papers

Publications (31)

cs.CL2024

Language models scale reliably with over-training and on downstream tasks

Samir Yitzhak Gadre, Georgios Smyrnis, Vaishaal Shankar +22

Scaling laws are useful guides for derisking expensive training runs, as they predict performance of large models using cheaper, small-scale experiments. However, there remain gaps…

cs.CV2024

Zero-Shot Open-Vocabulary Tracking with Large Pre-Trained Models

Wen-Hsuan Chu, Adam W. Harley, Pavel Tokmakov +3

Object tracking is central to robot perception and scene understanding. Tracking-by-detection has long been a dominant paradigm for object tracking of specific object categories. R…

cs.CV2024

Understanding Video Transformers via Universal Concept Discovery

Matthew Kowal, Achal Dave, Rares Ambrus +3

This paper studies the problem of concept-based interpretability of transformer representations for videos. Concretely, we seek to explain the decision-making process of video tran…

cs.LG2019

Do Image Classifiers Generalize Across Time?

Vaishaal Shankar, Achal Dave, Rebecca Roelofs +3

We study the robustness of image classifiers to temporal perturbations derived from videos. As part of this study, we construct two datasets, ImageNet-Vid-Robust and YTBB-Robust ,…

cs.CV2019

Learning to Track Any Object

Achal Dave, Pavel Tokmakov, Cordelia Schmid +1

Object tracking can be formulated as "finding the right object in a video". We observe that recent approaches for class-agnostic tracking tend to focus on the "finding" part, but l…

cs.CV2025

Understanding Complexity in VideoQA via Visual Program Generation

Cristobal Eyzaguirre, Igor Vasiljevic, Achal Dave +5

We propose a data-driven approach to analyzing query complexity in Video Question Answering (VideoQA). Previous efforts in benchmark design have relied on human expertise to design…

cs.CV2025

Long-Tailed 3D Detection via Multi-Modal Fusion

Yechi Ma, Neehar Peri, Achal Dave +3

Contemporary autonomous vehicle (AV) benchmarks have advanced techniques for training 3D detectors. While class labels naturally follow a long-tailed distribution in the real world…

cs.CV2022

Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details

Achal Dave, Piotr Dollár, Deva Ramanan +2

By design, average precision (AP) for object detection aims to treat all classes independently: AP is computed independently per category and averaged. On one hand, this is desirab…

cs.CV2024

pix2gestalt: Amodal Segmentation by Synthesizing Wholes

Ege Ozguroglu, Ruoshi Liu, Dídac Surís +4

We introduce pix2gestalt, a framework for zero-shot amodal segmentation, which learns to estimate the shape and appearance of whole objects that are only partially visible behind o…

cs.CV2022

Opening up Open-World Tracking

Yang Liu, Idil Esen Zulfikar, Jonathon Luiten +5

Tracking and detecting any object, including ones never-seen-before during model training, is a crucial but elusive capability of autonomous systems. An autonomous agent that is bl…

cs.LG2025

OpenThoughts: Data Recipes for Reasoning Models

Etash Guha, Ryan Marten, Sedrick Keh +47

Reasoning models have made rapid progress on many benchmarks involving math, code, and science. Yet, there are still many open questions about the best training recipes for reasoni…

cs.LG2025

DataComp-LM: In search of the next generation of training sets for language models

Jeffrey Li, Alex Fang, Georgios Smyrnis +56

We introduce DataComp for Language Models (DCLM), a testbed for controlled dataset experiments with the goal of improving language models. As part of DCLM, we provide a standardize…

cs.CV2020

Towards Segmenting Anything That Moves

Achal Dave, Pavel Tokmakov, Deva Ramanan

Detecting and segmenting individual objects, regardless of their category, is crucial for many applications such as action detection or robotic interaction. While this problem has…

cs.CV2024

Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis

Basile Van Hoorick, Rundi Wu, Ege Ozguroglu +6

Accurate reconstruction of complex dynamic scenes from just a single viewpoint continues to be a challenging task in computer vision. Current dynamic novel view synthesis methods t…

cs.CV2025

Espresso: High Compression For Rich Extraction From Videos for Your Vision-Language Model

