Publications

(2024). CiteME: Can Language Models Accurately Cite Scientific Claims?. NeurIPS 2024.

PDF Code Project

(2024). Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Models. CoLLAs 2024.

PDF

(2024). Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization. Third Conference on Lifelong Learning Agents (CoLLAs) 2024.

PDF Code Dataset Project Video

(2024). Modulated Neural ODEs. Neural Information Processing Systems (NeurIPS) 2023.

PDF Code

(2024). Investigating Continual Pretraining in Large Language Models: Insights and Implications.

PDF

(2024). Identifying latent state transition in non-linear dynamical systems.

PDF

(2024). Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?. Empirical Methods in Natural Language Processing (EMNLP) 2024.

PDF

(2024). In Search of Forgotten Domain Generalization.

PDF

(2024). Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models.

PDF Code Dataset

(2024). SuS-X---Training-Free Name-Only Transfer of Vision-Language Models.

PDF Code Video

(2024). No Zero-Shot Without Exponential Data---Pretraining Concept Frequency Determines Multimodal Model Performance.

PDF Code Dataset

(2024). Efficient Lifelong Model Evaluation in an Era of Rapid Progress.

PDF Code Dataset

(2024). A Practitioner's Guide to Continual Multimodal Pretraining.

PDF Code Dataset

(2024). A chromatic feature detector in the retina signals visual context changes. A chromatic feature detector in the retina signals visual context changes.

PDF DOI

(2024). Democratizing and Personalizing Evaluation with ∞-Benchmarks: Sample-Level Heterogeneous Testing Over Arbitrary Capabilities.

PDF

(2024). The Entropy Enigma: Success and Failure of Entropy Minimization. ICML 2024.

PDF Code

(2024). Deep feature matching vs spatio-temporal energy filtering for robust moving object segmentation. VSS 2024.

(2024). Scale Learning in Scale-Equivariant Convolutional Networks.

PDF

(2023). Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?.

PDF Code Project Slides

(2023). Provable Compositional Generalization for Object-Centric Learning.

PDF Code Project Slides

(2023). Compositional Generalization from First Principles.

PDF Code

(2023). RDumb: A simple approach that questions our progress in continual test-time adaptation. NeurIPS 2023.

PDF Code

(2023). Unsupervised object learning via common fate. CLeaR 2023.

PDF Code

(2022). The bittersweet lesson: data-rich models narrow the behavioural gap to human vision.

PDF

(2022). DeepGaze vs SceneWalk: what can DNNs and biological scan path models teach each other?.

PDF

(2022). Disentanglement and generalization under correlation shifts.

PDF

(2022). Common fate based object learning in machines and humans. VSS 2022.

PDF

(2022). Deepgaze iii: Modeling free-viewing human scanpaths with deep learning.

PDF

(2022). Digital twin reveals combinatorial code of non-linear computations in the mouse primary visual cortex.

PDF

(2022). Robust deep learning object recognition models rely on low frequency information in natural images.

PDF

(2022). Efficient coding of natural scenes improves neural system identification.

PDF

(2022). Semantic object-scene inconsisten.

PDF

(2022). ImageNet-D: A new challenging robustness dataset inspired by domain adaptation.

PDF

(2022). Diverse task-driven modeling of macaque V4 reveals functional specialization towards semantic tasks.

PDF

(2021). Partial success in closing the gap between human and machine vision.

PDF

(2021). How Well do Feature Visualizations Support Causal Understanding of CNN Activations?.

PDF

(2021). Contextualised meaning maps do not predict how semantic object-context inconsistencies change human gaze behaviour.

PDF

(2021). 2.1 Decision-Based Adversarial Attacks.

PDF

(2021). If your data distribution shifts, use self-learning.

PDF

(2021). Object-context inconsistencies affect gaze behavior differently than predicted by contextualized meaning maps.

PDF

(2021). New enhancements to the DeepGaze models for a better understanding of human scanpaths.

PDF

(2021). There is no evidence that meaning maps capture semantic information relevant to gaze guidance: Reply to Henderson, Hayes, Peacock, and Rehrig (2021).

PDF

(2021). Visual representation learning does not generalize strongly within the same domain.

PDF

(2021). Contrastive learning inverts the data generating process.

