论文检索

Applications/Everything Else

Yansong Ning, Hao Liu, Hao Wang, Zhenyu Zeng, Hui Xiong

Accurate Urban SpatioTemporal Prediction (USTP) is of great importance to the development and operation of the smart city. As an emerging building block, multi-sourced urban data are usually integrated as urban knowledge graphs (UrbanKGs) to provide critical knowledge for urban spatiotemporal prediction models. However, existing UrbanKGs are often tailored for specific downstream prediction tasks and are not publicly available, which limits the potential advancement. This paper presents UUKG, the unified urban knowledge graph dataset for knowledge-enhanced urban spatiotemporal predictions. Specifically, we first construct UrbanKGs consisting of millions of triplets for two metropolises by connecting heterogeneous urban entities such as administrative boroughs, POIs, and road segments. Moreover, we conduct qualitative and quantitative analysis on constructed UrbanKGs and uncover diverse high-order structural patterns, such as hierarchies and cycles, that can be leveraged to benefit downstream USTP tasks. To validate and facilitate the use of UrbanKGs, we implement and evaluate 15 KG embedding methods on the KG completion task and integrate the learned KG embeddings into 9 spatiotemporal models for five different USTP tasks. The extensive experimental results not only provide benchmarks of knowledge-enhanced USTP models under different task settings but also highlight the potential of state-of-the-art high-order structure-aware UrbanKG embedding methods. We hope the proposed UUKG fosters research on urban knowledge graphs and broad smart city applications. The dataset and source code are available at https://github.com/usail-hkust/UUKG/.

Applications/Language, Speech and Dialog

Simone Papicchio, Paolo Papotti, Luca Cagliero

Table Representation Learning (TRL) models are commonly pre-trained on large open-domain datasets comprising millions of tables and then used to address downstream tasks. Choosing the right TRL model to use on proprietary data can be challenging, as the best results depend on the content domain, schema, and data quality. Our purpose is to support end-users in testing TRL models on proprietary data in two established SQL-centric tasks, i.e., Question Answering (QA) and Semantic Parsing (SP). We present QATCH (Query-Aided TRL Checklist), a toolbox to highlight TRL models’ strengths and weaknesses on relational tables unseen at training time. For an input table, QATCH automatically generates a testing checklist tailored to QA and SP. Checklist generation is driven by a SQL query engine that crafts tests of different complexity. This design facilitates inherent portability, allowing the checks to be used by alternative models. We also introduce a set of cross-task performance metrics evaluating the TRL model’s performance over its output. Finally, we show how QATCH automatically generates tests for proprietary datasets to evaluate various state-of-the-art models including TAPAS, TAPEX, and CHATGPT.

Applications/Language, Speech and Dialog

Hengli Li, Song-Chun Zhu, Zilong Zheng

The ability to discern and comprehend pragmatic meanings is a cornerstone of social and emotional intelligence, referred to as pragmatic reasoning. Despite the strides made in the development of Large Language Models (LLMs), such as ChatGPT, these models grapple with capturing the nuanced and ambiguous facets of language, falling short of the aspiration to build human-like conversational agents. In this work, we introduce a novel benchmark, the **DiPlomat**, which delves into the fundamental components of conversational pragmatic reasoning, encompassing situational context reasoning, open-world knowledge acquisition, and unified figurative language understanding. We start by collecting a new human-annotated dialogue dataset, composed of 4,177 multi-turn dialogues and a vocabulary of 48,900 words. Along with the dataset, two tasks are proposed to evaluate machines' pragmatic reasoning capabilities, namely, Pragmatic Reasoning and Identification(PIR) and Conversational Question Answering (CQA). Furthermore, we probe into a zero-shot natural language inference task, where the significance of context in pragmatic reasoning is underscored. Experimental findings illustrate the existing limitations of current prevailing LLMs in the realm of pragmatic reasoning, shedding light on the pressing need for further research to facilitate the emergence of emotional intelligence within human-like conversational agents.

