Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models

• URL: http://arxiv.org/abs/2606.13558v1
• Date: Thu, 11 Jun 2026 16:41:25 GMT
• Title: Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models
• Abstract summary: BitResEdit is a training-free editor for bitwise-residual VAR generators such as Infinity.<n>It performs source-negative guidance by tilting the post-CFG per-bit log-odds along a source--target contrast computed on a shared edited prefix.<n>It converts the sampled bits into per-scale continuous-code residuals, gates them with a localization mask, and re-injects them through the generator's native sum-of-scales.
• Score: 85.59447229497101
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-guided image editing with visual autoregressive (VAR) generators requires controlling both what the model samples and where the sampled change is written back into the image code. Existing VAR editors mainly operate on token streams, features, or flat next-token logits, leaving two native structures of bitwise-residual VAR models underused: the per-bit Bernoulli prediction head and the additive multi-scale residual code field from which the image is assembled. We propose BitResEdit, a training-free editor for bitwise-residual VAR generators such as Infinity. BitEdit performs source-negative guidance by tilting the post-CFG per-bit log-odds along a source--target contrast computed on a shared edited prefix, then projects each update into a closed-form Bernoulli-KL trust region around the clean CFG sampler. ResEdit converts the sampled bits into per-scale continuous-code residuals, gates them with a localization mask, and re-injects them through the generator's native sum-of-scales. Together they couple decision-time bit guidance with combination-time code composition, so masked-out latent features are preserved exactly by code arithmetic while localized, scale-aware edits are applied inside the target region. On PIE-Bench with Infinity-2B, BitResEdit attains the strongest text alignment among same-backbone VAR editors, improving CLIP on the edited region by +1.07 over the strongest prior editor while keeping background preservation competitive with it. Ablations show BitEdit and ResEdit play complementary roles in target alignment and background preservation.

Related papers

• GRNEdit: Efficient General Video Editing from a New Binary-Evidence Perspective in Generative Refinement Networks [19.4535662221234]
  General video editing seeks to unify diverse editing operations within a single, intuitive interface.<n>GRNEdit is a lightweight two-stage framework that encodes visual semantics through combinations of bits.<n>We trained on only 0.6M pairs with less than 3% conditioning parameters, GRNEdit-2B and GRNEdit-8B achieve scores of 4.03 and 4.18 on OpenVE-Bench.
  arXiv  Detail & Related papers  (2026-08-17T09:31:56Z)
• Diffusion Image Editing via Asynchronous Token Decoding [9.39531887626368]
  ATDEdit is an inference-time framework that views each sampler step as a parallel update of a globally coupled token matrix.<n>It estimates editable locations using token-wise conditional surprisal and applies target-conditioned corrections to the selected token set.<n>It supplies source key/value memory at keep-token positions and projects selected keep-token latent rows back to their source values.
  arXiv  Detail & Related papers  (2026-08-10T09:02:13Z)
• Model the Edit, Not the Image: Visual Autoregressive Editing from a Source-Centric Perspective [23.408232115772833]
  Next-scale visual autoregressive models ( VARs) have emerged as a powerful generative paradigm, producing high-quality images through efficient coarse-to-fine prediction.<n>We propose textbfEditMod, which compares source- and target-conditioned predictions under a shared autoregressive context.<n>Experiments show that EditMod achieves leading source-image fidelity while maintaining strong text alignment, and completes end-to-end editing of a 1K image in only 1.57 seconds on a single A100 GPU.
  arXiv  Detail & Related papers  (2026-08-10T03:05:09Z)
• ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition [60.25038184390257]
  ReDesign is an agentic framework that grows an editable layer hierarchy by selecting and composing specialized tools across modalities.<n>To evaluate editability at scale, we introduce the Figma Edit Replay Benchmark consisting of 909 raw Figma files and 14,796 controlled edit instructions that replay edits on reconstructed outputs.
  arXiv  Detail & Related papers  (2026-07-28T10:53:33Z)
• Reasoning to Align: Implicit Reasoning in Diffusion Transformers for Video Editing [55.211537893248675]
  We propose RVEDiT, an implicit Reasoning Video Editing DiT framework built around two complementary components.<n> RVEDiT consistently outperforms state-of-the-art baselines, with particularly strong gains on localized and compositional edits.
  arXiv  Detail & Related papers  (2026-05-23T17:22:14Z)
• Edit Where You Mean: Region-Aware Adapter Injection for Mask-Free Local Image Editing [28.295031615161136]
  Large diffusion transformers (DiTs) follow global editing instructions well but consistently leak local edits into unrelated regions.<n>We introduce AdaptEdit, a co-trained, instruction- and region-aware adapter framework.<n> AdaptEdit achieves state-of-the-art results, simultaneously outperforming mask-free and oracle-mask baselines.
  arXiv  Detail & Related papers  (2026-04-26T15:28:02Z)
• SpotEdit: Selective Region Editing in Diffusion Transformers [66.44912649206553]
  SpotEdit is a training-free diffusion editing framework that selectively updates only the modified regions.<n>By reducing unnecessary computation and maintaining high fidelity in unmodified areas, SpotEdit achieves efficient and precise image editing.
  arXiv  Detail & Related papers  (2025-12-26T14:59:41Z)
• FlowDC: Flow-Based Decoupling-Decay for Complex Image Editing [52.54102743380658]
  We propose FlowDC, which decouples the complex editing into multiple sub-editing effects and superposes them in parallel during the editing process.<n>FlowDC shows superior results compared with existing methods.
  arXiv  Detail & Related papers  (2025-12-12T09:08:39Z)
• Group Relative Attention Guidance for Image Editing [38.299491082179905]
  Group Relative Attention Guidance (GRAG) is a simple yet effective method that modulates the focus of the model on the input image relative to the editing instruction.<n>Our code will be released at https://www.littlemisfit.com/little-misfit/GRAG-Image-Editing.
  arXiv  Detail & Related papers  (2025-10-28T17:22:44Z)
• Visual Autoregressive Modeling for Instruction-Guided Image Editing [97.04821896251681]
  We present a visual autoregressive framework that reframes image editing as a next-scale prediction problem.<n>VarEdit generates multi-scale target features to achieve precise edits.<n>It completes a $512times512$ editing in 1.2 seconds, making it 2.2$times$ faster than the similarly sized UltraEdit.
  arXiv  Detail & Related papers  (2025-08-21T17:59:32Z)
• iEdit: Localised Text-guided Image Editing with Weak Supervision [53.082196061014734]
  We propose a novel learning method for text-guided image editing. It generates images conditioned on a source image and a textual edit prompt. It shows favourable results against its counterparts in terms of image fidelity, CLIP alignment score and qualitatively for editing both generated and real images.
  arXiv  Detail & Related papers  (2023-05-10T07:39:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.