Carl Vondrick

Scott Geng, Revant Teotia, Purva Tendulkar et al. · uw

We introduce a video framework for modeling the association between verbal and non-verbal communication during dyadic conversation. Given the input speech of a speaker, our approach retrieves a video of a listener, who has facial expressions that would be socially appropriate given the context. Our approach further allows the listener to be conditioned on their own goals, personalities, or backgrounds. Our approach models conversations through a composition of large language models and vision-language models, creating internal representations that are interpretable and controllable. To study multimodal communication, we propose a new video dataset of unscripted conversations covering diverse topics and demographics. Experiments and visualizations show our approach is able to output listeners that are significantly more socially appropriate than baselines. However, many challenges remain, and we release our dataset publicly to spur further progress. See our website for video results, data, and code: https://realtalk.cs.columbia.edu.

Ruoshi Liu, Chengzhi Mao, Purva Tendulkar et al.

Many machine learning methods operate by inverting a neural network at inference time, which has become a popular technique for solving inverse problems in computer vision, robotics, and graphics. However, these methods often involve gradient descent through a highly non-convex loss landscape, causing the optimization process to be unstable and slow. We introduce a method that learns a loss landscape where gradient descent is efficient, bringing massive improvement and acceleration to the inversion process. We demonstrate this advantage on a number of methods for both generative and discriminative tasks, including GAN inversion, adversarial defense, and 3D human pose reconstruction.

Sruthi Sudhakar, Ruoshi Liu, Basile Van Hoorick et al.

Humans naturally build mental models of object interactions and dynamics, allowing them to imagine how their surroundings will change if they take a certain action. While generative models today have shown impressive results on generating/editing images unconditionally or conditioned on text, current methods do not provide the ability to perform object manipulation conditioned on actions, an important tool for world modeling and action planning. Therefore, we propose to learn an action-conditional generative models by learning from unlabeled videos of human hands interacting with objects. The vast quantity of such data on the internet allows for efficient scaling which can enable high-performing action-conditional models. Given an image, and the shape/location of a desired hand interaction, CosHand, synthesizes an image of a future after the interaction has occurred. Experiments show that the resulting model can predict the effects of hand-object interactions well, with strong generalization particularly to translation, stretching, and squeezing interactions of unseen objects in unseen environments. Further, CosHand can be sampled many times to predict multiple possible effects, modeling the uncertainty of forces in the interaction/environment. Finally, method generalizes to different embodiments, including non-human hands, i.e. robot hands, suggesting that generative video models can be powerful models for robotics.

Basile Van Hoorick, Carl Vondrick

The elementary operation of cropping underpins nearly every computer vision system, ranging from data augmentation and translation invariance to computational photography and representation learning. This paper investigates the subtle traces introduced by this operation. For example, despite refinements to camera optics, lenses will leave behind certain clues, notably chromatic aberration and vignetting. Photographers also leave behind other clues relating to image aesthetics and scene composition. We study how to detect these traces, and investigate the impact that cropping has on the image distribution. While our aim is to dissect the fundamental impact of spatial crops, there are also a number of practical implications to our work, such as revealing faulty photojournalism and equipping neural network researchers with a better understanding of shortcut learning. Code is available at https://github.com/basilevh/dissecting-image-crops.

Chengzhi Mao, Ziyuan Zhong, Junfeng Yang et al.

Deep networks are well-known to be fragile to adversarial attacks. We conduct an empirical analysis of deep representations under the state-of-the-art attack method called PGD, and find that the attack causes the internal representation to shift closer to the "false" class. Motivated by this observation, we propose to regularize the representation space under attack with metric learning to produce more robust classifiers. By carefully sampling examples for metric learning, our learned representation not only increases robustness, but also detects previously unseen adversarial samples. Quantitative experiments show improvement of robustness accuracy by up to 4% and detection efficiency by up to 6% according to Area Under Curve score over prior work. The code of our work is available at https://github.com/columbia/Metric_Learning_Adversarial_Robustness.

Chengzhi Mao, Carl Vondrick, Hao Wang et al.