PDF

(2021). Learning divisive normalization in primary visual cortex.

PDF

(2021). Semantic object-scene inconsistencies affect eye movements, but not in the way predicted by contextualized meaning maps.

PDF

(2021). Adapting imagenet-scale models to complex distribution shifts with self-learning.

PDF

(2021). Five points to check when comparing visual perception in humans and machines.

PDF

(2021). State-of-the-art in human scanpath prediction.

PDF

(2021). Pretraining boosts out-of-domain robustness for pose estimation.

PDF

(2021). Out-of-distribution generalization of internal models is correlated with reward.

PDF

(2021). Meaning maps and saliency models based on deep convolutional neural networks are insensitive to image meaning when predicting human fixations.

PDF

(2021). Künstliche Intelligenz–Die dritte Welle.

PDF

(2021). Five points to check when com.

PDF

(2021). DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling.

PDF

(2021). Benchmarking unsupervised object representations for video sequences.

PDF

(2021). A diverse task-driven characterization of early and mid-level representations of the primate ventral stream.

PDF

(2020). Shortcut learning in deep neural networks.

PDF

(2020). Closing the generalization gap in one-shot object detection.

PDF

(2020). Exemplary natural images explain CNN activations better than state-of-the-art feature visualization.

PDF

(2020). Unintended cue learning: Lessons for deep learning from experimental psychology.

PDF

(2020). Analyzing task-specific patterns in human scanpaths.

PDF

(2020). Exemplary natural images explain CNN activations better than feature visualizations.

PDF

(2020). A simple way to make neural networks robust against diverse image corruptions.

PDF

(2020). Measuring the importance of temporal features in video saliency.

PDF Code

(2020). Towards nonlinear disentanglement in natural data with temporal sparse coding.

PDF

(2020). Imagenet performance correlates with pose estimation robustness and generalization on out-of-domain data.

PDF

(2020). Unmasking the inductive biases of unsupervised object representations for video sequences.

PDF

(2020). Task-driven hierarchical deep neural network models of the proprioceptive pathway.

PDF

(2020). Towards causal generative scene models via competition of experts.

PDF

(2020). The temporal structure of the inner retina at a single glance.

PDF

(2020). System identification with biophysical constraints: A circuit model of the inner retina.

PDF

(2020). Rotation-invariant clustering of neuronal responses in primary visual cortex.

PDF

(2020). Natural images are more informative for interpreting cnn activations than state-of-the-art synthetic feature visualizations.

PDF

(2020). Improving robustness against common corruptions by covariate shift adaptation.

PDF

(2020). Generalized Invariant Risk Minimization: relating adaptation and invariant representation learning.

PDF

(2020). Adversarial vision challenge.

PDF

(2019). Correction to: Detecting distortions of peripherally presented letter stimuli under crowded conditions.

PDF

(2019). " Detecting distortions of peripherally presented letter stimuli under crowded conditions": Correction..

PDF

(2019). Engineering a less artificial intelligence.

PDF

(2019). How well do deep neural networks trained on object recognition characterize the mouse visual system?.

PDF

(2019). Inducing a human-like shape bias leads to emergent human-level distortion robustness in CNNs.

PDF

(2019). Hole-in-the-wall: Perception of 3D shape and affordances from static images in humans and machines.

PDF

(2019). Comparing Search Strategies of Humans and Machines in Clutter.

PDF

(2019). Behavioural evidence for the existence of a spatiotopic free-viewing saliency map.

PDF

(2019). Benchmarking robustness in object detection: Autonomous driving when winter is coming.

PDF

(2019). Using DeepLabCut for 3D markerless pose estimation across species and behaviors.

PDF

(2019). Image content is more important than Bouma’s Law for scene metamers.

PDF

(2019). Deep convolutional models improve predictions of macaque V1 responses to natural images.

PDF

(2019). Probing Neural Decision-Making in Behavioral Models of Scanpath Prediction.

PDF

(2019). Comparing Humans and Deep Neural Networks on Visual Shape Judgments in Cluttered Images.

PDF

(2019). Learning from brains how to regularize machines.

PDF

(2019). Accurate, reliable and fast robustness evaluation.

PDF

(2018). ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness.

