Autonomous systems for software engineering are now capable of fixing bugs and developing features. These systems are commonly evaluated on SWE-bench (Jimenez et al., 2024a), which assesses their ability to solve software issues from GitHub repositories. However, SWE-bench uses only Python repositories, with problem statements presented predominantly as text and lacking visual elements such as images. This limited coverage motivates our inquiry into how existing systems might perform on unrepresented software engineering domains (e.g., front-end, game development, DevOps), which use different programming languages and paradigms. Therefore, we propose SWE-bench Multimodal (SWE-bench M), to evaluate systems on their ability to fix bugs in visual, user-facing JavaScript software. SWE-bench M features 617 task instances collected from 17 JavaScript libraries used for web interface design, diagramming, data visualization, syntax highlighting, and interactive mapping. Each SWE-bench M task instance contains at least one image in its problem statement or unit tests. Our analysis finds that top-performing SWE-bench systems struggle with SWE-bench M, revealing limitations in visual problem-solving and cross-language generalization. Lastly, we show that SWE-agent’s flexible language-agnostic features enable it to substantially outperform alternatives on SWE-bench M, resolving 12% of task instances compared to 6% for the next best system.

Text-to-Video generation has achieved remarkable progress with the rise of diffusion models. In this work, we introduce Cached Memory-Guided Video Generation (Corgi), aiming to generate multi-scene videos with arbi-trary number of video clips, conditioned on input images and instruction prompts. This is a challenging task, as tra-ditional T2V methods often struggle to maintain the quality of longer videos due to the difficulties in preserving visual context from earlier scenes. We address this by introducing a cached memory mechanism that stores the key frames. Our multi-scene video generation process is explicitly con-ditioned on the cached memories to avoid forgetting the vi-sual appearance of target subjects. Corgi shows significant improvement in multi-scene video generation compared to the prior art, with up to 59.2% in long-term consistency and 7.6% in diversity.

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards, with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception.

NLP has recently made exciting progress toward training language models (LMs) with strong scientific problem-solving skills. However, model development has not focused on real-life use-cases of LMs for science, including applications in education that require processing long scientific documents. To address this, we introduce TutorEval and TutorChat. TutorEval is a diverse question-answering benchmark consisting of questions about long chapters from STEM textbooks, written by experts. TutorEval helps measure real-life usability of LMs as scientific assistants, and it is the first benchmark combining long contexts, free-form generation, and multi-disciplinary scientific knowledge. Moreover, we show that fine-tuning base models with existing dialogue datasets leads to poor performance on TutorEval. Therefore, we create TutorChat, a dataset of 80,000 long synthetic dialogues about textbooks. We use TutorChat to fine-tune Llemma models with 7B and 34B parameters. These LM tutors specialized in math have a 32K-token context window, and they excel at TutorEval while performing strongly on GSM8K and MATH. Our datasets build on open-source materials, and we release our models, data, and evaluations publicly.

Chart understanding plays a pivotal role when applying Multimodal Large Language Models (MLLMs) to real-world tasks such as analyzing scientific papers or financial reports. However, existing datasets often focus on oversimplified and homogeneous charts with template-based questions, leading to an overly optimistic measure of progress. We demonstrate that although open-source models can appear to outperform strong proprietary models on these benchmarks, a simple stress test with slightly different charts or questions deteriorates performance by up to 34.5%. In this work, we propose CharXiv, a comprehensive evaluation suite involving 2,323 natural, challenging, and diverse charts from scientific papers. CharXiv includes two types of questions: 1) descriptive questions about examining basic chart elements and 2) reasoning questions that require synthesizing information across complex visual elements in the chart. To ensure quality, all charts and questions are handpicked, curated, and verified by human experts. Our results reveal a substantial, previously underestimated gap between the reasoning skills of the strongest proprietary model (i.e., GPT-4o), which achieves 47.1% accuracy, and the strongest open-source model (i.e., InternVL Chat V1.5), which achieves 29.2%. All models lag far behind human performance of 80.5%, underscoring weaknesses in the chart understanding capabilities of existing MLLMs. We hope that CharXiv facilitates future research on MLLM chart understanding by providing a more realistic and faithful measure of progress. Project website: https://charxiv.github.io/