We find that large language models (LLMs) are more likely to modify human-written text than AI-generated text when tasked with rewriting. This tendency arises because LLMs often perceive AI-generated text as high-quality, leading to fewer modifications. We introduce a method to detect AI-generated content by prompting LLMs to rewrite text and calculating the editing distance of the output. We dubbed our geneRative AI Detection viA Rewriting method Raidar. Raidar significantly improves the F1 detection scores of existing AI content detection models -- both academic and commercial -- across various domains, including News, creative writing, student essays, code, Yelp reviews, and arXiv papers, with gains of up to 29 points. Operating solely on word symbols without high-dimensional features, our method is compatible with black box LLMs, and is inherently robust on new content. Our results illustrate the unique imprint of machine-generated text through the lens of the machines themselves.

Haozhe Chen, Carl Vondrick, Chengzhi Mao

How do large language models (LLMs) obtain their answers? The ability to explain and control an LLM's reasoning process is key for reliability, transparency, and future model developments. We propose SelfIE (Self-Interpretation of Embeddings), a framework that enables LLMs to interpret their own embeddings in natural language by leveraging their ability to respond to inquiries about a given passage. Capable of interpreting open-world concepts in the hidden embeddings, SelfIE reveals LLM internal reasoning in cases such as making ethical decisions, internalizing prompt injection, and recalling harmful knowledge. SelfIE's text descriptions on hidden embeddings also open up new avenues to control LLM reasoning. We propose Supervised Control, which allows editing open-ended concepts while only requiring gradient computation of individual layer. We extend RLHF to hidden embeddings and propose Reinforcement Control that erases harmful knowledge in LLM without supervision targets.

Mia Chiquier, Orr Avrech, Yossi Gandelsman et al.

Scientific expertise often requires recognizing subtle visual differences that remain challenging to articulate even for domain experts. We present a system that leverages generative models to automatically discover and visualize minimal discriminative features between categories while preserving instance identity. Our method generates counterfactual visualizations with subtle, targeted transformations between classes, performing well even in domains where data is sparse, examples are unpaired, and category boundaries resist verbal description. Experiments across six domains, including black hole simulations, butterfly taxonomy, and medical imaging, demonstrate accurate transitions with limited training data, highlighting both established discriminative features and novel subtle distinctions that measurably improved category differentiation. User studies confirm our generated counterfactuals significantly outperform traditional approaches in teaching humans to correctly differentiate between fine-grained classes, showing the potential of generative models to advance visual learning and scientific research.

Sachit Menon, Ahmet Iscen, Arsha Nagrani et al.

Video understanding has seen significant progress in recent years, with models' performance on perception from short clips continuing to rise. Yet, multiple recent benchmarks, such as LVBench, Neptune, and ActivityNet-RTL, show performance wanes for tasks requiring complex reasoning on videos as queries grow more complex and videos grow longer. In this work, we ask: can existing perception capabilities be leveraged to successfully perform more complex video reasoning? In particular, we develop a large language model agent given access to video modules as subagents or tools. Rather than following a fixed procedure to solve queries as in previous work such as Visual Programming, ViperGPT, and MoReVQA, the agent uses the results of each call to a module to determine subsequent steps. Inspired by work in the textual reasoning domain, we introduce a critic to distinguish between instances of successful and unsuccessful sequences from the agent. We show that the combination of our agent and critic achieve strong performance on the previously-mentioned datasets.

Arnold Caleb Asiimwe, Dídac Surís, Pranav Rajpurkar et al.

In medical reporting, the accuracy of radiological reports, whether generated by humans or machine learning algorithms, is critical. We tackle a new task in this paper: image-conditioned autocorrection of inaccuracies within these reports. Using the MIMIC-CXR dataset, we first intentionally introduce a diverse range of errors into reports. Subsequently, we propose a two-stage framework capable of pinpointing these errors and then making corrections, simulating an \textit{autocorrection} process. This method aims to address the shortcomings of existing automated medical reporting systems, like factual errors and incorrect conclusions, enhancing report reliability in vital healthcare applications. Importantly, our approach could serve as a guardrail, ensuring the accuracy and trustworthiness of automated report generation. Experiments on established datasets and state of the art report generation models validate this method's potential in correcting medical reporting errors.

Junbang Liang, Ruoshi Liu, Ege Ozguroglu et al.

A key challenge in manipulation is learning a policy that can robustly generalize to diverse visual environments. A promising mechanism for learning robust policies is to leverage video generative models, which are pretrained on large-scale datasets of internet videos. In this paper, we propose a visuomotor policy learning framework that fine-tunes a video diffusion model on human demonstrations of a given task. At test time, we generate an example of an execution of the task conditioned on images of a novel scene, and use this synthesized execution directly to control the robot. Our key insight is that using common tools allows us to effortlessly bridge the embodiment gap between the human hand and the robot manipulator. We evaluate our approach on four tasks of increasing complexity and demonstrate that harnessing internet-scale generative models allows the learned policy to achieve a significantly higher degree of generalization than existing behavior cloning approaches.

