While diffusion models are powerful in generating high-quality, diverse synthetic data for object-centric tasks, existing methods struggle with scene-aware tasks such as Visual Question Answering (VQA) and Human-Object Interaction (HOI) Reasoning, where it is critical to preserve scene attributes in generated images consistent with a multimodal context, i.e. a reference image with accompanying text guidance query. To address this, we introduce **Hummingbird**, the first diffusion-based image generator which, given a multimodal context, generates highly diverse images w.r.t. the reference image while ensuring high fidelity by accurately preserving scene attributes, such as object interactions and spatial relationships from the text guidance. Hummingbird employs a novel Multimodal Context Evaluator that simultaneously optimizes our formulated Global Semantic and Fine-grained Consistency Rewards to ensure generated images preserve the scene attributes of reference images in relation to the text guidance while maintaining diversity. As the first model to address the task of maintaining both diversity and fidelity given a multimodal context, we introduce a new benchmark formulation incorporating MME Perception and Bongard HOI datasets. Benchmark experiments show Hummingbird outperforms all existing methods by achieving superior fidelity while maintaining diversity, validating Hummingbird's potential as a robust multimodal context-aligned image generator in complex visual tasks. Project page: https://roar-ai.github.io/hummingbird

Giovanni Monea, Maxime Peyrard, Martin Josifoski, Vishrav Chaudhary, Jason Eisner, Emre Kiciman, Hamid Palangi, Barun Patra, Robert West. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

One of the prominent issues stifling the current generation of large language models is their limited context length. Recent proprietary models such as GPT-4 and Claude 2 have introduced longer context lengths, 8k/32k and 100k, respectively; however, despite the efforts in the community, most common models, such as LLama-2, have a context length of 4k or less. Unlimiformer (Bertsch et al., 2023) is a recently popular vector-retrieval augmentation method that offloads cross-attention computations to a kNN index. However, its main limitation is incompatibility with decoder-only transformers out of the box. In this work, we explore practical considerations of adapting Unlimiformer to decoder-only transformers and introduce a series of modifications to overcome this limitation. Moreover, we expand the original experimental setup on summarization to include a new task (i.e., free-form Q&A) and an instruction-tuned model (i.e., a custom 6.7B GPT model). Our results showcase the effectiveness of these modifications on summarization, performing on par with a model with 2x the context length. Moreover, we discuss limitations and future directions for free-form Q&A and instruction-tuned models.

Barun Patra, Saksham Singhal, Shaohan Huang, Zewen Chi, Li Dong, Furu Wei, Vishrav Chaudhary, Xia Song. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Yutao Sun, Li Dong, Barun Patra, Shuming Ma, Shaohan Huang, Alon Benhaim, Vishrav Chaudhary, Xia Song, Furu Wei. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

A big convergence of model architectures across language, vision, speech, and multimodal is emerging. However, under the same name ”Transformers”, the above areas use different implementations for better performance, e.g., Post-LayerNorm for BERT, and Pre-LayerNorm for GPT and vision Transformers. We call for the development of Foundation Transformer for true general-purpose modeling, which serves as a go-to architecture for various tasks and modalities with guaranteed training stability. In this work, we introduce a Transformer variant, named Magneto, to fulfill the goal. Specifically, we propose Sub-LayerNorm for good expressivity, and the initialization strategy theoretically derived from DeepNet for stable scaling up. Extensive experiments demonstrate its superior performance and better stability than the de facto Transformer variants designed for various applications, including language modeling (i.e., BERT, and GPT), machine translation, vision pretraining (i.e., BEiT), speech recognition, and multimodal pretraining (i.e., BEiT-3).