Compositionality is a critical capability in Text-to-Image (T2I) models, as it reflects their ability to understand and combine multiple concepts from text descriptions. Existing evaluations of compositional capability rely heavily on human-designed text prompts or fixed templates, limiting their diversity and complexity, and yielding low discriminative power. We propose ConceptMix, a scalable, controllable, and customizable benchmark which automatically evaluates compositional generation ability of T2I models. This is done in two stages. First, ConceptMix generates the text prompts: concretely, using categories of visual concepts (e.g., objects, colors, shapes, spatial relationships), it randomly samples an object and k-tuples of visual concepts, then uses GPT-4o to generate text prompts for image generation based on these sampled concepts. Second, ConceptMix evaluates the images generated in response to these prompts: concretely, it checks how many of the k concepts actually appeared in the image by generating one question per visual concept and using a strong VLM to answer them. Through administering ConceptMix to a diverse set of T2I models (proprietary as well as open ones) using increasing values of k, we show that our ConceptMix has higher discrimination power than earlier benchmarks. Specifically, ConceptMix reveals that the performance of several models, especially open models, drops dramatically with increased k. Importantly, it also provides insight into the lack of prompt diversity in widely-used training datasets. Additionally, we conduct extensive human studies to validate the design of ConceptMix and compare our automatic grading with human judgement. We hope it will guide future T2I model development.

Self-driving vehicles rely on urban street maps for autonomous navigation. In this paper, we introduce Pix2Map, a method for inferring urban street map topology directly from ego-view images, as needed to continually update and expand existing maps. This is a challenging task, as we need to infer a complex urban road topology directly from raw image data. The main insight of this paper is that this problem can be posed as cross-modal retrieval by learning a joint, cross-modal embedding space for images and existing maps, represented as discrete graphs that encode the topological layout of the visual surroundings. We conduct our experimental evaluation using the Argoverse dataset and show that it is indeed possible to accurately retrieve street maps corresponding to both seen and unseen roads solely from image data. Moreover, we show that our retrieved maps can be used to update or expand existing maps and even show proof-of-concept results for visual localization and image retrieval from spatial graphs.

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of dailylife activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards, with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception. Project page: https://ego4d-data.org/

Data augmentation has been proven to be an effective technique for developing machine learning models that are robust to known classes of distributional shifts (e.g., rotations of images), and alignment regularization is a technique often used together with data augmentation to further help the model learn representations invariant to the shifts used to augment the data. In this paper, motivated by a proliferation of options of alignment regularizations, we seek to evaluate the performances of several popular design choices along the dimensions of robustness and invariance, for which we introduce a new test procedure. Our synthetic experiment results speak to the benefits of squared ℓ2 norm regularization. Further, we also formally analyze the behavior of alignment regularization to complement our empirical study under assumptions we consider realistic. Finally, we test this simple technique we identify (worst-case data augmentation with squared ℓ2 norm alignment regularization) and show that the benefits of this method outrun those of the specially designed methods. We also release a software package in both TensorFlow and PyTorch for users to use the method with a couple of lines at https://github.com/jyanln/AlignReg.

We investigate the relationship between the frequency spectrum of image data and the generalization behavior of convolutional neural networks (CNN). We first notice CNN's ability in capturing the high-frequency components of images. These high-frequency components are almost imperceptible to a human. Thus the observation leads to multiple hypotheses that are related to the generalization behaviors of CNN, including a potential explanation for adversarial examples, a discussion of CNN's trade-off between robustness and accuracy, and some evidence in understanding training heuristics.

Cellular Electron Cryo Tomography (CECT) 3D imaging has permitted biomedical community to study macromolecule structures inside single cells with deep learning approaches. Many deep learning-based methods have since been developed to classify macromolecule structures from tomograms with high accuracy. However, several recent studies have demonstrated the lack of robustness in these models against often-imperceptible, designed changes of input. Therefore, making existing subtomogram-classification models robust remains a serious challenge. In this paper, we study the robustness of the state-of-the-art subtomogram classifier on CECT images and propose a method called Regularized Adversarial Training (RAT) to defend the classifier against a wide range of designed threats. Our results show that RAT improves robustness for CECT image classification over the previous methods.

Semi-supervised person re-identification (Re-ID) is an extension of the existing popular Re-ID research, which only uses a small portion of labeled data, while the majority of the training samples are unlabeled. This paper approaches the problem by constructing a set of heterogeneous convolutional neural networks (CNNs) fine-tuned by utilizing the labeled training samples, and then propagating the labels to the unlabeled portion for further fine-tuning the overall system in a self-paced manner. In this work, a novel self-paced multi-view clustering is presented to generate pseudo labels for unlabeled training samples, which combines multiple heterogeneous CNNs features to cluster. In our clustering method, we introduce a self-paced regularizer to select reliable samples for fine-tuning each CNNs by minimizing ranking loss and identification loss. Specifically, we select a small portion of unlabeled training data when multiple CNNs are weak. With CNNs become stronger, more and more unlabeled samples are selected. Pseudo label estimation and CNNs training are improved simultaneously, which optimize alternatively until all the unlabeled training samples are selected. In our framework, both the optimization of multiple CNNs training and multi-view clustering on unlabeled training samples are self-paced optimizing procedure. Extensive experiments have been conducted on two large-scale Re-ID datasets to demonstrate the superiority of the proposed method.