Applications/Chemistry and Drug Discovery

Tim Kucera, Carlos Oliver, Dexiong Chen, Karsten Borgwardt

We present ProteinShake, a Python software package that simplifies datasetcreation and model evaluation for deep learning on protein structures. Users cancreate custom datasets or load an extensive set of pre-processed datasets fromthe Protein Data Bank (PDB) and AlphaFoldDB. Each dataset is associated withprediction tasks and evaluation functions covering a broad array of biologicalchallenges. A benchmark on these tasks shows that pre-training almost alwaysimproves performance, the optimal data modality (graphs, voxel grids, or pointclouds) is task-dependent, and models struggle to generalize to new structures.ProteinShake makes protein structure data easily accessible and comparisonamong models straightforward, providing challenging benchmark settings withreal-world implications.ProteinShake is available at: https://proteinshake.ai

Applications

Jeroen Berrevoets, Daniel Jarrett, Alex Chan, Mihaela van der Schaar

Numerous real-world systems, ranging from healthcare to energy grids, involve users competing for finite and potentially scarce resources. Designing policies for resource allocation in such real-world systems is challenging for many reasons, including the changing nature of user types and their (possibly urgent) need for resources. Researchers have developed numerous machine learning solutions for determining resource allocation policies in these challenging settings. However, a key limitation has been the absence of good methods and test-beds for benchmarking these policies; almost all resource allocation policies are benchmarked in environments which are either completely synthetic or do not allow _any_ deviation from historical data. In this paper we introduce AllSim, which is a benchmarking environment for realistically simulating the impact and utility of policies for resource allocation in systems in which users compete for such scarce resources. Building such a benchmarking environment is challenging because it needs to successfully take into account _the entire collective_ of potential users and the impact a resource allocation policy has on all the other users in the system. AllSim's benchmarking environment is modular (each component being parameterized individually), learnable (informed by historical data), and customizable (adaptable to changing conditions). These, when interacting with an allocation policy, produce a dataset of simulated outcomes for evaluation and comparison of such policies. We believe AllSim is an essential step towards a more systematic evaluation of policies for scarce resource allocation compared to current approaches for benchmarking such methods.

Applications/Genetics, Cell Biology, etc

Zhangyang Gao, Cheng Tan, Yijie Zhang, Xingran Chen, Lirong Wu, Stan Z. Li

Protein inverse folding has attracted increasing attention in recent years. However, we observe that current methods are usually limited to the CATH dataset and the recovery metric. The lack of a unified framework for ensembling and comparing different methods hinders the comprehensive investigation. In this paper, we propose ProteinBench, a new benchmark for protein design, which comprises extended protein design tasks, integrated models, and diverse evaluation metrics. We broaden the application of methods originally designed for single-chain protein design to new scenarios of multi-chain and \textit{de novo} protein design. Recent impressive methods, including GraphTrans, StructGNN, GVP, GCA, AlphaDesign, ProteinMPNN, PiFold and KWDesign are integrated into our framework. In addition to the recovery, we also evaluate the confidence, diversity, sc-TM, efficiency, and robustness to thoroughly revisit current protein design approaches and inspire future work. As a result, we establish the first comprehensive benchmark for protein design, which is publicly available at \url{https://github.com/A4Bio/OpenCPD}.

Applications/Language, Speech and Dialog

CHEN CHEN, Yuchen Hu, Chao-Han Huck Yang, Sabato Marco Siniscalchi, Pin-Yu Chen, Eng-Siong Chng

Advancements in deep neural networks have allowed automatic speech recognition (ASR) systems to attain human parity on several publicly available clean speech datasets. However, even state-of-the-art ASR systems experience performance degradation when confronted with adverse conditions, as a well-trained acoustic model is sensitive to variations in the speech domain, e.g., background noise. Intuitively, humans address this issue by relying on their linguistic knowledge: the meaning of ambiguous spoken terms is usually inferred from contextual cues thereby reducing the dependency on the auditory system. Inspired by this observation, we introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction, where N-best decoding hypotheses provide informative elements for true transcription prediction. This approach is a paradigm shift from the traditional language model rescoring strategy that can only select one candidate hypothesis as output transcription. The proposed benchmark contains a novel dataset, "HyPoradise" (HP), encompassing more than 316,000 pairs of N-best hypotheses and corresponding accurate transcriptions across prevalent speech domains. Given this dataset, we examine three types of error correction techniques based on LLMs with varying amounts of labeled hypotheses-transcription pairs, which gains significant word error rate (WER) reduction. Experimental evidence demonstrates the proposed technique achieves a breakthrough by surpassing the upper bound of traditional re-ranking based methods. More surprisingly, LLM with reasonable prompt design can even correct those tokens that are missing in N-best list. We make our results publicly accessible for reproducible pipelines with released pre-trained models, thus providing a new paradigm for ASR error correction with LLMs.

