CVPR 2026PastComputer vision
The 2nd Workshop on Test-time Scaling for Computer Vision
2nd ViSCALE @ CVPR 2026
- Submission deadline
- Mar 13, 2026, 11:59 UTCOpenReview-synced 2026-03-13 11:59 UTC (as of 2026-06-23) — extensions on OpenReview are applied automatically; verify on the website.
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (18)
Fetched from OpenReview (v2) on 2026-06-10.
[EXTENDED ABSTRACT] Vero: An Open RL Recipe for General Visual Reasoning
ATHENA: Adaptive Test-Time Steering for Improving Count Fidelity in Diffusion Models
Attention Budget Scheduling: Token-Level Test-Time Scaling for Vision Transformers
EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents
EXTENDED ABSTRACT -- World2Mind: Cognition Toolkit for Allocentric Spatial Reasoning in Foundation Models
EXTENDED ABSTRACT: Learning to Think Fast and Slow for Visual Language Models
EXTENDED ABSTRACT: Scaling Test-Time Compute via Semantic Critique and Spectral Alignment for Visual Media Generation
IMA & TMA: Efficient Test-Time Adaptation for VLMs via Linear Transformation in Embedding Space
Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
MetaWorld: Skill Transfer and Composition in a Hierarchical World Model for Grounding High-Level Instructions
Mind over Space: Can Multimodal Large Language Models Mentally Navigate?
Predictive Spectral Calibration for Source-Free Test-Time Regression
ProFuse: Efficient Open-Vocabulary 3D Gaussian Splatting with Early-Saturating Semantic Uplifting
Rethinking Dense Optical Flow without Test-Time Scaling
SA-TTS: Stress-Aware Test-Time Scaling for Vision Models
ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning
TreeReasoner: Reinforcing Tool-Augmented Tree-of-Videos Reasoning
Understanding the Limits of Vision Test-Time Scaling: Path Redundancy, Instance Difficulty, and Adaptive Compute