Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

Read original
HuggingFace Daily Papers·Yifan Shen·Aug 5, 2026, 8:00 PM

ChronoVision: Temporal Reasoning via Latent State Reconstruction

Papers86

ChronoVision is a multimodal framework for temporal visual reasoning that supplements language-based reasoning with latent visual-state reconstruction. During supervised fine-tuning, a Reconstructive Visual Head predicts the latent representation of the final transformed state, while an ROI Attention Locating module identifies relevant visual evidence through semantic span queries. Post-training uses reinforcement learning with rewards for answer correctness, latent process alignment, and unsupervised visual focus. The authors introduce Vbvr-VQA, an image-ordering benchmark, and report 74.8% in-domain, 71.6% out-of-domain, and 55.0% on IntPhys2 accuracy.

Why it's worth reading

The paper is timely because it tests whether explicit latent-state reconstruction can reduce multimodal models’ weakness on multi-step visual transformations, including out-of-domain and cross-benchmark evaluation.

Tags

多模态推理时间推理视觉状态重建强化学习VQA跨域泛化ChronoVisionIntPhys2

Score breakdown

  • Novelty88
  • Impact84
  • Practicality78
  • Credibility80
  • Timeliness86