Rundi Wu, Ruoshi Liu, Carl Vondrick et al.

Synthesizing novel 3D models that resemble the input example has long been pursued by graphics artists and machine learning researchers. In this paper, we present Sin3DM, a diffusion model that learns the internal patch distribution from a single 3D textured shape and generates high-quality variations with fine geometry and texture details. Training a diffusion model directly in 3D would induce large memory and computational cost. Therefore, we first compress the input into a lower-dimensional latent space and then train a diffusion model on it. Specifically, we encode the input 3D textured shape into triplane feature maps that represent the signed distance and texture fields of the input. The denoising network of our diffusion model has a limited receptive field to avoid overfitting, and uses triplane-aware 2D convolution blocks to improve the result quality. Aside from randomly generating new samples, our model also facilitates applications such as retargeting, outpainting and local editing. Through extensive qualitative and quantitative evaluation, we show that our method outperforms prior methods in generation quality of 3D shapes.

Boyuan Chen, Robert Kwiatkowski, Carl Vondrick et al.

Internal computational models of physical bodies are fundamental to the ability of robots and animals alike to plan and control their actions. These "self-models" allow robots to consider outcomes of multiple possible future actions, without trying them out in physical reality. Recent progress in fully data-driven self-modeling has enabled machines to learn their own forward kinematics directly from task-agnostic interaction data. However, forward-kinema\-tics models can only predict limited aspects of the morphology, such as the position of end effectors or velocity of joints and masses. A key challenge is to model the entire morphology and kinematics, without prior knowledge of what aspects of the morphology will be relevant to future tasks. Here, we propose that instead of directly modeling forward-kinematics, a more useful form of self-modeling is one that could answer space occupancy queries, conditioned on the robot's state. Such query-driven self models are continuous in the spatial domain, memory efficient, fully differentiable and kinematic aware. In physical experiments, we demonstrate how a visual self-model is accurate to about one percent of the workspace, enabling the robot to perform various motion planning and control tasks. Visual self-modeling can also allow the robot to detect, localize and recover from real-world damage, leading to improved machine resiliency. Our project website is at: https://robot-morphology.cs.columbia.edu/

Boyuan Chen, Mia Chiquier, Hod Lipson et al.

Interacting with bins and containers is a fundamental task in robotics, making state estimation of the objects inside the bin critical. While robots often use cameras for state estimation, the visual modality is not always ideal due to occlusions and poor illumination. We introduce The Boombox, a container that uses sound to estimate the state of the contents inside a box. Based on the observation that the collision between objects and its containers will cause an acoustic vibration, we present a convolutional network for learning to reconstruct visual scenes. Although we use low-cost and low-power contact microphones to detect the vibrations, our results show that learning from multimodal data enables state estimation from affordable audio sensors. Due to the many ways that robots use containers, we believe the box will have a number of applications in robotics. Our project website is at: boombox.cs.columbia.edu

Chengzhi Mao, Mia Chiquier, Hao Wang et al.

We find that images contain intrinsic structure that enables the reversal of many adversarial attacks. Attack vectors cause not only image classifiers to fail, but also collaterally disrupt incidental structure in the image. We demonstrate that modifying the attacked image to restore the natural structure will reverse many types of attacks, providing a defense. Experiments demonstrate significantly improved robustness for several state-of-the-art models across the CIFAR-10, CIFAR-100, SVHN, and ImageNet datasets. Our results show that our defense is still effective even if the attacker is aware of the defense mechanism. Since our defense is deployed during inference instead of training, it is compatible with pre-trained networks as well as most other defenses. Our results suggest deep networks are vulnerable to adversarial examples partly because their representations do not enforce the natural structure of images.

Dídac Surís, Ruoshi Liu, Carl Vondrick

We introduce a framework for learning from unlabeled video what is predictable in the future. Instead of committing up front to features to predict, our approach learns from data which features are predictable. Based on the observation that hyperbolic geometry naturally and compactly encodes hierarchical structure, we propose a predictive model in hyperbolic space. When the model is most confident, it will predict at a concrete level of the hierarchy, but when the model is not confident, it learns to automatically select a higher level of abstraction. Experiments on two established datasets show the key role of hierarchical representations for action prediction. Although our representation is trained with unlabeled video, visualizations show that action hierarchies emerge in the representation.