Social Aspects/Fairness, Equity, Justice and Safety

Candice Schumann, Femi Olanubi, Auriel Wright, Ellis Monk, Courtney Heldreth, Susanna Ricco

Understanding different human attributes and how they affect model behavior may become a standard need for all model creation and usage, from traditional computer vision tasks to the newest multimodal generative AI systems. In computer vision specifically, we have relied on datasets augmented with perceived attribute signals (eg, gender presentation, skin tone, and age) and benchmarks enabled by these datasets. Typically labels for these tasks come from human annotators. However, annotating attribute signals, especially skin tone, is a difficult and subjective task. Perceived skin tone is affected by technical factors, like lighting conditions, and social factors that shape an annotator's lived experience.This paper examines the subjectivity of skin tone annotation through a series of annotation experiments using the Monk Skin Tone (MST) scale~\cite{Monk2022Monk}, a small pool of professional photographers, and a much larger pool of trained crowdsourced annotators. Along with this study we release the Monk Skin Tone Examples (MST-E) dataset, containing 1515 images and 31 videos spread across the full MST scale. MST-E is designed to help train human annotators to annotate MST effectively.Our study shows that annotators can reliably annotate skin tone in a way that aligns with an expert in the MST scale, even under challenging environmental conditions. We also find evidence that annotators from different geographic regions rely on different mental models of MST categories resulting in annotations that systematically vary across regions. Given this, we advise practitioners to use a diverse set of annotators and a higher replication count for each image when annotating skin tone for fairness research.

Deep Learning/Graph Neural Networks

Zhou Zhiyao, Sheng Zhou, Bochao Mao, Xuanyi Zhou, Jiawei Chen, Qiaoyu Tan, Daochen Zha, Yan Feng, Chun Chen, Can Wang

Graph Neural Networks (GNNs) have emerged as the *de facto* standard for representation learning on graphs, owing to their ability to effectively integrate graph topology and node attributes. However, the inherent suboptimal nature of node connections, resulting from the complex and contingent formation process of graphs, presents significant challenges in modeling them effectively. To tackle this issue, Graph Structure Learning (GSL), a family of data-centric learning approaches, has garnered substantial attention in recent years. The core concept behind GSL is to jointly optimize the graph structure and the corresponding GNN models. Despite the proposal of numerous GSL methods, the progress in this field remains unclear due to inconsistent experimental protocols, including variations in datasets, data processing techniques, and splitting strategies. In this paper, we introduce OpenGSL, the first comprehensive benchmark for GSL, aimed at addressing this gap. OpenGSL enables a fair comparison among state-of-the-art GSL methods by evaluating them across various popular datasets using uniform data processing and splitting strategies. Through extensive experiments, we observe that existing GSL methods do not consistently outperform vanilla GNN counterparts. We also find that there is no significant correlation between the homophily of the learned structure and task performance, challenging the common belief. Moreover, we observe that the learned graph structure demonstrates a strong generalization ability across different GNN models, despite the high computational and space consumption. We hope that our open-sourced library will facilitate rapid and equitable evaluation and inspire further innovative research in this field. The code of the benchmark can be found in https://github.com/OpenGSL/OpenGSL.

Deep Learning/Sequential Models, Time series

Cheng Tan, Siyuan Li, Zhangyang Gao, Wenfei Guan, Zedong Wang, Zicheng Liu, Lirong Wu, Stan Z. Li

Spatio-temporal predictive learning is a learning paradigm that enables models to learn spatial and temporal patterns by predicting future frames from given past frames in an unsupervised manner. Despite remarkable progress in recent years, a lack of systematic understanding persists due to the diverse settings, complex implementation, and difficult reproducibility. Without standardization, comparisons can be unfair and insights inconclusive. To address this dilemma, we propose OpenSTL, a comprehensive benchmark for spatio-temporal predictive learning that categorizes prevalent approaches into recurrent-based and recurrent-free models. OpenSTL provides a modular and extensible framework implementing various state-of-the-art methods. We conduct standard evaluations on datasets across various domains, including synthetic moving object trajectory, human motion, driving scenes, traffic flow, and weather forecasting. Based on our observations, we provide a detailed analysis of how model architecture and dataset properties affect spatio-temporal predictive learning performance. Surprisingly, we find that recurrent-free models achieve a good balance between efficiency and performance than recurrent models. Thus, we further extend the common MetaFormers to boost recurrent-free spatial-temporal predictive learning. We open-source the code and models at https://github.com/chengtan9907/OpenSTL.

Applications/Genetics, Cell Biology, etc

Zitong Sam Chen, Chau Pham, Siqi Wang, Michael Doron, Nikita Moshkov, Bryan Plummer, Juan C. Caicedo

Most neural networks assume that input images have a fixed number of channels (three for RGB images). However, there are many settings where the number of channels may vary, such as microscopy images where the number of channels changes depending on instruments and experimental goals. Yet, there has not been a systemic attempt to create and evaluate neural networks that are invariant to the number and type of channels. As a result, trained models remain specific to individual studies and are hardly reusable for other microscopy settings. In this paper, we present a benchmark for investigating channel-adaptive models in microscopy imaging, which consists of 1) a dataset of varied-channel single-cell images, and 2) a biologically relevant evaluation framework. In addition, we adapted several existing techniques to create channel-adaptive models and compared their performance on this benchmark to fixed-channel, baseline models. We find that channel-adaptive models can generalize better to out-of-domain tasks and can be computationally efficient. We contribute a curated dataset and an evaluation API to facilitate objective comparisons in future research and applications.

Mehran Kazemi, Quan Yuan, Deepti Bhatia, Najoung Kim, Xin Xu, Vaiva Imbrasaite, Deepak Ramachandran

Automated reasoning with unstructured natural text is a key requirement for many potential applications of NLP and for developing robust AI systems. Recently, Language Models (LMs) have demonstrated complex reasoning capacities even without any finetuning. However, existing evaluation for automated reasoning assumes access to a consistent and coherent set of information over which models reason. When reasoning in the real-world, the available information is frequently inconsistent or contradictory, and therefore models need to be equipped with a strategy to resolve such conflicts when they arise. One widely-applicable way of resolving conflicts is to impose preferences over information sources (e.g., based on source credibility or information recency) and adopt the source with higher preference. In this paper, we formulate the problem of reasoning with contradictory information guided by preferences over sources as the classical problem of defeasible reasoning, and develop a dataset called BoardgameQA for measuring the reasoning capacity of LMs in this setting. BoardgameQA also incorporates reasoning with implicit background knowledge, to better reflect reasoning problems in downstream applications. We benchmark various LMs on BoardgameQA and the results reveal a significant gap in the reasoning capacity of state-of-the-art LMs on this problem, showing that reasoning with conflicting information does not surface out-of-the-box in LMs. While performance can be improved with finetuning, it nevertheless remains poor.

Applications/Computer Vision

Hugo Laurençon, Lucile Saulnier, Leo Tronchon, Stas Bekman, Amanpreet Singh, Anton Lozhkov, Thomas Wang, Siddharth Karamcheti, Alexander Rush, Douwe Kiela 等

Large multimodal models trained on natural documents, which interleave images and text, outperform models trained on image-text pairs on various multimodal benchmarks. However, the datasets used to train these models have not been released, and the collection process has not been fully specified. We introduce the OBELICS dataset, an open web-scale filtered dataset of interleaved image-text documents comprising 141 million web pages extracted from Common Crawl, 353 million associated images, and 115 billion text tokens. We describe the dataset creation process, present comprehensive filtering rules, and provide an analysis of the dataset's content. To show the viability of OBELICS, we train on the dataset vision and language models of 9 and 80 billion parameters, IDEFICS-9B and IDEFICS, and obtain competitive performance on different multimodal benchmarks. We release our dataset, models and code.

Shihang Feng, Hanchen Wang, Chengyuan Deng, Yinan Feng, Yanhua Liu, Min Zhu, Peng Jin, Yinpeng Chen, Youzuo Lin

