Many vision-language models (VLMs) that prove very effective at a range of multimodal task, build on CLIP-based vision encoders, which are known to have various limitations. We investigate the hypothesis that the strong language backbone in VLMs compensates for possibly weak visual features by contextualizing or enriching them. Using three CLIP-based VLMs, we perform controlled self-attention ablations on a carefully designed probing task. Our findings show that despite known limitations, CLIP visual representations offer ready-to-read semantic information to the language decoder. However, in scenarios of reduced contextualization in the visual representations, the language decoder can largely compensate for the deficiency and recover performance. This suggests a dynamic division of labor in VLMs and motivates future architectures that offload more visual processing to the language decoder.

Multilingual vision-language models have made significant strides in image captioning, yet they still lag behind their English counterparts due to limited multilingual training data and costly large-scale model parameterization. Retrieval-augmented generation (RAG) offers a promising alternative by conditioning caption generation on retrieved examples in the target language, reducing the need for extensive multilingual training. However, multilingual RAG captioning models often depend on retrieved captions translated from English, which can introduce mismatches and linguistic biases relative to the source language. We introduce CONCAP, a multilingual image captioning model that integrates retrieved captions with image-specific concepts, enhancing the contextualization of the input image and grounding the captioning process across different languages. Experiments on the XM3600 dataset indicate that CONCAP enables strong performance on low- and mid-resource languages, with highly reduced data requirements. Our findings highlight the effectiveness of concept-aware retrieval augmentation in bridging multilingual performance gaps.

Vision-language Models (VLMs) have emerged as general-purpose tools for addressing a variety of complex computer vision problems. Such models have been shown to be highly capable, but, at the same time, lacking some basic visual understanding skills. In this paper, we set out to understand the limitations of SoTA VLMs on fundamental visual tasks by constructing a series of tests that probe which components of design, specifically, may be lacking. Importantly, we go significantly beyond the current benchmarks, which simply measure the final performance of VLM response, by also comparing and contrasting it to the performance of probes trained directly on features obtained from the visual encoder, intermediate vision-language projection and LLM-decoder output. In doing so, we uncover shortcomings in VLMs and make a number of important observations about their capabilities, robustness and how they process visual information. We hope our insights will guide progress in further improving VLMs.

Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding for downstream multi-modal tasks. Despite their success, LVLMs still suffer from generating hallucinations in complex generation tasks, leading to inconsistencies between visual inputs and generated content. To address this issue, some approaches have introduced inference-time interventions, such as contrastive decoding and attention rectification, to reduce overreliance on language priors. However, these approaches overlook hallucinations stemming from spurious inter-modality correlations. In this paper, we propose an Inter-Modality Correlation Calibration Decoding (IMCCD) method to mitigate hallucinations in LVLMs in a training-free manner. In this method, we design a Cross-Modal Value-Enhanced Decoding(CMVED) module to alleviate hallucination by a novel contrastive decoding mechanism. During the estimation of distorted distribution, CMVED masks the value vectors associated with significant cross-modal attention weights, which address both uni-modality overreliance and misleading inter-modality correlations. Additionally, a Content-Driven Attention Refinement(CDAR) module refines cross-modal attention weights, guiding LVLMs to focus on important visual content. Experimental results on diverse hallucination benchmarks validate the superiority of our method over existing state-of-the-art techniques in reducing hallucinations in LVLM text generation. Our code will be available at https://github.com/lijm48/IMCCD.

Human-friendly natural language has been explored for tasks such as driving explanation and 3D captioning. However, previous works primarily focused on the paradigm of declarative interpretability, where the natural language interpretations are not grounded in the intermediate outputs of AD systems, making the interpretations only declarative. In contrast, aligned interpretability establishes a connection between language and the intermediate outputs of AD systems. Here we introduce Hint-AD, an integrated AD-language system that generates language aligned with the holistic perceptionprediction-planning outputs of the AD model. By incorporating the intermediate outputs and a holistic token mixer sub-network for effective feature adaptation, Hint-AD achieves desirable accuracy, achieving state-of-the-art results in driving language tasks including driving explanation, 3D dense captioning, and command prediction. To facilitate further study on driving explanation task on nuScenes, we also introduce a human-labeled dataset, Nu-X.