PDF

(2018). Faster processing of moving compared with flashed bars in awake macaque V1 provides a neural correlate of the flash lag illusion.

PDF

(2018). Excessive invariance causes adversarial vulnerability.

PDF

(2018). A rotation-equivariant convolutional neural network model of primary visual cortex.

PDF

(2018). Extending deepgaze ii: Scanpath prediction from deep features.

PDF

(2018). DeepLabCut: markerless pose estimation of user-defined body parts with deep learning.

PDF

(2018). Comparing the ability of humans and DNNs to recognise closed contours in cluttered images.

PDF

(2018). Adversarial vision challenge.

PDF

(2018). Markerless tracking of user-defined anatomical features with deep learning.

PDF

(2018). Attentional fluctuations induce shared variability in macaque primary visual cortex.

PDF

(2018). One-shot segmentation in clutter.

PDF

(2018). Scaling of information in large sensory populations.

PDF

(2018). Towards the first adversarially robust neural network model on MNIST.

PDF

(2018). Community-based benchmarking improves spike rate inference from two-photon calcium imaging data.

PDF

(2018). Towards goal-driven deep neural network models to elucidate human arm proprioception.

PDF

(2018). Trace your sources in large-scale data: one ring to find them all.

PDF

(2018). 伯克利 AI 研究院利用反向课程学习, 改善强化学习智能体.

PDF

(2018). Saliency benchmarking made easy: Separating models, maps and metrics.

PDF

(2018). Salad: A toolbox for semi-supervised adaptive learning across domains.

PDF

(2018). Multi-task generalization and adaptation between noisy digit datasets: An empirical study.

PDF

(2018). Introduction to NIPS 2017 Competition Track.

PDF

(2018). Generalisation in humans and deep neural networks.

PDF

(2018). Diverse feature visualizations reveal invariances in early layers of deep neural networks.

PDF

(2018). Consistent Saliency Benchmarking: How One Model Can Win on All Metrics.

PDF

(2017). Guiding human gaze with convolutional neural networks.

PDF

(2017). Neural system identification for large populations separating what and where.

PDF

(2017). Signatures of criticality arise from random subsampling in simple population models.

PDF

(2017). Texture and art with deep neural networks.

PDF

(2017). A parametric texture model based on deep convolutional features closely matches texture appearance for humans.

PDF

(2017). Towards matching peripheral appearance for arbitrary natural images using deep features.

PDF

(2017). Of human observers and deep neural networks: A detailed psychophysical comparison.

PDF

(2017). Mixed latent variable model of attention in V1.

PDF

(2017). Community-based benchmarking improves spike inference from two-photon calcium imaging data.

PDF

(2017). Foolbox: A python toolbox to benchmark the robustness of machine learning models.

PDF

(2017). Comparing deep neural networks against humans: object recognition when the signal gets weaker.

PDF

(2017). Detecting distortions of peripherally presented letter stimuli under crowded conditions.

PDF

(2017). Inhibition decorrelates visual feature representations in the inner retina.

PDF

(2017). Synthesising dynamic textures using convolutional neural networks.

PDF

(2017). Standardizing and benchmarking data analysis for calcium imaging.

PDF

(2017). Boosting olfactory cocktail-party performance by semi-supervised learning in mice.

PDF

(2017). Methods and measurements to compare men against machines.

PDF

(2017). Understanding low-and high-level contributions to fixation prediction.

PDF

(2017). Predicting Fixations From Deep and Low-Level Features.

PDF

(2017). Die Retina im Rausch der Kanäle.

PDF

(2017). Controlling perceptual factors in neural style transfer.

PDF

(2016). Towards matching the peripheral visual appearance of arbitrary scenes using deep convolutional neural networks.

PDF

(2016). DeepGaze II: Reading fixations from deep features trained on object recognition.

PDF

(2016). Large scale blind source separation.

PDF

(2016). Reading out olfactory receptors: feedforward circuits detect odors in mixtures without demixing.

PDF

(2016). Texture synthesis using random shallow neural networks.

PDF

(2016). Statistical inference with the Elliptical Gamma Distribution.

PDF

(2016). Inference and mixture modeling with the Elliptical Gamma Distribution.

