Search

Recently, Large Multimodal Models (LMMs) have made significant progress in video question-answering using a frame-wise approach by leveraging large-scale, image-based pretraining in a zero-shot manner. While image-based methods for videos have shown impressive performance, a current limitation is that they often overlook how key timestamps are selected and cannot adjust when incorrect timestamps are identified. Moreover, they are unable to extract details relevant to the question, instead providing general descriptions of the frame. To overcome this, we design a multi-LMM agent framework that travels along the video, iteratively collecting relevant information from keyframes through interactive question-asking until there is sufficient information to answer the question. Specifically, we propose TraveLER, a model that can create a plan to "Traverse" through the video, ask questions about individual frames to "Locate" and store key information, and then "Evaluate" if there is enough information to answer the question. Finally, if there is not enough information, our method is able to "Replan" based on its collected knowledge. Through extensive experiments, we find that the proposed TraveLER approach improves performance on several video question-answering benchmarks, such as NExT-QA, STAR, and Perception Test, without the need to fine-tune on specific datasets.

We present a zero-shot pose optimization method that enforces accurate physical contact constraints when estimating the 3D pose of humans. Our central insight is that since language is often used to describe physical interaction, large pretrained text-based models can act as priors on pose estimation. We can thus leverage this insight to improve pose estimation by converting natural language descriptors, generated by a large multimodal model (LMM), into tractable losses to constrain the 3D pose optimization. Despite its simplicity, our method produces surprisingly compelling pose reconstructions of people in close contact, correctly capturing the semantics of the social and physical interactions. We demonstrate that our method rivals more complex state-of-the-art approaches that require expensive human annotation of contact points and training specialized models. Moreover, unlike previous approaches, our method provides a unified framework for resolving self-contact and person-to-person contact.

We present a framework that formulates visual question answering as modular code generation. In contrast to prior work on modular approaches to VQA, our approach requires no additional training and relies on pre-trained language models (LMs), visual models pre-trained on image-caption pairs, and fifty VQA examples used for in-context learning. The generated Python programs invoke and compose the outputs of the visual models using arithmetic and conditional logic. Our approach improves accuracy on the COVR dataset by at least 3% and on the GQA dataset by roughly 2% compared to the few-shot baseline that does not employ code generation., Comment: ACL 2023

Visual Programming (VP) has emerged as a powerful framework for Visual Question Answering (VQA). By generating and executing bespoke code for each question, these methods demonstrate impressive compositional and reasoning capabilities, especially in few-shot and zero-shot scenarios. However, existing VP methods generate all code in a single function, resulting in code that is suboptimal in terms of both accuracy and interpretability. Inspired by human coding practices, we propose Recursive Visual Programming (RVP), which simplifies generated routines, provides more efficient problem solving, and can manage more complex data structures. RVP is inspired by human coding practices and approaches VQA tasks with an iterative recursive code generation approach, allowing decomposition of complicated problems into smaller parts. Notably, RVP is capable of dynamic type assignment, i.e., as the system recursively generates a new piece of code, it autonomously determines the appropriate return type and crafts the requisite code to generate that output. We show RVP's efficacy through extensive experiments on benchmarks including VSR, COVR, GQA, and NextQA, underscoring the value of adopting human-like recursive and modular programming techniques for solving VQA tasks through coding.

Addressing the challenge of adapting pre-trained vision-language models for generating insightful explanations for visual reasoning tasks with limited annotations, we present ReVisE: a $\textbf{Re}$cursive $\textbf{Vis}$ual $\textbf{E}$xplanation algorithm. Our method iteratively computes visual features (conditioned on the text input), an answer, and an explanation, to improve the explanation quality step by step until the answer converges. We find that this multi-step approach guides the model to correct its own answers and outperforms single-step explanation generation. Furthermore, explanations generated by ReVisE also serve as valuable annotations for few-shot self-training. Our approach outperforms previous methods while utilizing merely 5% of the human-annotated explanations across 10 metrics, demonstrating up to a 4.2 and 1.3 increase in BLEU-1 score on the VCR and VQA-X datasets, underscoring the efficacy and data-efficiency of our method., Comment: EMNLP 2023 Main

