We simplify space binding by focusing on two core components, a single encoder per modality and high-quality data; enabling training state-of-the-art models on a single GPU in a few hours as opposed to multiple days. We present EBind, an Easy, data-centric, and parameter-efficient method to Bind the embedding spaces of multiple contrastive models. We demonstrate that a simple 1.8B-parameter image-text-video-audio-3D model can outperform models 4 to 17x the size. The key to achieving this is a carefully curated dataset of three complementary data sources: i) 6.7M fully-automated multimodal quintuples sourced via SOTA retrieval models, ii) 1M diverse, semi-automated triples annotated by humans as negative, partial, or positive matches, and iii) 3.4M pre-existing captioned data items. We use 13 different evaluations to demonstrate the value of each data source. Due to limitations with existing benchmarks, we further introduce the first high-quality, consensus-annotated zero-shot classification benchmark between audio and PCs. In contrast to related work, we will open-source our code, model weights, and datasets.

Contrastive Language-Image Pre-training (CLIP) [37] has emerged as a pivotal model in computer vision and multi-modal learning, achieving state-of-the-art performance at aligning visual and textual representations through contrastive learning. However, CLIP struggles with potential information misalignment in many image-text datasets and suffers from entangled representation. On the one hand, short captions for a single image in datasets like MSCOCO may describe disjoint regions in the image, leaving the model uncertain about which visual features to retain or disregard. On the other hand, directly aligning long captions with images can lead to the retention of entangled details, preventing the model from learning disentangled, atomic concepts - ultimately limiting its generalization on certain downstream tasks involving short prompts. In this paper, we establish theoretical conditions that enable flexible alignment between textual and visual representations across varying levels of granularity. Specifically, our framework ensures that a model can not only preserve cross-modal semantic information in its entirety but also disentangle visual representations to capture fine-grained textual concepts. Building on this foundation, we introduce SmartCLIP, a novel approach that identifies and aligns the most relevant visual and textual representations in a modular manner . Superior performance across various tasks demonstrates its capability to handle information misalignment and supports our identification theory.

Our method leverages text-to-audio alignment and music-structural alignment rewards during inference to encourage the generated music to be consistent with the input caption. Specifically, we introduce two objectives scores: a text-audio consistency score that measures rhythmic alignment between the generated music and the original text caption, and a harmonic-consistency score that penalizes generated music containing notes inconsistent with the key. By optimizing these alignment-based objectives during the generation process, our model produces symbolic music that is more closely tied to the input captions, thereby improving the overall quality and coherence of the generated compositions. Our approach can extend any existing autoregressive model without requiring further training or fine-tuning. We evaluate our work on top of Text2midi - an existing text-to-midi generation model, demonstrating significant improvements in both objective and subjective evaluation metrics.

This is interesting work that is pointing into the right direction, but a few aspects of this paper are a bit problematic: 1) It would have been useful (or interesting) to use a corpus that has existing text captions, and either have users re-speak the text captions, or collect additional captions. The data collections seems generally well thought-out, but why was the Places205 data set used? Prompted speech (such as collected here) is not "spontaneous", otherwise the WSJ recognizer would not have given 20 % WER (this aspect is irrelevant for the purpose of this paper, though, I think). Typically, multiple captions are being generated for a single image. Has this been done here as well? Or is there only a single caption for each image?

This paper introduces text2midi, an end-to-end model to generate MIDI files from textual descriptions. Leveraging the growing popularity of multimodal generative approaches, text2midi capitalizes on the extensive availability of textual data and the success of large language models (LLMs). Our end-to-end system harnesses the power of LLMs to generate symbolic music in the form of MIDI files. Specifically, we utilize a pretrained LLM encoder to process captions, which then condition an autoregressive transformer decoder to produce MIDI sequences that accurately reflect the provided descriptions. This intuitive and user-friendly method significantly streamlines the music creation process by allowing users to generate music pieces using text prompts. We conduct comprehensive empirical evaluations, incorporating both automated and human studies, that show our model generates MIDI files of high quality that are indeed controllable by text captions that may include music theory terms such as chords, keys, and tempo. We release the code and music samples on our demo page (https://github.com/AMAAI-Lab/Text2midi) for users to interact with text2midi.

Image tokenization, the process of transforming raw image pixels into a compact low-dimensional latent representation, has proven crucial for scalable and efficient image generation. However, mainstream image tokenization methods generally have limited compression rates, making high-resolution image generation computationally expensive. To address this challenge, we propose to leverage language for efficient image tokenization, and we call our method Text-Conditioned Image Tokenization (TexTok). TexTok is a simple yet effective tokenization framework that leverages language to provide high-level semantics. By conditioning the tokenization process on descriptive text captions, TexTok allows the tokenization process to focus on encoding fine-grained visual details into latent tokens, leading to enhanced reconstruction quality and higher compression rates. Compared to the conventional tokenizer without text conditioning, TexTok achieves average reconstruction FID improvements of 29.2% and 48.1% on ImageNet-256 and -512 benchmarks respectively, across varying numbers of tokens. These tokenization improvements consistently translate to 16.3% and 34.3% average improvements in generation FID. By simply replacing the tokenizer in Diffusion Transformer (DiT) with TexTok, our system can achieve a 93.5x inference speedup while still outperforming the original DiT using only 32 tokens on ImageNet-512. TexTok with a vanilla DiT generator achieves state-of-the-art FID scores of 1.46 and 1.62 on ImageNet-256 and -512 respectively. Furthermore, we demonstrate TexTok's superiority on the text-to-image generation task, effectively utilizing the off-the-shelf text captions in tokenization.

