pith. sign in

arxiv: 2311.05437 · v1 · pith:UNXJRTXJnew · submitted 2023-11-09 · 💻 cs.CV · cs.AI· cs.CL· cs.LG· cs.MM

LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents

classification 💻 cs.CV cs.AIcs.CLcs.LGcs.MM
keywords llava-plusmultimodaltoolscapabilitiesmodelsabilityacquireactivate
0
0 comments X
read the original abstract

LLaVA-Plus is a general-purpose multimodal assistant that expands the capabilities of large multimodal models. It maintains a skill repository of pre-trained vision and vision-language models and can activate relevant tools based on users' inputs to fulfill real-world tasks. LLaVA-Plus is trained on multimodal instruction-following data to acquire the ability to use tools, covering visual understanding, generation, external knowledge retrieval, and compositions. Empirical results show that LLaVA-Plus outperforms LLaVA in existing capabilities and exhibits new ones. It is distinct in that the image query is directly grounded and actively engaged throughout the entire human-AI interaction sessions, significantly improving tool use performance and enabling new scenarios.

This paper has not been read by Pith yet.

discussion (0)

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

Forward citations

Cited by 13 Pith papers

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

  1. Waking Up Blind: Cold-Start Optimization of Supervision-Free Agentic Trajectories for Grounded Visual Perception

    cs.AI 2026-04 unverdicted novelty 7.0

    SPECTRA enables supervision-free bootstrapping of agentic capabilities in SVLMs via cascaded tool rollout alignment, multi-objective rewards, and the TIU metric, yielding up to 5% higher task accuracy and 9% better to...

  2. ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents

    cs.AI 2026-06 unverdicted novelty 6.0

    ReGRPO augments group-relative policy optimization with a reflective data engine that generates ErrorType-Evidence-FixPlan triplets from near-miss tool actions to improve recovery in multimodal agents.

  3. Mitigating Coordinate Prediction Bias from Positional Encoding Failures

    cs.CV 2025-10 unverdicted novelty 6.0

    VPSG corrects predictable directional coordinate biases in MLLMs by shuffling visual positional encodings to isolate unconditioned tendencies and steering digit decoding with a lightweight finite-state machine, yieldi...

  4. Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language Models

    cs.CV 2025-05 unverdicted novelty 6.0

    Circle-RoPE achieves cross-modal positional disentanglement in VLMs by mapping 2D image tokens to a cone-like annulus orthogonal to the text axis, with PTD=0 eliminating RoPE geometric bias while preserving intra-imag...

  5. Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model

    cs.AI 2024-08 unverdicted novelty 6.0

    A single transformer combines language modeling loss and diffusion loss on mixed-modality data, scaling to 7B parameters and 2T tokens while matching specialized language and diffusion models.

  6. MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

    cs.CV 2024-03 unverdicted novelty 6.0

    MM1 models achieve state-of-the-art few-shot multimodal results by pre-training on a careful mix of image-caption, interleaved, and text-only data with optimized image encoders.

  7. IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools

    cs.CV 2026-05 unverdicted novelty 5.0

    IndusAgent achieves state-of-the-art zero-shot performance on industrial anomaly benchmarks by using a custom Indus-CoT dataset, dynamic tool orchestration, and gated RL to optimize anomaly classification, localizatio...

  8. Second-Order Multi-Level Variance Correction for Modality Competition in Multimodal Models

    cs.CV 2026-05 unverdicted novelty 5.0

    Introduces ML-FOP-SOAP optimizer using Fisher-Orthogonal Projection and hierarchical folding to mitigate modality competition in multimodal autoregressive training, reporting gains over AdamW on Janus and Emu3.

  9. Less Detail, Better Answers: Degradation-Driven Prompting for VQA

    cs.CV 2026-04 unverdicted novelty 5.0

    Degradation-Driven Prompting improves VQA by intentionally reducing image detail and using masks, lines, and examples to guide models toward essential structures.

  10. MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices

    cs.CV 2023-12 unverdicted novelty 5.0

    MobileVLM achieves on-par performance with much larger vision-language models on standard benchmarks while delivering state-of-the-art inference speeds of 21.5 tokens per second on Snapdragon 888 CPU and 65.3 on Jetso...

  11. Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction

    cs.MM 2024-10 unverdicted novelty 3.0

    Survey proposing a taxonomy for document parsing into pipeline-based systems and VLM-driven unified models, reviewing components, metrics, benchmarks, and challenges.

  12. Large Language Models: A Survey

    cs.CL 2024-02 accept novelty 3.0

    The paper surveys key large language models, their training methods, datasets, evaluation benchmarks, and future research directions in the field.

  13. A Survey on Hallucination in Large Vision-Language Models

    cs.CV 2024-02 unverdicted novelty 3.0

    This survey reviews the definition, symptoms, evaluation benchmarks, root causes, and mitigation methods for hallucinations in large vision-language models.