We present a framework for generating appropriate facial responses from a listener in dyadic social interactions based on the speaker's words. Given an input transcription of the speaker's words with their timestamps, our approach autoregressively predicts a response of a listener: a sequence of listener facial gestures, quantized using a VQ-VAE. Since gesture is a language component, we propose treating the quantized atomic motion elements as additional language token inputs to a transformer-based large language model. Initializing our transformer with the weights of a language model pre-trained only on text results in significantly higher quality listener responses than training a transformer from scratch. We show that our generated listener motion is fluent and reflective of language semantics through quantitative metrics and a qualitative user study. In our evaluation, we analyze the model's ability to utilize temporal and semantic aspects of spoken text. Project page: https://people.eecs.berkeley.edu/~evonne_ng/projects/text2listen, Comment: ICCV 2023; Project page: https://people.eecs.berkeley.edu/~evonne_ng/projects/text2listen

Training a referring expression comprehension (ReC) model for a new visual domain requires collecting referring expressions, and potentially corresponding bounding boxes, for images in the domain. While large-scale pre-trained models are useful for image classification across domains, it remains unclear if they can be applied in a zero-shot manner to more complex tasks like ReC. We present ReCLIP, a simple but strong zero-shot baseline that repurposes CLIP, a state-of-the-art large-scale model, for ReC. Motivated by the close connection between ReC and CLIP's contrastive pre-training objective, the first component of ReCLIP is a region-scoring method that isolates object proposals via cropping and blurring, and passes them to CLIP. However, through controlled experiments on a synthetic dataset, we find that CLIP is largely incapable of performing spatial reasoning off-the-shelf. Thus, the second component of ReCLIP is a spatial relation resolver that handles several types of spatial relations. We reduce the gap between zero-shot baselines from prior work and supervised models by as much as 29% on RefCOCOg, and on RefGTA (video game imagery), ReCLIP's relative improvement over supervised ReC models trained on real images is 8%., Comment: ACL 2022

Answering questions that involve multi-step reasoning requires decomposing them and using the answers of intermediate steps to reach the final answer. However, state-of-the-art models in grounded question answering often do not explicitly perform decomposition, leading to difficulties in generalization to out-of-distribution examples. In this work, we propose a model that computes a representation and denotation for all question spans in a bottom-up, compositional manner using a CKY-style parser. Our model induces latent trees, driven by end-to-end (the answer) supervision only. We show that this inductive bias towards tree structures dramatically improves systematic generalization to out-of-distribution examples, compared to strong baselines on an arithmetic expressions benchmark as well as on CLOSURE, a dataset that focuses on systematic generalization for grounded question answering. On this challenging dataset, our model reaches an accuracy of 96.1%, significantly higher than prior models that almost perfectly solve the task on a random, in-distribution split., Comment: Accepted for publication in Transactions of the Association for Computational Linguistics (TACL), 2020. Author's final version

Neural module networks (NMNs) are a popular approach for modeling compositionality: they achieve high accuracy when applied to problems in language and vision, while reflecting the compositional structure of the problem in the network architecture. However, prior work implicitly assumed that the structure of the network modules, describing the abstract reasoning process, provides a faithful explanation of the model's reasoning; that is, that all modules perform their intended behaviour. In this work, we propose and conduct a systematic evaluation of the intermediate outputs of NMNs on NLVR2 and DROP, two datasets which require composing multiple reasoning steps. We find that the intermediate outputs differ from the expected output, illustrating that the network structure does not provide a faithful explanation of model behaviour. To remedy that, we train the model with auxiliary supervision and propose particular choices for module architecture that yield much better faithfulness, at a minimal cost to accuracy., Comment: ACL 2020; first three authors contributed equally

Standard test sets for supervised learning evaluate in-distribution generalization. Unfortunately, when a dataset has systematic gaps (e.g., annotation artifacts), these evaluations are misleading: a model can learn simple decision rules that perform well on the test set but do not capture a dataset's intended capabilities. We propose a new annotation paradigm for NLP that helps to close systematic gaps in the test data. In particular, after a dataset is constructed, we recommend that the dataset authors manually perturb the test instances in small but meaningful ways that (typically) change the gold label, creating contrast sets. Contrast sets provide a local view of a model's decision boundary, which can be used to more accurately evaluate a model's true linguistic capabilities. We demonstrate the efficacy of contrast sets by creating them for 10 diverse NLP datasets (e.g., DROP reading comprehension, UD parsing, IMDb sentiment analysis). Although our contrast sets are not explicitly adversarial, model performance is significantly lower on them than on the original test sets---up to 25\% in some cases. We release our contrast sets as new evaluation benchmarks and encourage future dataset construction efforts to follow similar annotation processes.

Understanding the relationship between figures and text is key to scientific document understanding. Medical figures in particular are quite complex, often consisting of several subfigures (75% of figures in our dataset), with detailed text describing their content. Previous work studying figures in scientific papers focused on classifying figure content rather than understanding how images relate to the text. To address challenges in figure retrieval and figure-to-text alignment, we introduce MedICaT, a dataset of medical images in context. MedICaT consists of 217K images from 131K open access biomedical papers, and includes captions, inline references for 74% of figures, and manually annotated subfigures and subcaptions for a subset of figures. Using MedICaT, we introduce the task of subfigure to subcaption alignment in compound figures and demonstrate the utility of inline references in image-text matching. Our data and code can be accessed at https://github.com/allenai/medicat., Comment: EMNLP-Findings 2020

Several clustering frameworks with interactive (semi-supervised) queries have been studied in the past. Recently, clustering with same-cluster queries has become popular. An algorithm in this setting has access to an oracle with full knowledge of an optimal clustering, and the algorithm can ask the oracle queries of the form, "Does the optimal clustering put vertices u and v in the same cluster?" Due to its simplicity, this querying model can easily be implemented in real crowd-sourcing platforms and has attracted a lot of recent work. In this paper, we study the popular correlation clustering problem (Bansal et al., 2002) under the same-cluster querying framework. Given a complete graph G=(V,E) with positive and negative edge labels, correlation clustering objective aims to compute a graph clustering that minimizes the total number of disagreements, that is the negative intra-cluster edges and positive inter-cluster edges. In a recent work, Ailon et al. (2018b) provided an approximation algorithm for correlation clustering that approximates the correlation clustering objective within (1+epsilon) with O((k^{14} log{n} log{k})/epsilon^6) queries when the number of clusters, k, is fixed. For many applications, k is not fixed and can grow with |V|. Moreover, the dependency of k^14 on query complexity renders the algorithm impractical even for datasets with small values of k. In this paper, we take a different approach. Let C_{OPT} be the number of disagreements made by the optimal clustering. We present algorithms for correlation clustering whose error and query bounds are parameterized by C_{OPT} rather than by the number of clusters. Indeed, a good clustering must have small C_{OPT}. Specifically, we present an efficient algorithm that recovers an exact optimal clustering using at most 2C_{OPT} queries and an efficient algorithm that outputs a 2-approximation using at most C_{OPT} queries. In addition, we show under a plausible complexity assumption, there does not e

Several clustering frameworks with interactive (semi-supervised) queries have been studied in the past. Recently, clustering with same-cluster queries has become popular. An algorithm in this setting has access to an oracle with full knowledge of an optimal clustering, and the algorithm can ask the oracle queries of the form, "Does the optimal clustering put vertices u and v in the same cluster?" Due to its simplicity, this querying model can easily be implemented in real crowd-sourcing platforms and has attracted a lot of recent work. In this paper, we study the popular correlation clustering problem (Bansal et al., 2002) under the same-cluster querying framework. Given a complete graph G=(V,E) with positive and negative edge labels, correlation clustering objective aims to compute a graph clustering that minimizes the total number of disagreements, that is the negative intra-cluster edges and positive inter-cluster edges. In a recent work, Ailon et al. (2018b) provided an approximation algorithm for correlation clustering that approximates the correlation clustering objective within (1+epsilon) with O((k^{14} log{n} log{k})/epsilon^6) queries when the number of clusters, k, is fixed. For many applications, k is not fixed and can grow with |V|. Moreover, the dependency of k^14 on query complexity renders the algorithm impractical even for datasets with small values of k. In this paper, we take a different approach. Let C_{OPT} be the number of disagreements made by the optimal clustering. We present algorithms for correlation clustering whose error and query bounds are parameterized by C_{OPT} rather than by the number of clusters. Indeed, a good clustering must have small C_{OPT}. Specifically, we present an efficient algorithm that recovers an exact optimal clustering using at most 2C_{OPT} queries and an efficient algorithm that outputs a 2-approximation using at most C_{OPT} queries. In addition, we show under a plausible complexity assumption, there does not e

Neural NLP models are increasingly accurate but are imperfect and opaque---they break in counterintuitive ways and leave end users puzzled at their behavior. Model interpretation methods ameliorate this opacity by providing explanations for specific model predictions. Unfortunately, existing interpretation codebases make it difficult to apply these methods to new models and tasks, which hinders adoption for practitioners and burdens interpretability researchers. We introduce AllenNLP Interpret, a flexible framework for interpreting NLP models. The toolkit provides interpretation primitives (e.g., input gradients) for any AllenNLP model and task, a suite of built-in interpretation methods, and a library of front-end visualization components. We demonstrate the toolkit's flexibility and utility by implementing live demos for five interpretation methods (e.g., saliency maps and adversarial attacks) on a variety of models and tasks (e.g., masked language modeling using BERT and reading comprehension using BiDAF). These demos, alongside our code and tutorials, are available at https://allennlp.org/interpret ., Comment: EMNLP 2019 Demo

Determining temporal relations (e.g., before or after) between events has been a challenging natural language understanding task, partly due to the difficulty to generate large amounts of high-quality training data. Consequently, neural approaches have not been widely used on it, or showed only moderate improvements. This paper proposes a new neural system that achieves about 10% absolute improvement in accuracy over the previous best system (25% error reduction) on two benchmark datasets. The proposed system is trained on the state-of-the-art MATRES dataset and applies contextualized word embeddings, a Siamese encoder of a temporal common sense knowledge base, and global inference via integer linear programming (ILP). We suggest that the new approach could serve as a strong baseline for future research in this area., Comment: This short paper is accepted to EMNLP 2019; appendix included

Several clustering frameworks with interactive (semi-supervised) queries have been studied in the past. Recently, clustering with same-cluster queries has become popular. An algorithm in this setting has access to an oracle with full knowledge of an optimal clustering, and the algorithm can ask the oracle queries of the form, "Does the optimal clustering put vertices $ u $ and $ v $ in the same cluster?" Due to its simplicity, this querying model can easily be implemented in real crowd-sourcing platforms and has attracted a lot of recent work. In this paper, we study the popular correlation clustering problem (Bansal et al., 2002) under this framework. Given a complete graph $G=(V,E)$ with positive and negative edge labels, correlation clustering objective aims to compute a graph clustering that minimizes the total number of disagreements, that is the negative intra-cluster edges and positive inter-cluster edges. Let $ C_{OPT} $ be the number of disagreements made by the optimal clustering. We present algorithms for correlation clustering whose error and query bounds are parameterized by $C_{OPT}$ rather than by the number of clusters. Indeed, a good clustering must have small $C_{OPT}$. Specifically, we present an efficient algorithm that recovers an exact optimal clustering using at most $2C_{OPT} $ queries and an efficient algorithm that outputs a $2$-approximation using at most $C_{OPT} $ queries. In addition, we show under a plausible complexity assumption, there does not exist any polynomial time algorithm that has an approximation ratio better than $1+\alpha$ for an absolute constant $\alpha >0$ with $o(C_{OPT})$ queries. We extensively evaluate our methods on several synthetic and real-world datasets using real crowd-sourced oracles. Moreover, we compare our approach against several known correlation clustering algorithms., Comment: ESA 2019

In order for coreference resolution systems to be useful in practice, they must be able to generalize to new text. In this work, we demonstrate that the performance of the state-of-the-art system decreases when the names of PER and GPE named entities in the CoNLL dataset are changed to names that do not occur in the training set. We use the technique of adversarial gradient-based training to retrain the state-of-the-art system and demonstrate that the retrained system achieves higher performance on the CoNLL dataset (both with and without the change of named entities) and the GAP dataset., Comment: *SEM 2019

