NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples

Vision-language models (VLMs) have made significant progress in recent visual-question-answering (VQA) benchmarks that evaluate complex visio-linguistic reasoning. However, are these models truly effective? In this work, we show that VLMs still struggle with natural images and questions that humans can easily answer, which we term natural adversarial samples. We also find it surprisingly easy to generate these VQA samples from natural image-text corpora using off-the-shelf models like CLIP and ChatGPT. We propose a semi-automated approach to collect a new benchmark, NaturalBench, for reliably evaluating VLMs with 10,000 human-verified VQA samples. Crucially, we adopt a $\textbf{vision-centric}$ design by pairing each question with two images that yield different answers, preventing blind solutions from answering without using the images. This makes NaturalBench more challenging than previous benchmarks that can be solved with commonsense priors. We evaluate 53 state-of-the-art VLMs on NaturalBench, showing that models like LLaVA-OneVision, Cambrian-1, Llama3.2-Vision, Molmo, Qwen2-VL, and even GPT-4o lag 50%-70% behind human performance (over 90%). We analyze why NaturalBench is hard from two angles: (1) Compositionality: Solving NaturalBench requires diverse visio-linguistic skills, including understanding attribute bindings, object relationships, and advanced reasoning like logic and counting. To this end, unlike prior work that uses a single tag per sample, we tag each NaturalBench sample with 1 to 8 skill tags for fine-grained evaluation. (2) Biases: NaturalBench exposes severe biases in VLMs, as models often choose the same answer regardless of the image. Lastly, we apply our benchmark curation method to diverse data sources, including long captions (over 100 words) and non-English languages like Chinese and Hindi, highlighting its potential for dynamic evaluations of VLMs.

Pearl: A Production-ready Reinforcement Learning Agent

Reinforcement Learning (RL) offers a versatile framework for achieving long-term goals. Its generality allows us to formalize a wide range of problems that real-world intelligent systems encounter, such as dealing with delayed rewards, handling partial observability, addressing the exploration and exploitation dilemma, utilizing offline data to improve online performance, and ensuring safety constraints are met. Despite considerable progress made by the RL research community in addressing these issues, existing open-source RL libraries tend to focus on a narrow portion of the RL solution pipeline, leaving other aspects largely unattended. This paper introduces Pearl, a Production-ready RL agent software package explicitly designed to embrace these challenges in a modular fashion. In addition to presenting preliminary benchmark results, this paper highlights Pearl's industry adoptions to demonstrate its readiness for production usage. Pearl is open sourced on Github at github.com/facebookresearch/pearl and its official website is located at pearlagent.github.io.

On Noisy Evaluation in Federated Hyperparameter Tuning

Hyperparameter tuning is critical to the success of federated learning applications. Unfortunately, appropriately selecting hyperparameters is challenging in federated networks. Issues of scale, privacy, and heterogeneity introduce noise in the tuning process and make it difficult to evaluate the performance of various hyperparameters. In this work, we perform the first systematic study on the effect of noisy evaluation in federated hyperparameter tuning. We first identify and rigorously explore key sources of noise, including client subsampling, data and systems heterogeneity, and data privacy. Surprisingly, our results indicate that even small amounts of noise can significantly impact tuning methods-reducing the performance of state-of-the-art approaches to that of naive baselines. To address noisy evaluation in such scenarios, we propose a simple and effective approach that leverages public proxy data to boost the evaluation signal. Our work establishes general challenges, baselines, and best practices for future work in federated hyperparameter tuning.

Distilling Heterogeneity: From Explanations of Heterogeneous Treatment Effect Models to Interpretable Policies

Internet companies are increasingly using machine learning models to create personalized policies which assign, for each individual, the best predicted treatment for that individual. They are frequently derived from black-box heterogeneous treatment effect (HTE) models that predict individual-level treatment effects. In this paper, we focus on (1) learning explanations for HTE models; (2) learning interpretable policies that prescribe treatment assignments. We also propose guidance trees, an approach to ensemble multiple interpretable policies without the loss of interpretability. These rule-based interpretable policies are easy to deploy and avoid the need to maintain a HTE model in a production environment.

Extreme Multi-label Learning for Semantic Matching in Product Search

We consider the problem of semantic matching in product search: given a customer query, retrieve all semantically related products from a huge catalog of size 100 million, or more. Because of large catalog spaces and real-time latency constraints, semantic matching algorithms not only desire high recall but also need to have low latency. Conventional lexical matching approaches (e.g., Okapi-BM25) exploit inverted indices to achieve fast inference time, but fail to capture behavioral signals between queries and products. In contrast, embedding-based models learn semantic representations from customer behavior data, but the performance is often limited by shallow neural encoders due to latency constraints. Semantic product search can be viewed as an eXtreme Multi-label Classification (XMC) problem, where customer queries are input instances and products are output labels. In this paper, we aim to improve semantic product search by using tree-based XMC models where inference time complexity is logarithmic in the number of products. We consider hierarchical linear models with n-gram features for fast real-time inference. Quantitatively, our method maintains a low latency of 1.25 milliseconds per query and achieves a 65% improvement of Recall@100 (60.9% v.s. 36.8%) over a competing embedding-based DSSM model. Our model is robust to weight pruning with varying thresholds, which can flexibly meet different system requirements for online deployments. Qualitatively, our method can retrieve products that are complementary to existing product search system and add diversity to the match set.

What is the appropriate speed for an autonomous vehicle? Designing a Pedestrian Aware Contextual Speed Controller

Social acceptance is a major hurdle for autonomous vehicle technology, central to which is ensuring both passengers and nearby pedestrians feel safe. This idea of `feeling safe' and perceived safety is highly subjective and rooted in human intuition. As such, traditional analytical approaches to autonomous navigation often fail to cater for the social expectations of individuals. Therefore, this paper proposes an approach to capture the complexity of social expectations and integrate this complexity into a 3-layered Contextual Speed Controller. The layers were; the legal road speed limit, the socially acceptable speed given the number of nearby pedestrians, and the socially acceptable speed based on proximity to nearby pedestrians. An implementation of this layered approach was tested in areas of both low and high vehicle-pedestrian interactions. From the experiments conducted, the lower two layers were seen working in tandem to modulate the vehicle speed to appropriate levels that mimicked conservative human driver behaviour. In summary, this work quantified the relationship between pedestrian context and socially acceptable vehicle speeds, allowing for more perceivably safe autonomous driving. Furthermore, the need for different driving schemes for navigating different road environments was identified.