arXiv (All)
open access
Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling
Visual Autoregressive Models (VAR) generate images through next-scale prediction, producing all tokens within each scale in parallel. We show that this parallel decoding constitutes a mean-field-style approximation that discards spatial dependencies among same-scale tokens, causing locally incoheren
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling#673504
- MMGR: Multi-Modal Generative Reasoning Benchmark and Evaluation#999700
- Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction#1116684
- Temporal State Transport in Video Generation: Diagnosing and Correcting Spectral Imbalance#985854
- UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm#1064459
Record · ID 999490
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive