BENCHAGENTS: Automated Benchmark Creation with Agent Interaction

Evaluations are limited by benchmark availability. As models evolve, there is a need to create benchmarks that can measure progress on new generative capabilities. However, creating new benchmarks through human annotations is slow and expensive, restricting comprehensive evaluations for any capability. We introduce BENCHAGENTS, a framework that methodically leverages large language models (LLMs) to automate benchmark creation for complex capabilities while inherently ensuring data and metric quality. BENCHAGENTS decomposes the benchmark creation process into planning, generation, data verification, and evaluation, each of which is executed by an LLM agent. These agents interact with each other and utilize human-in-the-loop feedback from benchmark developers to explicitly improve and flexibly control data diversity and quality. We use BENCHAGENTS to create benchmarks to evaluate capabilities related to planning and constraint satisfaction during text generation. We then use these benchmarks to study seven state-of-the-art models and extract new insights on common failure modes and model differences.

Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models

With models getting stronger, evaluations have grown more complex, testing multiple skills in one benchmark and even in the same instance at once. However, skill-wise performance is obscured when inspecting aggregate accuracy, under-utilizing the rich signal modern benchmarks contain. We propose an automatic approach to recover the underlying skills relevant for any evaluation instance, by way of inspecting model-generated rationales. After validating the relevance of rationale-parsed skills and inferring skills for $46$k instances over $12$ benchmarks, we observe many skills to be common across benchmarks, resulting in the curation of hundreds of skill-slices (i.e. sets of instances testing a common skill). Inspecting accuracy over these slices yields novel insights on model trade-offs: e.g., compared to GPT-4o and Claude 3.5 Sonnet, on average, Gemini 1.5 Pro is $18\%$ more accurate in "computing molar mass", but $19\%$ less accurate in "applying constitutional law", despite the overall accuracies of the three models differing by a mere $0.4\%$. Furthermore, we demonstrate the practical utility of our approach by showing that insights derived from skill slice analysis can generalize to held-out instances: when routing each instance to the model strongest on the relevant skills, we see a $3\%$ accuracy improvement over our $12$ dataset corpus. Our skill-slices and framework open a new avenue in model evaluation, leveraging skill-specific analyses to unlock a more granular and actionable understanding of model capabilities.

Eureka: Evaluating and Understanding Large Foundation Models

Rigorous and reproducible evaluation is critical for assessing the state of the art and for guiding scientific advances in Artificial Intelligence. Evaluation is challenging in practice due to several reasons, including benchmark saturation, lack of transparency in methods used for measurement, development challenges in extracting measurements for generative tasks, and, more generally, the extensive number of capabilities required for a well-rounded comparison across models. We make three contributions to alleviate the above challenges. First, we present Eureka, an open-source framework for standardizing evaluations of large foundation models beyond single-score reporting and rankings. Second, we introduce Eureka-Bench as an extensible collection of benchmarks testing capabilities that (i) are still challenging for state-of-the-art models and (ii) represent fundamental but overlooked language and multimodal capabilities. The inherent space for improvement in non-saturated benchmarks enables us to discover meaningful differences between models at a capability level. Third, using Eureka, we conduct an analysis of 12 state-of-the-art models, providing in-depth insights into failure understanding and model comparison, which can be leveraged to plan targeted improvements. In contrast to recent trends in reports and leaderboards showing absolute rankings and claims for one model or another to be the best, our analysis shows that there is no such best model. Different models have different strengths, but there are models that appear more often than others as best performers for some capabilities. Despite the recent improvements, current models still struggle with several fundamental capabilities including detailed image understanding, benefiting from multimodal input when available rather than fully relying on language, factuality and grounding for information retrieval, and over refusals.

Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models

Large language models (LLMs) and vision-language models (VLMs) have demonstrated remarkable performance across a wide range of tasks and domains. Despite this promise, spatial understanding and reasoning -- a fundamental component of human cognition -- remains under-explored. We develop novel benchmarks that cover diverse aspects of spatial reasoning such as relationship understanding, navigation, and counting. We conduct a comprehensive evaluation of competitive language and vision-language models. Our findings reveal several counter-intuitive insights that have been overlooked in the literature: (1) Spatial reasoning poses significant challenges where competitive models can fall behind random guessing; (2) Despite additional visual input, VLMs often under-perform compared to their LLM counterparts; (3) When both textual and visual information is available, multi-modal language models become less reliant on visual information if sufficient textual clues are provided. Additionally, we demonstrate that leveraging redundancy between vision and text can significantly enhance model performance. We hope our study will inform the development of multimodal models to improve spatial intelligence and further close the gap with human intelligence.

HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World

Building an interactive AI assistant that can perceive, reason, and collaborate with humans in the real world has been a long-standing pursuit in the AI community. This work is part of a broader research effort to develop intelligent agents that can interactively guide humans through performing tasks in the physical world. As a first step in this direction, we introduce HoloAssist, a large-scale egocentric human interaction dataset, where two people collaboratively complete physical manipulation tasks. The task performer executes the task while wearing a mixed-reality headset that captures seven synchronized data streams. The task instructor watches the performer's egocentric video in real time and guides them verbally. By augmenting the data with action and conversational annotations and observing the rich behaviors of various participants, we present key insights into how human assistants correct mistakes, intervene in the task completion procedure, and ground their instructions to the environment. HoloAssist spans 166 hours of data captured by 350 unique instructor-performer pairs. Furthermore, we construct and present benchmarks on mistake detection, intervention type prediction, and hand forecasting, along with detailed analysis. We expect HoloAssist will provide an important resource for building AI assistants that can fluidly collaborate with humans in the real world. Data can be downloaded at https://holoassist.github.io/.

