Pith. sign in

REVIEW 21 cited by

ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation

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 2407.06135 v1 pith:WMYI6KBX submitted 2024-07-08 cs.CL cs.AIcs.CV

ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation

classification cs.CL cs.AIcs.CV
keywords generationmultimodalanolelargemodelsnativeautoregressiveimage-text
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Previous open-source large multimodal models (LMMs) have faced several limitations: (1) they often lack native integration, requiring adapters to align visual representations with pre-trained large language models (LLMs); (2) many are restricted to single-modal generation; (3) while some support multimodal generation, they rely on separate diffusion models for visual modeling and generation. To mitigate these limitations, we present Anole, an open, autoregressive, native large multimodal model for interleaved image-text generation. We build Anole from Meta AI's Chameleon, adopting an innovative fine-tuning strategy that is both data-efficient and parameter-efficient. Anole demonstrates high-quality, coherent multimodal generation capabilities. We have open-sourced our model, training framework, and instruction tuning data.

discussion (0)

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

Forward citations

Cited by 21 Pith papers

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

  1. Parallel Jacobi Decoding for Fast Autoregressive Image Generation

    cs.CV 2026-06 conditional novelty 7.0

    Parallel Jacobi Decoding accelerates autoregressive image models 4.8x-6.4x by using 2D spatial draft expansion and adjusted attention masks while keeping generation quality competitive.

  2. DeepLatent: Think with Images via Parallel Latent Visual Reasoning

    cs.CV 2026-05 unverdicted novelty 7.0

    DeepLatent introduces a parallel latent visual reasoning framework with learnable 2D tokens and continuous RL, trained via distillation then RL, plus a new 180K dataset, claiming SOTA benchmark results.

  3. ETCHR: Editing To Clarify and Harness Reasoning

    cs.CV 2026-05 unverdicted novelty 7.0

    A decoupled question-conditioned image editor trained via supervised imitation then VLM-reward enhancement improves MLLM visual reasoning Pass@1 by 4.6-5.5 points across models and tasks.

  4. ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both

    cs.CV 2026-05 unverdicted novelty 7.0

    ATLAS uses a single functional token to unify agentic and latent visual reasoning without image generation or external execution.

  5. Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning

    cs.AI 2026-01 unverdicted novelty 7.0

    Omni-R1 unifies multimodal reasoning by generating intermediate images during the process in a SFT-plus-RL framework, with an Omni-R1-Zero variant that matches or exceeds it using only text data.

  6. VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping

    cs.CV 2025-11 conditional novelty 7.0

    VVS accelerates visual AR image generation by partially skipping verifications in speculative decoding, achieving 2.8x fewer target forward passes while preserving competitive quality.

  7. Improving Sample Diversity in Autoregressive Text-to-Image Generation via Cluster Truncation

    cs.CV 2026-07 conditional novelty 6.0

    p-less cluster decoding, which truncates and samples over K-means clusters of visual tokens rather than individual tokens, yields higher per-prompt sample diversity than default or dynamic-temperature baselines on mos...

  8. DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics

    cs.LG 2026-07 accept novelty 6.0

    Schema-guided interleaved state-transition pretraining with selective attention and reweighted loss improves hierarchical visual dynamics modeling for narrative generation and world simulation.

  9. NavWM: A Unified Navigation World Model for Foresight-Driven Planning

    cs.RO 2026-06 unverdicted novelty 6.0

    NavWM unifies latent world tokens and anchor-based multimodal trajectory forecasting into a closed-loop planner that improves future state generation and zero-shot navigation.

  10. Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement

    cs.CV 2026-06 conditional novelty 6.0

    Supervising text–image handoffs with Reflective SFT and Flow-GRPO (MoTiF) reduces modal isolation and raises accuracy on four visual puzzle benchmarks versus end-task-only training.

  11. Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement

    cs.CV 2026-06 unverdicted novelty 6.0

    MoTiF is a two-stage framework that optimizes modality transition fidelity in interleaved multimodal models via Reflective SFT and Flow-GRPO, yielding gains on visual puzzle benchmarks.

  12. SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learning

    cs.AI 2026-06 unverdicted novelty 6.0

    SVoT uses RL with GRPO to train MLLMs on interleaved textual and visual reasoning chains for multi-hop spatial tasks, achieving up to 65% accuracy gains on new domains with quantitative state verification.

  13. CASCADE: Context-Aware Relaxation for Speculative Image Decoding

    cs.CV 2026-05 unverdicted novelty 6.0

    CASCADE formalizes semantic interchangeability and convergence in target model representations to enable context-aware acceptance relaxation in tree-based speculative decoding, delivering up to 3.6x speedup on text-to...

  14. SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation

    cs.CV 2026-03 accept novelty 6.0

    SJD-PAC combines proactive multi-path drafting and adaptive continuation to raise average acceptance length in Speculative Jacobi Decoding, delivering 3.8 imes lossless wall-clock speedup on Lumina-mGPT and Emu3.

  15. Mull-Tokens: Modality-Agnostic Latent Thinking

    cs.CV 2025-12 unverdicted novelty 6.0

    Mull-Tokens are modality-agnostic latent tokens that enable free-form multimodal thinking and deliver up to 16% gains on spatial reasoning benchmarks.

  16. GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning

    cs.CV 2025-08 unverdicted novelty 6.0

    GoViG decomposes goal-conditioned navigation instruction generation into visual state prediction and instruction synthesis using an autoregressive multimodal LLM with one-pass and interleaved reasoning, showing gains ...

  17. Imagine while Reasoning in Space: Multimodal Visualization-of-Thought

    cs.CL 2025-01 unverdicted novelty 6.0

    MVoT lets multimodal models create coherent images during chain-of-thought reasoning via a token discrepancy loss, yielding competitive or better results than text-only CoT on dynamic spatial tasks.

  18. ProLaViT: Learning Progressive Latent Visual Thoughts in Structured Latent Space

    cs.CV 2026-07 conditional novelty 5.5

    Progressive multi-step latent visual thoughts, endogenously distilled from a model's own encoder on synthetic trajectories and regularized by distance-weighted diversity, improve MLLM visual reasoning accuracy and efficiency.

  19. UniCanvas: A Diffusion-base Unified Model for Text-in-Image Joint Generation

    cs.CV 2026-06 unverdicted novelty 5.0

    UniCanvas introduces a diffusion-based approach for unified multimodal generation by embedding text as visual patterns within images on a shared canvas.

  20. SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

    cs.CV 2026-05 unverdicted novelty 5.0

    SenseNova-U1 presents native unified multimodal models that match top understanding VLMs while delivering strong performance in image generation, infographics, and interleaved tasks via the NEO-unify architecture.

  21. Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation

    cs.CV 2026-06 unverdicted novelty 4.0

    ILLUME-X is a unified multimodal model that generates free-form interleaved text-image sequences via an expanded data pipeline, progressive self-adaptive training, and ILScore evaluation, claiming outperformance over ...