🛰️ Daily AI Frontier
‹ back to 2026-08-04

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression

Research Multimodal & Generative

Ranking

Overall 67
Content 80
Popularity 36

Observed public metrics from 1 member.

Representative image for Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression

Merged summary

TL;DR - SPIRAL is a self-supervised framework that fixes "cross-path inconsistency" in Vision-Text Compression, where text rendered into images is encoded by a ViT as glyphs/layout rather than linguistic semantics. It matters because it lets long texts be compressed into far fewer visual tokens while nearly matching native-text performance.

  • Diagnoses cross-path inconsistency via rendering perturbation experiments, identifying it as the key VTC bottleneck since ViTs are pretrained on natural images.
  • Uses only the model's own text-path behavior as supervision — no external teachers or extra annotations — at two granularities: token-level on-policy distillation (OPD) and sequence-level preference optimization (DPO).
  • On VTCBench, lifts Qwen3-VL-8B from 35.10 to 54.02 overall, close to native text input (55.60) and beating models up to 30x larger.
  • OPD is sample-efficient and strongest on retrieval; DPO is stronger on reasoning/memory and scales better with data; gains also transfer to out-of-domain benchmarks.

Sources (1)

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression

arXiv cs.CV Tianyu Liang, Xiangxi Zheng, Yilin Wang, Dongxing Mao 2026-08-03 arXiv:2608.02109
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-08-24 14:27:38.095765 UTC

TL;DR - SPIRAL is a self-supervised framework that fixes "cross-path inconsistency" in Vision-Text Compression, where text rendered into images is encoded by a ViT as glyphs/layout rather than linguistic semantics. It matters because it lets long texts be compressed into far fewer visual tokens while nearly matching native-text performance.

  • Diagnoses cross-path inconsistency via rendering perturbation experiments, identifying it as the key VTC bottleneck since ViTs are pretrained on natural images.
  • Uses only the model's own text-path behavior as supervision — no external teachers or extra annotations — at two granularities: token-level on-policy distillation (OPD) and sequence-level preference optimization (DPO).
  • On VTCBench, lifts Qwen3-VL-8B from 35.10 to 54.02 overall, close to native text input (55.60) and beating models up to 30x larger.
  • OPD is sample-efficient and strongest on retrieval; DPO is stronger on reasoning/memory and scales better with data; gains also transfer to out-of-domain benchmarks.
item →