Beyond Generation: Harnessing Text to Image Models for Object Detection and Segmentation

We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation into foreground object generation, and contextually coherent background generation. To generate foreground objects, we employ a straightforward textual template, incorporating the object class name as input prompts. This is fed into a text-to-image synthesis framework, producing various foreground images set against isolated backgrounds. A foreground-background segmentation algorithm is then used to generate foreground object masks. To generate context images, we begin by creating language descriptions of the context. This is achieved by applying an image captioning method to a small set of images representing the desired context. These textual descriptions are then transformed into a diverse array of context images via a text-to-image synthesis framework. Subsequently, we composite these with the foreground object masks produced in the initial step, utilizing a cut-and-paste method, to formulate the training data. We demonstrate the advantages of our approach on five object detection and segmentation datasets, including Pascal VOC and COCO. We found that detectors trained solely on synthetic data produced by our method achieve performance comparable to those trained on real data (Fig. 1). Moreover, a combination of real and synthetic data yields even much better results. Further analysis indicates that the synthetic data distribution complements the real data distribution effectively. Additionally, we emphasize the compositional nature of our data generation approach in out-of-distribution and zero-shot data generation scenarios. We open-source our code at https://github.com/gyhandy/Text2Image-for-Detection

Controllable Text-to-Image Generation with GPT-4

Current text-to-image generation models often struggle to follow textual instructions, especially the ones requiring spatial reasoning. On the other hand, Large Language Models (LLMs), such as GPT-4, have shown remarkable precision in generating code snippets for sketching out text inputs graphically, e.g., via TikZ. In this work, we introduce Control-GPT to guide the diffusion-based text-to-image pipelines with programmatic sketches generated by GPT-4, enhancing their abilities for instruction following. Control-GPT works by querying GPT-4 to write TikZ code, and the generated sketches are used as references alongside the text instructions for diffusion models (e.g., ControlNet) to generate photo-realistic images. One major challenge to training our pipeline is the lack of a dataset containing aligned text, images, and sketches. We address the issue by converting instance masks in existing datasets into polygons to mimic the sketches used at test time. As a result, Control-GPT greatly boosts the controllability of image generation. It establishes a new state-of-art on the spatial arrangement and object positioning generation and enhances users' control of object positions, sizes, etc., nearly doubling the accuracy of prior models. Our work, as a first attempt, shows the potential for employing LLMs to enhance the performance in computer vision tasks.

Neural-Sim: Learning to Generate Training Data with NeRF

Training computer vision models usually requires collecting and labeling vast amounts of imagery under a diverse set of scene configurations and properties. This process is incredibly time-consuming, and it is challenging to ensure that the captured data distribution maps well to the target domain of an application scenario. Recently, synthetic data has emerged as a way to address both of these issues. However, existing approaches either require human experts to manually tune each scene property or use automatic methods that provide little to no control; this requires rendering large amounts of random data variations, which is slow and is often suboptimal for the target domain. We present the first fully differentiable synthetic data pipeline that uses Neural Radiance Fields (NeRFs) in a closed-loop with a target application's loss function. Our approach generates data on-demand, with no human labor, to maximize accuracy for a target task. We illustrate the effectiveness of our method on synthetic and real-world object detection tasks. We also introduce a new "YCB-in-the-Wild" dataset and benchmark that provides a test scenario for object detection with varied poses in real-world environments.

Scaling Novel Object Detection with Weakly Supervised Detection Transformers

Weakly supervised object detection (WSOD) enables object detectors to be trained using image-level class labels. However, the practical application of current WSOD models is limited, as they operate at small scales and require extensive training and refinement. We propose the Weakly Supervised Detection Transformer, which enables efficient knowledge transfer from a large-scale pretraining dataset to WSOD finetuning on hundreds of novel objects. We leverage pretrained knowledge to improve the multiple instance learning framework used in WSOD, and experiments show our approach outperforms the state-of-the-art on datasets with twice the novel classes than previously shown.

Visual Attention Emerges from Recurrent Sparse Reconstruction

Visual attention helps achieve robust perception under noise, corruption, and distribution shifts in human vision, which are areas where modern neural networks still fall short. We present VARS, Visual Attention from Recurrent Sparse reconstruction, a new attention formulation built on two prominent features of the human visual attention mechanism: recurrency and sparsity. Related features are grouped together via recurrent connections between neurons, with salient objects emerging via sparse regularization. VARS adopts an attractor network with recurrent connections that converges toward a stable pattern over time. Network layers are represented as ordinary differential equations (ODEs), formulating attention as a recurrent attractor network that equivalently optimizes the sparse reconstruction of input using a dictionary of "templates" encoding underlying patterns of data. We show that self-attention is a special case of VARS with a single-step optimization and no sparsity constraint. VARS can be readily used as a replacement for self-attention in popular vision transformers, consistently improving their robustness across various benchmarks. Code is released on GitHub (https://github.com/bfshi/VARS).