Keunwoo Peter Yu, Achal Dave, Rares Ambrus +1

Recent advances in vision-language models (VLMs) have shown great promise in connecting images and text, but extending these models to long videos remains challenging due to the ra…

cs.CV2022

Differentiable Raycasting for Self-supervised Occupancy Forecasting

Tarasha Khurana, Peiyun Hu, Achal Dave +3

Motion planning for safe autonomous driving requires learning how the environment around an ego-vehicle evolves with time. Ego-centric perception of driveable regions in a scene no…

cs.CV2025

AllTracker: Efficient Dense Point Tracking at High Resolution

Adam W. Harley, Yang You, Xinglong Sun +11

We introduce AllTracker: a model that estimates long-range point tracks by way of estimating the flow field between a query frame and every other frame of a video. Unlike existing…

cs.CL2024

Linearizing Large Language Models

Jean Mercat, Igor Vasiljevic, Sedrick Keh +4

Linear transformers have emerged as a subquadratic-time alternative to softmax attention and have garnered significant interest due to their fixed-size recurrent state that lowers…

cs.CV2017

Predictive-Corrective Networks for Action Detection

Achal Dave, Olga Russakovsky, Deva Ramanan

While deep feature learning has revolutionized techniques for static-image understanding, the same does not quite hold for video processing. Architectures and optimization techniqu…

cs.CV2024

TAO-Amodal: A Benchmark for Tracking Any Object Amodally

Cheng-Yen Hsieh, Kaihua Chen, Achal Dave +2

Amodal perception, the ability to comprehend complete object structures from partial visibility, is a fundamental skill, even for infants. Its significance extends to applications…

cs.CV2023

Towards Long-Tailed 3D Detection

Neehar Peri, Achal Dave, Deva Ramanan +1

Contemporary autonomous vehicle (AV) benchmarks have advanced techniques for training 3D detectors, particularly on large-scale lidar data. Surprisingly, although semantic class la…

cs.CV2023

Shape of You: Precise 3D shape estimations for diverse body types

Rohan Sarkar, Achal Dave, Gerard Medioni +1

This paper presents Shape of You (SoY), an approach to improve the accuracy of 3D body shape estimation for vision-based clothing recommendation systems. While existing methods hav…

cs.CV2020

Detecting Invisible People

Tarasha Khurana, Achal Dave, Deva Ramanan

Monocular object detection and tracking have improved drastically in recent years, but rely on a key assumption: that objects are visible to the camera. Many offline tracking appro…

cs.CV2025

Should VLMs be Pre-trained with Image Data?

Sedrick Keh, Jean Mercat, Samir Yitzhak Gadre +8

Pre-trained LLMs that are further trained with image data perform well on vision-language tasks. While adding images during a second training phase effectively unlocks this capabil…

cs.CV2023

HandsOff: Labeled Dataset Generation With No Additional Human Annotations

Austin Xu, Mariya I. Vasileva, Achal Dave +1

Recent work leverages the expressive power of generative adversarial networks (GANs) to generate labeled synthetic datasets. These dataset generation methods often require new anno…

cs.CV2022

BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video

Ali Athar, Jonathon Luiten, Paul Voigtlaender +4

Multiple existing benchmarks involve tracking and segmenting objects in video e.g., Video Object Segmentation (VOS) and Multi-Object Tracking and Segmentation (MOTS), but there is…

cs.CV2024

GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion

Vitor Guizilini, Pavel Tokmakov, Achal Dave +1

3D reconstruction from a single image is a long-standing problem in computer vision. Learning-based methods address its inherent scale ambiguity by leveraging increasingly large la…

cs.CV2020

TAO: A Large-Scale Benchmark for Tracking Any Object

Achal Dave, Tarasha Khurana, Pavel Tokmakov +2

For many years, multi-object tracking benchmarks have focused on a handful of categories. Motivated primarily by surveillance and self-driving applications, these datasets provide…

cs.RO2024

Dreamitate: Real-World Visuomotor Policy Learning via Video Generation

Junbang Liang, Ruoshi Liu, Ege Ozguroglu +5

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…

cs.CV2022

Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)

Alex Fang, Gabriel Ilharco, Mitchell Wortsman +4

Contrastively trained language-image models such as CLIP, ALIGN, and BASIC have demonstrated unprecedented robustness to multiple challenging natural distribution shifts. Since the…

cs.LG2020

Measuring Robustness to Natural Distribution Shifts in Image Classification

Rohan Taori, Achal Dave, Vaishaal Shankar +3

We study how robust current ImageNet models are to distribution shifts arising from natural variations in datasets. Most research on robustness focuses on synthetic image perturbat…