Elastic geophysical properties (such as P- and S-wave velocities) are of great importance to various subsurface applications like CO$_2$ sequestration and energy exploration (e.g., hydrogen and geothermal). Elastic full waveform inversion (FWI) is widely applied for characterizing reservoir properties. In this paper, we introduce $\mathbf{\mathbb{E}^{FWI}}$, a comprehensive benchmark dataset that is specifically designed for elastic FWI. $\mathbf{\mathbb{E}^{FWI}}$ encompasses 8 distinct datasets that cover diverse subsurface geologic structures (flat, curve, faults, etc). The benchmark results produced by three different deep learning methods are provided. In contrast to our previously presented dataset (pressure recordings) for acoustic FWI (referred to as OpenFWI), the seismic dataset in $\mathbf{\mathbb{E}^{FWI}}$ has both vertical and horizontal components. Moreover, the velocity maps in $\mathbf{\mathbb{E}^{FWI}}$ incorporate both P- and S-wave velocities. While the multicomponent data and the added S-wave velocity make the data more realistic, more challenges are introduced regarding the convergence and computational cost of the inversion. We conduct comprehensive numerical experiments to explore the relationship between P-wave and S-wave velocities in seismic data. The relation between P- and S-wave velocities provides crucial insights into the subsurface properties such as lithology, porosity, fluid content, etc. We anticipate that $\mathbf{\mathbb{E}^{FWI}}$ will facilitate future research on multiparameter inversions and stimulate endeavors in several critical research topics of carbon-zero and new energy exploration. All datasets, codes and relevant information can be accessed through our website at https://efwi-lanl.github.io/

Reinforcement Learning

Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas, Sander Schulhoff, Brandon Houghton, Rohin Shah

The MineRL BASALT competition has served to catalyze advances in learning from human feedback through four hard-to-specify tasks in Minecraft, such as create and photograph a waterfall. Given the completion of two years of BASALT competitions, we offer to the community a formalized benchmark through the BASALT Evaluation and Demonstrations Dataset (BEDD), which serves as a resource for algorithm development and performance assessment. BEDD consists of a collection of 26 million image-action pairs from nearly 14,000 videos of human players completing the BASALT tasks in Minecraft. It also includes over 3,000 dense pairwise human evaluations of human and algorithmic agents. These comparisons serve as a fixed, preliminary leaderboard for evaluating newly-developed algorithms. To enable this comparison, we present a streamlined codebase for benchmarking new algorithms against the leaderboard. In addition to presenting these datasets, we conduct a detailed analysis of the data from both datasets to guide algorithm development and evaluation. The released code and data are available at https://github.com/minerllabs/basalt-benchmark.

Applications

Mohammad Mahdi Kamani, Yuhang Yao, Hanjia Lyu, Zhongwei Cheng, Lin Chen, Liangju Li, Carlee Joe-Wong, Jiebo Luo

In the rapidly evolving landscape of smart home automation, the potential of IoT devices is vast. In this realm, rules are the main tool utilized for this automation, which are predefined conditions or triggers that establish connections between devices, enabling seamless automation of specific processes. However, one significant challenge researchers face is the lack of comprehensive datasets to explore and advance the field of smart home rule recommendations. These datasets are essential for developing and evaluating intelligent algorithms that can effectively recommend rules for automating processes while preserving the privacy of the users, as it involves personal information about users' daily lives. To bridge this gap, we present the Wyze Rule Dataset, a large-scale dataset designed specifically for smart home rule recommendation research. Wyze Rule encompasses over 1 million rules gathered from a diverse user base of 300,000 individuals from Wyze Labs, offering an extensive and varied collection of real-world data. With a focus on federated learning, our dataset is tailored to address the unique challenges of a cross-device federated learning setting in the recommendation domain, featuring a large-scale number of clients with widely heterogeneous data. To establish a benchmark for comparison and evaluation, we have meticulously implemented multiple baselines in both centralized and federated settings. Researchers can leverage these baselines to gauge the performance and effectiveness of their rule recommendation systems, driving advancements in the domain. The Wyze Rule Dataset is publicly accessible through [HuggingFace](https://huggingface.co/datasets/wyzelabs/RuleRecommendation)'s dataset API.

Applications/Genetics, Cell Biology, etc

Pascal Notin, Aaron Kollasch, Daniel Ritter, Lood van Niekerk, Steffanie Paul, Han Spinner, Nathan Rollins, Ada Shaw, Rose Orenbuch, Ruben Weitzman 等

Predicting the effects of mutations in proteins is critical to many applications, from understanding genetic disease to designing novel proteins to address our most pressing challenges in climate, agriculture and healthcare. Despite an increase in machine learning-based protein modeling methods, assessing their effectiveness is problematic due to the use of distinct, often contrived, experimental datasets and variable performance across different protein families. Addressing these challenges requires scale. To that end we introduce ProteinGym v1.0, a large-scale and holistic set of benchmarks specifically designed for protein fitness prediction and design. It encompasses both a broad collection of over 250 standardized deep mutational scanning assays, spanning millions of mutated sequences, as well as curated clinical datasets providing high-quality expert annotations about mutation effects. We devise a robust evaluation framework that combines metrics for both fitness prediction and design, factors in known limitations of the underlying experimental methods, and covers both zero-shot and supervised settings. We report the performance of a diverse set of over 40 high-performing models from various subfields (eg., mutation effects, inverse folding) into a unified benchmark. We open source the corresponding codebase, datasets, MSAs, structures, predictions and develop a user-friendly website that facilitates comparisons across all settings.