Continual learning (CL) adapt the deep learning scenarios with timely updated datasets. However, existing CL models suffer from the catastrophic forgetting issue, where new knowledge replaces past learning. In this paper, we propose Continual Learning with Task Specialists (CLTS) to address the issues of catastrophic forgetting and limited labelled data in real-world datasets by performing class incremental learning of the incoming stream of data. The model consists of Task Specialists (T S) and Task Predictor (T P ) with pre-trained Stable Diffusion (SD) module. Here, we introduce a new specialist to handle a new task sequence and each T S has three blocks; i) a variational autoencoder (V AE) to learn the task distribution in a low dimensional latent space, ii) a K-Means block to perform data clustering and iii) Bootstrapping Language-Image Pre-training (BLIP ) model to generate a small batch of captions from the input data. These captions are fed as input to the pre-trained stable diffusion model (SD) for the generation of task samples. The proposed model does not store any task samples for replay, instead uses generated samples from SD to train the T P module. A comparison study with four SOTA models conducted on three real-world datasets shows that the proposed model outperforms all the selected baselines

Generative models guided by text prompts are increasingly becoming more popular. However, no text-to-MIDI models currently exist, mostly due to the lack of a captioned MIDI dataset. This work aims to enable research that combines LLMs with symbolic music by presenting the first large-scale MIDI dataset with text captions that is openly available: MidiCaps. MIDI (Musical Instrument Digital Interface) files are a widely used format for encoding musical information. Their structured format captures the nuances of musical composition and has practical applications by music producers, composers, musicologists, as well as performers. Inspired by recent advancements in captioning techniques applied to various domains, we present a large-scale curated dataset of over 168k MIDI files accompanied by textual descriptions. Each MIDI caption succinctly describes the musical content, encompassing tempo, chord progression, time signature, instruments present, genre and mood; thereby facilitating multi-modal exploration and analysis. The dataset contains a mix of various genres, styles, and complexities, offering a rich source for training and evaluating models for tasks such as music information retrieval, music understanding and cross-modal translation. We provide detailed statistics about the dataset and have assessed the quality of the captions in an extensive listening study. We anticipate that this resource will stimulate further research in the intersection of music and natural language processing, fostering advancements in both fields.

Three-dimensional (3D) reconstruction from a single image is an ill-posed problem with inherent ambiguities, i.e. scale. Predicting a 3D scene from text description(s) is similarly ill-posed, i.e. spatial arrangements of objects described. We investigate the question of whether two inherently ambiguous modalities can be used in conjunction to produce metric-scaled reconstructions. To test this, we focus on monocular depth estimation, the problem of predicting a dense depth map from a single image, but with an additional text caption describing the scene. To this end, we begin by encoding the text caption as a mean and standard deviation; using a variational framework, we learn the distribution of the plausible metric reconstructions of 3D scenes corresponding to the text captions as a prior. To "select" a specific reconstruction or depth map, we encode the given image through a conditional sampler that samples from the latent space of the variational text encoder, which is then decoded to the output depth map. Our approach is trained alternatingly between the text and image branches: in one optimization step, we predict the mean and standard deviation from the text description and sample from a standard Gaussian, and in the other, we sample using a (image) conditional sampler. Once trained, we directly predict depth from the encoded text using the conditional sampler. We demonstrate our approach on indoor (NYUv2) and outdoor (KITTI) scenarios, where we show that language can consistently improve performance in both.

We present Compound Conditioned ControlNet, C3Net, a novel generative neural architecture taking conditions from multiple modalities and synthesizing multimodal contents simultaneously (e.g., image, text, audio). C3Net adapts the ControlNet architecture to jointly train and make inferences on a production-ready diffusion model and its trainable copies. Specifically, C3Net first aligns the conditions from multi-modalities to the same semantic latent space using modality-specific encoders based on contrastive training. Then, it generates multimodal outputs based on the aligned latent space, whose semantic information is combined using a ControlNet-like architecture called Control C3-UNet. Correspondingly, with this system design, our model offers an improved solution for joint-modality generation through learning and explaining multimodal conditions instead of simply taking linear interpolations on the latent space. Meanwhile, as we align conditions to a unified latent space, C3Net only requires one trainable Control C3-UNet to work on multimodal semantic information. Furthermore, our model employs unimodal pretraining on the condition alignment stage, outperforming the non-pretrained alignment even on relatively scarce training data and thus demonstrating high-quality compound condition generation. We contribute the first high-quality tri-modal validation set to validate quantitatively that C3Net outperforms or is on par with first and contemporary state-of-the-art multimodal generation. Our codes and tri-modal dataset will be released.