PDF

(2016). Seeking summary statistics that match peripheral visual appearance using naturalistic textures generated by Deep Neural Networks.

PDF

(2016). Preserving color in neural artistic style transfer.

PDF

(2016). Texture synthesis using shallow convolutional networks with random filters.

PDF

(2016). Benchmarking spike rate inference in population calcium imaging.

PDF

(2016). On the structure of neuronal population activity under fluctuations in attentional state.

PDF

(2016). Supervised learning sets benchmark for robust spike rate inference from calcium imaging signals.

PDF

(2016). Electrophysiological, transcriptomic and morphologic profiling of single neurons using Patch-seq.

PDF

(2016). The functional diversity of retinal ganglion cells in the mouse.

PDF

(2016). Using Deep Features to Predict Where People Look.

PDF

(2016). Texture Modelling Using Convolutional Neural Networks.

PDF

(2016). Image style transfer using convolutional neural networks.

PDF

(2016). A goal-driven deep learning approach for V1 system identification.

PDF

(2015). Information-theoretic model comparison unifies saliency metrics.

PDF

(2015). A note on the evaluation of generative models.

PDF

(2015). Modeling natural image statistics.

PDF

(2015). Scaling of information in large sensory neuronal populations.

PDF

(2015). Metamers of the ventral stream revisited.

PDF

(2015). A neural algorithm of artistic style.

PDF

(2015). Unexpected functional diversity among mouse retinal ganglion cell types.

PDF

(2015). Synaptic unreliability facilitates information transmission in balanced cortical populations.

PDF

(2015). A generative model of natural texture surrogates.

PDF

(2015). On the structure of population activity under fluctuations in attentional state.

PDF

(2015). Following the visual signal across the entire mouse retina: From cone calcium to ganglion cell spikes.

PDF

(2015). Correlations and signatures of criticality in neural population models.

PDF

(2015). Data modeling with the elliptical gamma distribution.

PDF

(2015). Texture synthesis using convolutional neural networks.

PDF

(2015). Generative image modeling using spatial lstms.

PDF

(2015). A neural algorithm of artistic style. arXiv.

PDF

(2014). Deep gaze i: Boosting saliency prediction with feature maps trained on imagenet.

PDF

(2014). Natter: A Python Natural Image Statistics Toolbox.

PDF

(2014). What the mouse eye tells the mouse brain: Fingerprinting the retinal ganglion cell types of the mouse retina.

PDF

(2014). Information theoretic analysis of neural populations.

PDF

(2014). Autonomous Learning.

PDF

(2014). Population code in mouse V1 facilitates readout of natural scenes through increased sparseness.

PDF

(2014). State dependence of noise correlations in macaque primary visual cortex.

PDF

(2014). Slowness and sparseness have diverging effects on complex cell learning.

PDF

(2014). Efficient Population Coding.

PDF

(2014). How much signal is there in the noise?.

PDF

(2013). Beyond GLMs: a generative mixture modeling approach to neural system identification.

PDF

(2013). Neural Adaptation as Bayesian Inference.

PDF

(2013). Information Coding in the Variance of Neural Activity.

PDF

(2013). Recording the entire visual representation along the vertical pathway in the retina.

PDF

(2013). The bipolar cell terminal as a selective spatio-temporal filter.

PDF

(2013). Encoding of natural scene statistics in the primary visual cortex of the mouse.

PDF

(2013). A generative model of natural images as patchworks of textures.

PDF

(2013). Inferring decoding strategies from choice probabilities in the presence of correlated variability.

PDF

(2013). How sensitive is the human visual system to the local statistics of natural images?.

PDF

(2013). Spikes in mammalian bipolar cells support temporal layering of the inner retina.

PDF

(2012). A fast and simple population code for orientation in primate V1.

PDF

(2012). The correlation structure induced by fluctuations in attention.

PDF

(2012). A new perceptual bias reveals suboptimal population decoding of sensory responses.

PDF

(2012). Surprising Speed Jitter Invariance Of Pattern Matching In Random Dot Stereopsis.

PDF

(2012). Inferring decoding strategy from choice probabilities in the presence of noise correlations.

PDF

(2011). LNP Analysis of Primary Whisker Afferents.