Applications/Everything Else

Maurice Weber, Carlo Siebenschuh, Rory Butler, Anton Alexandrov, Valdemar Thanner, Georgios Tsolakis, Haris Jabbar, Ian Foster, Bo Li, Rick Stevens 等

We introduce WordScape, a novel pipeline for the creation of cross-disciplinary, multilingual corpora comprising millions of pages with annotations for document layout detection. Relating visual and textual items on document pages has gained further significance with the advent of multimodal models. Various approaches proved effective for visual question answering or layout segmentation. However, the interplay of text, tables, and visuals remains challenging for a variety of document understanding tasks. In particular, many models fail to generalize well to diverse domains and new languages due to insufficient availability of training data. WordScape addresses these limitations. Our automatic annotation pipeline parses the Open XML structure of Word documents obtained from the web, jointly providing layout-annotated document images and their textual representations. In turn, WordScape offers unique properties as it (1) leverages the ubiquity of the Word file format on the internet, (2) is readily accessible through the Common Crawl web corpus, (3) is adaptive to domain-specific documents, and (4) offers culturally and linguistically diverse document pages with natural semantic structure and high-quality text. Together with the pipeline, we will additionally release 9.5M urls to word documents which can be processed using WordScape to create a dataset of over 40M pages. Finally, we investigate the quality of text and layout annotations extracted by WordScape, assess the impact on document understanding benchmarks, and demonstrate that manual labeling costs can be substantially reduced.

Applications/Computer Vision

Xiaoyu Tian, Tao Jiang, Longfei Yun, Yucheng Mao, Huitong Yang, Yue Wang, Yilun Wang, Hang Zhao

Robotic perception requires the modeling of both 3D geometry and semantics. Existing methods typically focus on estimating 3D bounding boxes, neglecting finer geometric details and struggling to handle general, out-of-vocabulary objects. 3D occupancy prediction, which estimates the detailed occupancy states and semantics of a scene, is an emerging task to overcome these limitations.To support 3D occupancy prediction, we develop a label generation pipeline that produces dense, visibility-aware labels for any given scene. This pipeline comprises three stages: voxel densification, occlusion reasoning, and image-guided voxel refinement. We establish two benchmarks, derived from the Waymo Open Dataset and the nuScenes Dataset, namely Occ3D-Waymo and Occ3D-nuScenes benchmarks. Furthermore, we provide an extensive analysis of the proposed dataset with various baseline models. Lastly, we propose a new model, dubbed Coarse-to-Fine Occupancy (CTF-Occ) network, which demonstrates superior performance on the Occ3D benchmarks.The code, data, and benchmarks are released at \url{https://tsinghua-mars-lab.github.io/Occ3D/}.

Applications/Time Series

Patrick Emami, Abhijeet Sahu, Peter Graf

Short-term forecasting of residential and commercial building energy consumption is widely used in power systems and continues to grow in importance. Data-driven short-term load forecasting (STLF), although promising, has suffered from a lack of open, large-scale datasets with high building diversity. This has hindered exploring the pretrain-then-fine-tune paradigm for STLF. To help address this, we present BuildingsBench, which consists of: 1) Buildings-900K, a large-scale dataset of 900K simulated buildings representing the U.S. building stock; and 2) an evaluation platform with over 1,900 real residential and commercial buildings from 7 open datasets. BuildingsBench benchmarks two under-explored tasks: zero-shot STLF, where a pretrained model is evaluated on unseen buildings without fine-tuning, and transfer learning, where a pretrained model is fine-tuned on a target building. The main finding of our benchmark analysis is that synthetically pretrained models generalize surprisingly well to real commercial buildings. An exploration of the effect of increasing dataset size and diversity on zero-shot commercial building performance reveals a power-law with diminishing returns. We also show that fine-tuning pretrained models on real commercial and residential buildings improves performance for a majority of target buildings. We hope that BuildingsBench encourages and facilitates future research on generalizable STLF. All datasets and code can be accessed from https://github.com/NREL/BuildingsBench.