Two Research Papers Accepted at ECCV 2026 CDEL Workshop
We are delighted to announce that two papers from our research lab have been accepted at the ECCV 2026 CDEL Workshop (Computer Vision for Data Curation, Efficiency & Learning).
VAIL is a research lab working across computer vision, interpretability, and AI safety.
focus areas
Our research focus
We do two things: build systems that perceive, and build methods that make their reasoning legible. The second is what makes the first usable, because a model whose decisions nobody can inspect is one nobody can debug, audit, or safely deploy.
computer-vision
Computer Vision
Recognition, segmentation, generation, and multimodal systems, with a focus on data and evaluation.
interpretabilityInterpretability
Attribution, concept probes, and mechanistic analysis of what models represent internally.
ai-safetyAI Safety
Failure modes, robustness under shift, and evaluation that catches problems before deployment.
ongoing
Ongoing competitions
Our lab participates in research competitions benchmarking scientific machine learning and physical reasoning in modern AI models.
NeurIPS 2026→
RealPDE Competition
Scientific ML for real-world physical systems using paired experimental (PIV) and simulated (CFD) fluid dynamics data over the NACA4418 airfoil.
NeurIPS 2026→
QuantiPhy Challenge
Benchmarking quantitative physical reasoning in vision-language models, evaluating numerical estimates of scale, velocity, and acceleration from video.
recent
Recent publications
FAILGROUND: Constructing and Safely Replaying LLM Agent Failure Knowledge Bases
Anonymous · Under review · 2026
MedCurate-Bench: Auditing the Diagnostic Validity of Curated Medical Image Datasets
Sarthak Pandey, Shreshth Rai, Seifedine Kadry · Second Workshop on Curated Data for Efficient Learning @ ECCV · 2026
PRAXIS: Principled Reasoning via Agentic Exploration at Inference-time Scale
Anonymous · Under review · 2026
When Agreement Is Not Enough: A Selection Bottleneck in Non-Verifiable Reasoning
Shreshth Rai, Sarthak Pandey, Seifedine Kadry · Second Workshop on Curated Data for Efficient Learning @ ECCV · 2026
lab news
News
9 members
People
get in touch
Contact
We publish open research, release datasets and tools, and collaborate with academia and industry.
Contact the lab