Music tagging is a task to predict the tags of music recordings. However, previous music tagging research primarily focuses on close-set music tagging tasks which can not be generalized to new tags. In this work, we propose a zero-shot music tagging system modeled by a joint music and language attention (JMLA) model to address the open-set music tagging problem. The JMLA model consists of an audio encoder modeled by a pretrained masked autoencoder and a decoder modeled by a Falcon7B. We introduce preceiver resampler to convert arbitrary length audio into fixed length embeddings. We introduce dense attention connections between encoder and decoder layers to improve the information flow between the encoder and decoder layers. We collect a large-scale music and description dataset from the internet. We propose to use ChatGPT to convert the raw descriptions into formalized and diverse descriptions to train the JMLA models. Our proposed JMLA system achieves a zero-shot audio tagging accuracy of $ 64.82\% $ on the GTZAN dataset, outperforming previous zero-shot systems and achieves comparable results to previous systems on the FMA and the MagnaTagATune datasets.

We present RECAP (REtrieval-Augmented Audio CAPtioning), a novel and effective audio captioning system that generates captions conditioned on an input audio and other captions similar to the audio retrieved from a datastore. Additionally, our proposed method can transfer to any domain without the need for any additional fine-tuning. To generate a caption for an audio sample, we leverage an audio-text model CLAP to retrieve captions similar to it from a replaceable datastore, which are then used to construct a prompt. Next, we feed this prompt to a GPT-2 decoder and introduce cross-attention layers between the CLAP encoder and GPT-2 to condition the audio for caption generation. Experiments on two benchmark datasets, Clotho and AudioCaps, show that RECAP achieves competitive performance in in-domain settings and significant improvements in out-of-domain settings. Additionally, due to its capability to exploit a large text-captions-only datastore in a \textit{training-free} fashion, RECAP shows unique capabilities of captioning novel audio events never seen during training and compositional audios with multiple events. To promote research in this space, we also release 150,000+ new weakly labeled captions for AudioSet, AudioCaps, and Clotho.

Large language models (LLMs) have demonstrated significant universal capabilities as few/zero-shot learners in various tasks due to their pre-training on vast amounts of text data, as exemplified by GPT-3, which boosted to InstrctGPT and ChatGPT, effectively following natural language instructions to accomplish real-world tasks. In this paper, we propose to introduce instruction tuning into multi-modal models, motivated by the Flamingo model's upstream interleaved format pretraining dataset. We adopt a similar approach to construct our MultI-Modal In-Context Instruction Tuning (MIMIC-IT) dataset. We then introduce Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following ability and in-context learning. We also optimize OpenFlamingo's implementation for researchers, democratizing the required training resources from 1$\times$ A100 GPU to 4$\times$ RTX-3090 GPUs, and integrate both OpenFlamingo and Otter into Huggingface Transformers for more researchers to incorporate the models into their customized training and inference pipelines.

Image Captioning is a traditional vision-and-language task that aims to generate the language description of an image. Recent studies focus on scaling up the model size and the number of training data, which significantly increase the cost of model training. Different to these heavy-cost models, we introduce a lightweight image captioning framework (I-Tuning), which contains a small number of trainable parameters. We design a novel I-Tuning cross-attention module to connect the non-trainable pre-trained language decoder GPT2 and vision encoder CLIP-ViT. Since most parameters are not required to be updated during training, our framework is lightweight and fast. Experimental results conducted on three image captioning benchmarks reveal that our framework achieves comparable or better performance than the large-scale baseline systems. But our models contain up to 10 times fewer trainable parameters and require much fewer data for training compared with state-of-the-art baselines.

Researchers demonstrate an AI system that can reconstruct semantic content in the form of text from fMRI data. A brain-computer interface that reconstructs language would have numerous applications in science, medicine, and industry. Invasive methods using recordings from surgically implanted electrodes show that it is possible to reconstruct language for simple brain control. But these interventions remain dangerous, even though companies like Elon Musk's Neuralink are working on methods to make such interventions as harmless as possible and without consequential damage. Non-invasive language decoders, however, could become commonplace and help people in the future to control technical devices by thought, for example.