People are often entities of interest in tasks such as search and information extraction. In these tasks, the goal is to find as much information as possible about people specified by their name. However in text, some of the references to people are by pronouns (she, his) or generic descriptions (the professor, the German chancellor). It is therefore important that coreference resolution systems are able to link these different types of mentions to the correct person name. Here, we evaluate two state of the art coreference resolution systems on the subtask of Named Person Coreference, in which we are interested in identifying a person mentioned by name, along with all other mentions of the person, by pronoun or generic noun phrase. Our analysis reveals that standard coreference metrics do not reflect adequately the requirements in this task: they do not penalize systems for not identifying any mentions by name and they reward systems even if systems find correctly mentions to the same entity but fail to link these to a proper name (she--the student---no name). We introduce new metrics for evaluating named person coreference that address these discrepancies. We present a simple rule-based named entity recognition driven system, which outperforms the current state-of-the-art systems on these task-specific metrics and performs on par with them on traditional coreference evaluations. Finally, we present similar evaluation for coreference resolution of other named entities and show that the rule-based approach is effective only for person named coreference, not other named entity types.

Thesis (M.B.A.)--Massachusetts Institute of Technology, Sloan School of Management; and, (S.M.)--Massachusetts Institute of Technology, Dept. of Mechanical Engineering; in conjunction with the Leaders for Manufacturing Program at MIT, 2008., Includes bibliographical references (p. 57)., In today's competitive environment, a compressed flow-time enables companies to present a strong value proposition especially for products with a high asset value. In a retrofitting manufacturing process the state of incoming product and customer requirements is unpredictable. This results in long flow-times from customer order to delivery of completed product. The uncertainty involved in identifying the parts forces companies to complete the engineering analysis and design before procuring parts from the supplier. The freighter conversions group at The Boeing Company is in the business of retrofitting passenger planes into cargo planes. The group is exploring ways to significantly reduce the overall conversion flow-time.This thesis presents an approach to group parts based on its reusability percentage and lead-time. The thesis then introduces a partially decoupled model where different strategies are applied to each group to reduce the overall flow-time.The analysis reveals a high degree of reusability in the retrofitting manufacturing process. Up to 90% of parts were used in every single conversion. When the highly variable parts are excluded, a strategy of ordering and stocking parts before the completion of engineering tasks can help reduce the flow-time with minimal risk. The results show that flow-time can be reduced from 27 to 11 with an investment of less than 1% of annual part cost in safety stock. The obsolescence risk associated with this strategy is less than 0.5% of annual part cost. The analysis further shows that there is a non-linear relationship between flowtime reduction and the investment required in safety stock and obsolescence risk. The analysis presented in this thesis is the result of work done during a 6.5 month LFM internship at The Boeing Company in Everett, Washington., by Sanjay Subramanian., S.M., M.B.A.

Thesis (M.B.A.)--Massachusetts Institute of Technology, Sloan School of Management; and, (S.M.)--Massachusetts Institute of Technology, Dept. of Mechanical Engineering; in conjunction with the Leaders for Manufacturing Program at MIT, 2008., Includes bibliographical references (p. 57)., In today's competitive environment, a compressed flow-time enables companies to present a strong value proposition especially for products with a high asset value. In a retrofitting manufacturing process the state of incoming product and customer requirements is unpredictable. This results in long flow-times from customer order to delivery of completed product. The uncertainty involved in identifying the parts forces companies to complete the engineering analysis and design before procuring parts from the supplier. The freighter conversions group at The Boeing Company is in the business of retrofitting passenger planes into cargo planes. The group is exploring ways to significantly reduce the overall conversion flow-time.This thesis presents an approach to group parts based on its reusability percentage and lead-time. The thesis then introduces a partially decoupled model where different strategies are applied to each group to reduce the overall flow-time.The analysis reveals a high degree of reusability in the retrofitting manufacturing process. Up to 90% of parts were used in every single conversion. When the highly variable parts are excluded, a strategy of ordering and stocking parts before the completion of engineering tasks can help reduce the flow-time with minimal risk. The results show that flow-time can be reduced from 27 to 11 with an investment of less than 1% of annual part cost in safety stock. The obsolescence risk associated with this strategy is less than 0.5% of annual part cost. The analysis further shows that there is a non-linear relationship between flowtime reduction and the investment required in safety stock and obsolescence risk. The analysis presented in this thesis is the result of work done during a 6.5 month LFM internship at The Boeing Company in Everett, Washington., by Sanjay Subramanian., S.M., M.B.A.