A big convergence of language, multimodal perception, action, and world modeling is a key step toward artificial general intelligence. In this work, we introduce KOSMOS-1, a Multimodal Large Language Model (MLLM) that can perceive general modalities, learn in context (i.e., few-shot), and follow instructions (i.e., zero-shot). Specifically, we train KOSMOS-1 from scratch on web-scale multi-modal corpora, including arbitrarily interleaved text and images, image-caption pairs, and text data. We evaluate various settings, including zero-shot, few-shot, and multimodal chain-of-thought prompting, on a wide range of tasks without any gradient updates or finetuning. Experimental results show that KOSMOS-1 achieves impressive performance on (i) language understanding, generation, and even OCR-free NLP (directly fed with document images), (ii) perception-language tasks, including multimodal dialogue, image captioning, visual question answering, and (iii) vision tasks, such as image recognition with descriptions (specifying classification via text instructions). We also show that MLLMs can benefit from cross-modal transfer, i.e., transfer knowledge from language to multimodal, and from multimodal to language. In addition, we introduce a dataset of Raven IQ test, which diagnoses the nonverbal reasoning capability of MLLMs.

Maxime Peyrard, Sarvjeet Ghotra, Martin Josifoski, Vidhan Agarwal, Barun Patra, Dean Carignan, Emre Kiciman, Saurabh Tiwary, Robert West. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.

Sparse mixture of experts provides larger model capacity while requiring a constant computational overhead. It employs the routing mechanism to distribute input tokens to the best-matched experts according to their hidden representations. However, learning such a routing mechanism encourages token clustering around expert centroids, implying a trend toward representation collapse. In this work, we propose to estimate the routing scores between tokens and experts on a low-dimensional hypersphere. We conduct extensive experiments on cross-lingual language model pre-training and fine-tuning on downstream tasks. Experimental results across seven multilingual benchmarks show that our method achieves consistent gains. We also present a comprehensive analysis on the representation and routing behaviors of our models. Our method alleviates the representation collapse issue and achieves more consistent routing than the baseline mixture-of-experts methods.

Abstract We present the novel task of understanding multi-sentenceentity-seekingquestions (MSEQs), that is, the questions that may be expressed in multiple sentences, and that expect one or more entities as an answer. We formulate the problem of understanding MSEQs as a semantic labeling task over an open representation that makes minimal assumptions about schema or ontology-specific semantic vocabulary. At the core of our model, we use a BiLSTM (bidirectional LSTM) conditional random field (CRF), and to overcome the challenges of operating with low training data, we supplement it by using BERT embeddings, hand-designed features, as well as hard and soft constraints spanning multiple sentences. We find that this results in a 12–15 points gain over a vanilla BiLSTM CRF. We demonstrate the strengths of our work using the novel task of answering real-world entity-seeking questions from the tourism domain. The use of our labels helps answer 36% more questions with 35% more (relative) accuracy as compared to baselines. We also demonstrate how our framework can rapidly enable the parsing of MSEQs in an entirely new domain with small amounts of training data and little change in the semantic representation.

State of the art research for date-time 1 entity extraction from text is task agnostic.Consequently, while the methods proposed in literature perform well for generic date-time extraction from texts, they don't fare as well on task specific date-time entity extraction where only a subset of the date-time entities present in the text are pertinent to solving the task.Furthermore, some tasks require identifying negation constraints associated with the date-time entities to correctly reason over time.We showcase a novel model for extracting task-specific date-time entities along with their negation constraints.We show the efficacy of our method on the task of date-time understanding in the context of scheduling meetings for an email-based digital AI scheduling assistant.Our method achieves an absolute gain of 19% f-score points compared to baseline methods in detecting the date-time entities relevant to scheduling meetings and a 4% improvement over baseline methods for detecting negation constraints over date-time entities.

Recent work on bilingual lexicon induction (BLI) has frequently depended either on aligned bilingual lexicons or on distribution matching, often with an assumption about the isometry of the two spaces.We propose a technique to quantitatively estimate this assumption of the isometry between two embedding spaces and empirically show that this assumption weakens as the languages in question become increasingly etymologically distant.We then propose Bilingual Lexicon Induction with Semi-Supervision (BLISS) -a semi-supervised approach that relaxes the isometric assumption while leveraging both limited aligned bilingual lexicons and a larger set of unaligned word embeddings, as well as a novel hubness filtering technique.Our proposed method obtains state of the art results on 15 of 18 language pairs on the MUSE dataset, and does particularly well when the embedding spaces don't appear to be isometric.In addition, we also show that adding supervision stabilizes the learning procedure, and is effective even with minimal supervision.⇤

Barun Patra, Joel Ruben Antony Moniz. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.