Yana Hasson

	@article{henn2026aimip,
		 title={AIMIP Phase 1: Systematic Evaluations of AI Weather and Climate Models},
		 author={Henn, Brian and Bretherton, Christopher S. and Koldunov, Nikolay and Lessig, Christian and Molina, Maria J. and Arcomano, Troy and Watt-Meyer, Oliver and Couairon, Guillaume and Singh, Renu and Brunstein, Robert and Hasson, Yana and Jost, Antonia and Brenowitz, Noah and Manshausen, Peter and Cresswell-Clay, Nathaniel and Durran, Dale and Hall, Kyle Joseph Chen and Yuval, Janni and Kochkov, Dmitrii and Hoyer, Stephan and Lopez-Gomez, Ignacio},
		 journal={arXiv preprint arXiv:2605.06944},
		 year={2026}
		}
								

The AI weather and climate model intercomparison project (AIMIP) establishes a standardized framework for evaluating AI-based weather and climate models. Phase 1 assesses participating models trained on ERA5 reanalysis data, tasked with simulating the atmosphere from 1979 to 2024. Models are evaluated across biases, trends, El Niño responses, temporal variability, and out-of-sample generalization.

	@article{singh2026archesweather,
		 title={Evaluating Skill and Stability of ArchesWeather and ArchesWeatherGen under Multi-Decadal Climate Simulations},
		 author={Singh, Renu and Brunstein, Robert and Jost, Antonia and Rackow, Thomas and Monteleoni, Claire and Hasson, Yana and Lessig, Christian and Couairon, Guillaume},
		 journal={arXiv preprint arXiv:2605.29976},
		 year={2026}
		}
								

We evaluate ArchesWeather (deterministic) and ArchesWeatherGen (probabilistic flow-matching) when adapted for multi-decadal climate simulation following the AIMIP Phase 1 protocol. Despite their origins in short-term weather forecasting, both models produce stable long-term climate simulations, maintaining a stable annual cycle, capturing climate variable drift, and faithfully reproducing ERA5 climatology, large-scale circulations, and interannual variability.

	@article{alayrac2022flamingo,
		 title={Flamingo: a Visual Language Model for Few-Shot Learning},
		 author = {Alayrac, Jean-Baptiste and Donahue, Jeff and Luc, Pauline and Miech, Antoine and Barr, Iain and Hasson, Yana and Lenc, Karel and Mensch, Arthur and Millican, Katie and Reynolds, Malcolm and Ring, Roman and Rutherford, Eliza and Cabi, Serkan and Han, Tengda and Gong, Zhitao and Samangooei, Sina and Monteiro, Marianne and Menick, Jacob and Borgeaud, Sebastian and Brock, Andrew and Nematzadeh, Aida and Sharifzadeh, Sahand and Binkowski, Mikolaj and Barreira, Ricardo and Vinyals, Oriol and Zisserman, Andrew and Simonyan, Karen},
		 journal={arXiv preprint arXiv:2204.14198},
		 year={2022}
		}
								

@article{{hasson20_homan,
			title     = {Towards unconstrained joint hand-object reconstruction from RGB videos},
			author    = {Hasson, Yana and Varol, G"{u}l and Laptev, Ivan and Schmid, Cordelia},
			journal  ={arXiv preprint arXiv:2108.07044},
			year      = {2021}
	}

Our work aims to obtain 3D reconstruction of hands and manipulated objects from monocular videos. Reconstructing hand-object manipulations holds a great potential for robotics and learning from human demonstrations. The supervised learning approach to this problem, however, requires 3D supervision and remains limited to constrained laboratory settings and simulators for which 3D ground truth is available. In this paper we first propose a learning-free fitting approach for hand-object reconstruction which can seamlessly handle two-hand object interactions. Our method relies on cues obtained with common methods for object detection, hand pose estimation and instance segmentation. We quantitatively evaluate our approach and show that it can be applied to datasets with varying levels of difficulty for which training data is unavailable.

To unlock video chat for hundreds of millions of people hindered by poor connectivity or unaffordable data costs, we propose to authentically reconstruct faces on the receiver's device using facial landmarks extracted at the sender's side and transmitted over the network. In this context, we discuss and evaluate the benefits and disadvantages of several deep adversarial approaches. In particular, we explore quality and bandwidth trade-offs for approaches based on static landmarks, dynamic landmarks or segmentation maps. We design a mobile-compatible architecture based on the first order animation model of Siarohin et al. In addition, we leverage SPADE blocks to refine results in important areas such as the eyes and lips. We compress the networks down to about 3MB, allowing models to run in real time on iPhone 8 (CPU). This approach enables video calling at a few kbits per second, an order of magnitude lower than currently available alternatives.

@INPROCEEDINGS{hasson20_handobjectconsist,
			title     = {Leveraging Photometric Consistency over Time for Sparsely Supervised Hand-Object Reconstruction},
			author    = {Hasson, Yana and Tekin, Bugra and Bogo, Federica and Laptev, Ivan and Pollefeys, Marc and Schmid, Cordelia},
			booktitle = {CVPR},
			year      = {2020}
	}

Modeling hand-object manipulations is essential for understanding how humans interact with their environment. While of practical importance, estimating the pose of hands and objects during interactions is challenging due to the large mutual occlusions that occur during manipulation. Recent efforts have been directed towards fully-supervised methods that require large amounts of labeled training samples. Collecting 3D ground-truth data for hand-object interactions, however, is costly, tedious, and error-prone. To overcome this challenge we present a method to leverage photometric consistency across time when annotations are only available for a sparse subset of frames in a video. Our model is trained end-to-end on color images to jointly reconstruct hands and objects in 3D by inferring their poses. Given our estimated reconstructions, we differentiably render the optical flow between pairs of adjacent images and use it within the network to warp one frame to another. We then apply a self-supervised photometric loss that relies on the visual consistency between nearby images. We achieve state-of-the-art results on 3D hand-object reconstruction benchmarks and demonstrate that our approach allows us to improve the pose estimation accuracy by leveraging information from neighboring frames in low-data regimes.

@INPROCEEDINGS{hasson19_obman,
	title     = {Learning joint reconstruction of hands and manipulated objects},
	author    = {Hasson, Yana and Varol, G{\"u}l and Tzionas, Dimitrios and Kalevatykh, Igor and Black, Michael J. and Laptev, Ivan and Schmid, Cordelia},
	booktitle = {CVPR},
	year      = {2019}
}