novelty 4.0 of 10

    EvoMoE creates MoE experts as decaying averages of a single trained FFN and routes tokens with hypernetwork-generated weights, yielding small benchmark gains over MoE-LLaVA.

  13. Multimodal Large Language Models for Medicine: A Comprehensive Survey

    cs.LG 2025-04 conditional novelty 2.0 of 10

    A comprehensive review cataloging medical MLLMs, their uses in report generation, diagnosis, and treatment, and the challenges of accuracy, hallucination, fairness, privacy, and deployment.

Pith tools