Ruilin Xu, Rundi Wu, Yuko Ishiwaka et al.

We introduce a deep learning model for speech denoising, a long-standing challenge in audio analysis arising in numerous applications. Our approach is based on a key observation about human speech: there is often a short pause between each sentence or word. In a recorded speech signal, those pauses introduce a series of time periods during which only noise is present. We leverage these incidental silent intervals to learn a model for automatic speech denoising given only mono-channel audio. Detected silent intervals over time expose not just pure noise but its time-varying features, allowing the model to learn noise dynamics and suppress it from the speech signal. Experiments on multiple datasets confirm the pivotal role of silent interval detection for speech denoising, and our method outperforms several state-of-the-art denoising methods, including those that accept only audio input (like ours) and those that denoise based on audiovisual input (and hence require more information). We also show that our method enjoys excellent generalization properties, such as denoising spoken languages not seen during training.

Chengzhi Mao, Amogh Gupta, Vikram Nitin et al.

Although deep networks achieve strong accuracy on a range of computer vision benchmarks, they remain vulnerable to adversarial attacks, where imperceptible input perturbations fool the network. We present both theoretical and empirical analyses that connect the adversarial robustness of a model to the number of tasks that it is trained on. Experiments on two datasets show that attack difficulty increases as the number of target tasks increase. Moreover, our results suggest that when models are trained on multiple tasks at once, they become more robust to adversarial attacks on individual tasks. While adversarial defense remains an open challenge, our results suggest that deep networks are vulnerable partly because they are trained on too few tasks.

Dave Epstein, Carl Vondrick

We introduce a framework that predicts the goals behind observable human action in video. Motivated by evidence in developmental psychology, we leverage video of unintentional action to learn video representations of goals without direct supervision. Our approach models videos as contextual trajectories that represent both low-level motion and high-level action features. Experiments and visualizations show our trained model is able to predict the underlying goals in video of unintentional action. We also propose a method to "automatically correct" unintentional action by leveraging gradient signals of our model to adjust latent trajectories. Although the model is trained with minimal supervision, it is competitive with or outperforms baselines trained on large (supervised) datasets of successfully executed goals, showing that observing unintentional action is crucial to learning about goals in video. Project page: https://aha.cs.columbia.edu/

Dídac Surís, Dave Epstein, Heng Ji et al.

Language acquisition is the process of learning words from the surrounding scene. We introduce a meta-learning framework that learns how to learn word representations from unconstrained scenes. We leverage the natural compositional structure of language to create training episodes that cause a meta-learner to learn strong policies for language acquisition. Experiments on two datasets show that our approach is able to more rapidly acquire novel words as well as more robustly generalize to unseen compositions, significantly outperforming established baselines. A key advantage of our approach is that it is data efficient, allowing representations to be learned from scratch without language pre-training. Visualizations and analysis suggest visual information helps our approach learn a rich cross-modal representation from minimal examples. Project webpage is available at https://expert.cs.columbia.edu/

Dave Epstein, Boyuan Chen, Carl Vondrick

From just a short glance at a video, we can often tell whether a person's action is intentional or not. Can we train a model to recognize this? We introduce a dataset of in-the-wild videos of unintentional action, as well as a suite of tasks for recognizing, localizing, and anticipating its onset. We train a supervised neural network as a baseline and analyze its performance compared to human consistency on the tasks. We also investigate self-supervised representations that leverage natural signals in our dataset, and show the effectiveness of an approach that uses the intrinsic speed of video to perform competitively with highly-supervised pretraining. However, a significant gap between machine and human performance remains. The project website is available at https://oops.cs.columbia.edu

Boyuan Chen, Shuran Song, Hod Lipson et al.

We train embodied agents to play Visual Hide and Seek where a prey must navigate in a simulated environment in order to avoid capture from a predator. We place a variety of obstacles in the environment for the prey to hide behind, and we only give the agents partial observations of their environment using an egocentric perspective. Although we train the model to play this game from scratch, experiments and visualizations suggest that the agent learns to predict its own visibility in the environment. Furthermore, we quantitatively analyze how agent weaknesses, such as slower speed, effect the learned policy. Our results suggest that, although agent weaknesses make the learning problem more challenging, they also cause more useful features to be learned. Our project website is available at: http://www.cs.columbia.edu/ ~bchen/visualhideseek/.