M-ORE decouples text and visual update statistics in MLLMs and applies recursive low-rank edits in an orthogonal subspace to reduce cross-modal conflict and long-horizon interference.
Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
Multimodal Large Language Models (MLLMs) have shown promising capabilities in generating Scalable Vector Graphics (SVG) via direct code synthesis. However, existing paradigms typically adopt an open-loop "blind drawing" approach, where models generate symbolic code sequences without perceiving intermediate visual outcomes. This methodology severely underutilizes the powerful visual priors embedded in MLLMs vision encoders, treating SVG generation as a disjointed textual sequence modeling task rather than an integrated visuo-spatial one. Consequently, models struggle to reason about partial canvas states and implicit occlusion relationships, which are visually explicit but textually ambiguous. To bridge this gap, we propose Render-in-the-Loop, a novel generation paradigm that reformulates SVG synthesis as a step-wise, visual-context-aware process. By rendering intermediate code states into a cumulative canvas, the model explicitly observes the evolving visual context at each step, leveraging on-the-fly feedback to guide subsequent generation. However, we demonstrate that applying this visual loop naively to off-the-shelf models is suboptimal due to their inability to leverage incremental visual-code mappings. To address this, we first utilize fine-grained path decomposition to construct dense multi-step visual trajectories, and then introduce a Visual Self-Feedback (VSF) training strategy to condition the next primitive generation on intermediate visual states. Furthermore, a Render-and-Verify (RaV) inference mechanism is proposed to effectively filter degenerate and redundant primitives. Our framework, instantiated on a multimodal foundation model, outperforms strong open-weight baselines on the standard MMSVGBench. This result highlights the remarkable data efficiency and generalization capability of our Render-in-the-Loop paradigm for both Text-to-SVG and Image-to-SVG tasks.
years
2026 7representative citing papers
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
SynGR is a synergistic generative recommendation method that masks dominant-modal tokens and uses contrastive learning to capture cross-modal synergies, outperforming prior methods on Amazon Arts, Games, and Instruments.
BoostAPR boosts automated program repair by training a sequence-level assessor and line-level credit allocator from execution outcomes, then applying them in PPO to reach 40.7% on SWE-bench Verified.
A reinforcement-learning agent that picks high-error trajectory segments during consistency distillation improves few-step text-to-image generation on FLUX and SDXL.
NaviEdit is a training-free inference-time controller that decouples edit progress from model scale traversal in diffusion-based image editing via self-consistency, reporting average gains across editors and backbones.
MedSynapse-V proposes a latent memory evolution framework with meta-query prior retrieval, causal counterfactual refinement via RL, and intrinsic memory transition to improve diagnostic accuracy over chain-of-thought baselines in medical VLMs.
citing papers explorer
-
Modality-Decoupled Online Recursive Editing
M-ORE decouples text and visual update statistics in MLLMs and applies recursive low-rank edits in an orthogonal subspace to reduce cross-modal conflict and long-horizon interference.
-
VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
-
SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation
SynGR is a synergistic generative recommendation method that masks dominant-modal tokens and uses contrastive learning to capture cross-modal synergies, outperforming prior methods on Amazon Arts, Games, and Instruments.
-
BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models
BoostAPR boosts automated program repair by training a sequence-level assessor and line-level credit allocator from execution outcomes, then applying them in PPO to reach 40.7% on SWE-bench Verified.
-
Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
A reinforcement-learning agent that picks high-error trajectory segments during consistency distillation improves few-step text-to-image generation on FLUX and SDXL.
-
Semantic Granularity Navigation in Image Editing
NaviEdit is a training-free inference-time controller that decouples edit progress from model scale traversal in diffusion-based image editing via self-consistency, reporting average gains across editors and backbones.
-
MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution
MedSynapse-V proposes a latent memory evolution framework with meta-query prior retrieval, causal counterfactual refinement via RL, and intrinsic memory transition to improve diagnostic accuracy over chain-of-thought baselines in medical VLMs.