PDF

(2011). A multiscale model of natural images.

PDF

(2011). Gravitational lensing accuracy testing 2010 (GREAT10) challenge handbook.

PDF

(2011). The effect of noise correlations in populations of diversely tuned neurons.

PDF

(2011). Gaussian process methods for estimating cortical maps.

PDF

(2011). Reassessing optimal neural population codes with neurometric functions.

PDF

(2011). Perceptual Sensitivity to Statistical Regularities in Natural Images.

PDF

(2011). Reconstructing stimuli from the spike times of leaky integrate and fire neurons.

PDF

(2011). Optimal Population Coding, Revisited.

PDF

(2010). In All Likelihood, Deep Belief Is Not Enough.

PDF

(2010). Estimating cortical maps with Gaussian process models.

PDF

(2010). What is the Goal of Complex Cell Coding in V1?.

PDF

(2010). New Estimate for the Redundancy of Natural Images.

PDF

(2010). Likelihood Estimation in Deep Belief Networks.

PDF

(2010). Results of the GREAT08 Challenge: an image analysis competition for cosmological lensing.

PDF

(2010). Decorrelated Firing in Cortical Microcircuits.

PDF

(2010). Implications of correlated neuronal noise in decision making circuits for physiology and behavior.

PDF

(2010). Decorrelated neuronal firing in cortical microcircuits.

PDF

(2010). Bayesian inference for generalized linear models for spiking neurons.

PDF

(2009). Method and device for image compression.

PDF

(2009). Unsupervised learning of disparity maps from stereo images.

PDF

(2009). Neuronal decision-making with realistic spiking models.

PDF

(2009). Inferring characteristics of stimulus encoding mechanisms using rippled noise stimuli.

PDF

(2009). Hierarchical models of natural images.

PDF

(2009). Characterization of the p-generalized normal distribution.

PDF

(2009). Natural image coding in V1: how much use is orientation selectivity?.

PDF

(2009). The effect of pairwise neural correlations on global population statistics.

PDF

(2009). Generating spike trains with specified correlation coefficients.

PDF

(2009). Sensory input statistics and network mechanisms in primate primary visual cortex.

PDF

(2009). Neurometric function analysis of short-term population codes.

PDF

(2008). Image library for unsupervised learning of depth from stereo.

PDF

(2008). Modeling populations of spiking neurons with the Dichotomized Gaussian distribution.

PDF

(2008). Flexible Models for Population Spike Trains.

PDF

(2008). Towards the neural basis of the flash-lag effect.

PDF

(2008). Pairwise Correlations and Multineuronal Firing Patterns in the Primary Visual Cortex of the Awake, Behaving Macaque.

PDF

(2007). Studying the effects of noise correlations on population coding using a sampling method.

PDF

(2007). The independent components of natural images are perceptually dependent.

PDF

(2007). Unsupervised learning of a steerable basis for invariant image representations.

PDF

(2007). Identifying temporal population codes in the retina using canonical correlation analysis.

PDF

(2007). Estimating Population Receptive Fields in Space and Time.

PDF

(2007). Bayesian Receptive Fields and Neural Couplings with Sparsity Prior and Error Bars.

PDF

(2007). Bayesian inference for spiking neuron models with a sparsity prior.

PDF

(2006). Bayesian Neural System identification: error bars, receptive fields and neural couplings.

PDF

(2004). Dynamics of population rate codes in ensembles of neocortical neurons.

PDF

(2004). Neural Networks Referees in 2003.

PDF

(2003). Geheimsprache der Neuronen.

PDF

(2003). El lenguaje de las neuronas.

PDF

(2003). El lenguaje de las neuronas.

PDF

(2002). Optimal short-term population coding: When Fisher information fails.

PDF

(2002). Population coding with unreliable spikes.

PDF

(2002). Geheimsprache der Neuronen.

PDF

(2002). Binary tuning is optimal for neural rate coding with high temporal resolution.

PDF

(2001). Spike-frequency adaptation: phenomenological model and experimental tests.

PDF

(2000). Spike-Frequency Adaptation: Phenomenological.

PDF

(1999). Brief pauses as signals for degressing synapses.

PDF

(1998). Coherence detection with dynamic synapses.

PDF