The remarkable progress of modern computer vision has been propelled by the relentless logic of scaling laws: bigger models, more data, more compute, predictably better performance. On benchmarks like ImageNet, deep networks now match or even surpass human accuracy. Yet beneath these headline results, the alignment with human vision is fragile: on deceptively simple probes from the cognitive sciences, even the largest models drop to near-chance, and on ImageNet itself, models that reach human accuracy do so by strikingly different visual strategies — a divergence that, troublingly, widens with scale.
In this plenary, I will argue that the path to more natural artificial vision lies not in pushing scaling laws further, but in a deeper engagement with the neural laws of biological vision: developmental principles that shape how brains learn to see, and architectural constraints that impose strong inductive biases on cortical processing. I will share recent work from my lab on two such laws. On the learning side, I will present preliminary evidence that pairing the right learning objectives with naturalistic video — sequences of object transformations like those the developing brain encounters — can pull deep networks toward markedly more human-like visual strategies. On the architectural side, I will show how recent advances in state space models can scale cortical recurrent feedback into a brain-inspired alternative to transformer self-attention, one that closes the gap on cognitive probes where transformers fail, and on ImageNet traces more favorable scaling laws than transformers.
Together, these results point toward a future in which scaling laws and neural laws are in agreement rather than in tension, and in which computer vision, in dialogue with the brain sciences, helps build AI systems that are not only more capable but more aligned with the kind of intelligence we ultimately seek to understand and emulate.
Art Exhibition
The Art Gallery presents 84 works in video format alongside 24 individual installations:
- Sun Chuanqi & Yuhan Wang, Dream Brush (2026)
- Mingyong Cheng The Silhouette Seeker (2026)
- Myungin Lee & Noah Bissell & Ethan Paley & Amanda Wang Sensorium Arc: AI Agent System for Oceanic Data Exploration and Interactive Eco-Art (2025)
- Nick Oh & Alex Park artefact(s): LeNet-1 (2026)
- Nicolas Romano Techno-juggling (2026)
- Shih-Chieh Su PASTEL (2026)
- Uttam Grandhi Cubic Visions (2026)
- Yalin Wang Stellar Pathfinding (2025)
- Veronika Szücs & Maximilian Noichl, The Thousand Names of Macskusz (2026)
- Yamin Xu No.5 (2026)
- Rundong Luo, Shadow Art From Everyday Objects (2026)
- Apolinário Passos, GlitchBox (2025)
- Zhanpei Fang, Stanford Bunny (2026)
- Matt DesLauriers Synthetic Gestures (2026)
- Aastha Valecha, Afterglow (2026)
- Anthony Luo, Introducing 16047 38 2898 (2026)
- Daniel Ambrosi, Schynige Platte ‘Stratamorphic Dream’ (2026)
- Garrett Lynch IRL & Frédérique Santune, Image/Object (2026)
- Marco Zaccaria Di Fraia, Virtual Water (2026)
- William Latham & Stephen Todd & Dylan Banarse, Half Way to Butterflies. Mutator and Gemini Research and Art Software (2025)
- Tom White, Synesthetic Visions (2026)
- Ioannis Siglidis, IIRd, or why data can't tell its own narrative (2026)
- Anna Borou Yu & Jiajian Min & Qingyun Liu, Interdependent Visibility (2025)
- Avital Meshi & Dorte Bjerre Jensen Rest! (2026)
Art Gallery Tour with Curator and Artists
The curator of the CVPR Art Gallery, Luba Elliott, and participating artists will walk through the installations and select video works.
FOVEA: Flexible Ontology Visual Event Analyzer
Aaron Steven WhiteRapid 3D Object Annotation through In-Situ Geometric Grounding
Narges Honarvar NazariEMMA: Extracting Multiple Physical Parameters from Multimodal Data
Farhat Shaikh, Ayan Banerjee, Sandeep GuptaSparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation
Jiongze Yu, Xiangbo Gao, Pooja Verlani, Akshay Gadde, Yilin Wang, Balu Adsumilli, Zhengzhong TuEgoMedAgent: Towards Evidence-based Egocentric Assistant for Clinical Perception and Action
Chen Fang, Xu Cao, Houze Yang, Yifan ShenAuthenticating Matryoshka Nesting Dolls via Zero-Shot 3D Completion
Yulia Kumar, Srotriyo Sengupta