Valeo.ai Brings 5 ECCV 2026 Papers on Driving Video Prediction and LVLM Safety
abursuc · x · 2026-09-05
Valeo.ai will present 3 main-track papers and 2 workshop papers at ECCV 2026, plus 2 workshop keynotes and 1 tutorial.
- Re2Pix: a hierarchical video prediction framework for autonomous driving that first forecasts future scene semantics in a frozen vision foundation model's feature space, then conditions a latent diffusion model to render photorealistic frames.
- Workshop talks cover Human Motion-Informed World Models and uncertainty quantification (UNCV); the tutorial spans hallucination detection to adversarial defense for LVLM/LLM safety.
- Several team members won Outstanding Reviewer awards.
More from Research
- Metaⁿ and Recuris: filling the missing pieces in recursive self-improvement — TheTuringPost · 2026-09-05
- LLMs exploiting Lean bugs is a short-term problem, author argues — avt_im · 2026-09-05
- FinFIRST benchmark tests agents on real financial research: source discovery, evidence selection and math — alifcoder · 2026-09-05
- Sakana AI's Percept-Lens: a simple rule on frozen vision features detects AI images — SakanaAILabs · 2026-09-05
- VI3 anchors pretrained 3D foundation models to metric scale using only IMU readings — zhenjun_zhao · 2026-09-05
- ZipMVS compresses cost volumes for memory-efficient multi-view stereo reconstruction — zhenjun_zhao · 2026-09-05