Target-oriented grasping in unstructured scenes with language control is essential for intelligent robot arm grasping. The ability for the robot arm to understand the human language and execute corresponding grasping actions is a pivotal challenge. In this paper, we propose a combination model called QwenGrasp which combines a large vision-language model with a 6-DoF grasp neural network. QwenGrasp is able to conduct a 6-DoF grasping task on the target object with textual language instruction. We design a complete experiment with six-dimension instructions to test the QwenGrasp when facing with different cases. The results show that QwenGrasp has a superior ability to comprehend the human intention. Even in the face of vague instructions with descriptive words or instructions with direction information, the target object can be grasped accurately. When QwenGrasp accepts the instruction which is not feasible or not relevant to the grasping task, our approach has the ability to suspend the task execution and provide a proper feedback to humans, improving the safety. In conclusion, with the great power of large vision-language model, QwenGrasp can be applied in the open language environment to conduct the target-oriented grasping task with freely input instructions.
Text is ubiquitous in our visual world, conveying crucial information, such as in documents, websites, and everyday photographs. In this work, we propose UReader, a first exploration of universal OCR-free visually-situated language understanding based on the Multimodal Large Language Model (MLLM). By leveraging the shallow text recognition ability of the MLLM, we only finetuned 1.2% parameters and the training cost is much lower than previous work following domain-specific pretraining and finetuning paradigms. Concretely, UReader is jointly finetuned on a wide range of Visually-situated Language Understanding tasks via a unified instruction format. To enhance the visual text and semantic understanding, we further apply two auxiliary tasks with the same format, namely text reading and key points generation tasks. We design a shape-adaptive cropping module before the encoder-decoder architecture of MLLM to leverage the frozen low-resolution vision encoder for processing high-resolution images. Without downstream finetuning, our single model achieves state-of-the-art ocr-free performance in 8 out of 10 visually-situated language understanding tasks, across 5 domains: documents, tables, charts, natural images, and webpage screenshots. Codes and instruction-tuning datasets will be released.
Cameras and LiDARs are both important sensors for autonomous driving, playing critical roles for 3D object detection. Camera-LiDAR Fusion has been a prevalent solution for robust and accurate autonomous driving perception. In contrast to the vast majority of existing arts that focus on how to improve the performance of 3D target detection through cross-modal schemes, deep learning algorithms, and training tricks, we devote attention to the impact of sensor configurations on the performance of learning-based methods. To achieve this, we propose a unified information-theoretic surrogate metric for camera and LiDAR evaluation based on the proposed sensor perception model. We also design an accelerated high-quality framework for data acquisition, model training, and performance evaluation that functions with the CARLA simulator. To show the correlation between detection performance and our surrogate metrics, We conduct experiments using several camera-LiDAR placements and parameters inspired by self-driving companies and research institutions. Extensive experimental results of representative algorithms on NuScenes dataset validate the effectiveness of our surrogate metric, demonstrating that sensor configurations significantly impact point-cloud-image fusion based detection models, which contribute up to 30% discrepancy in terms of average precision.
Retrieval-augmented language models (RALMs) improve performance by accessing long-tail and up-to-date knowledge from external data stores, but are challenging to build. Existing approaches require either expensive retrieval-specific modifications to LM pre-training or use post-hoc integration of the data store that leads to suboptimal performance. We introduce Retrieval-Augmented Dual Instruction Tuning (RA-DIT), a lightweight fine-tuning methodology that provides a third option by retrofitting any LLM with retrieval capabilities. Our approach operates in two distinct fine-tuning steps: (1) one updates a pre-trained LM to better use retrieved information, while (2) the other updates the retriever to return more relevant results, as preferred by the LM. By fine-tuning over tasks that require both knowledge utilization and contextual awareness, we demonstrate that each stage yields significant performance improvements, and using both leads to additional gains. Our best model, RA-DIT 65B, achieves state-of-the-art performance across a range of knowledge-intensive zero- and few-shot learning benchmarks, significantly outperforming existing in-context RALM approaches by up to +8.9% in 0-shot setting and +1.4% in 5-shot setting on average.
The problem of audio-to-text alignment has seen significant amount of research using complete supervision during training. However, this is typically not in the context of long audio recordings wherein the text being queried does not appear verbatim within the audio file. This work is a collaboration with a non-governmental organization called CARE India that collects long audio health surveys from young mothers residing in rural parts of Bihar, India. Given a question drawn from a questionnaire that is used to guide these surveys, we aim to locate where the question is asked within a long audio recording. This is of great value to African and Asian organizations that would otherwise have to painstakingly go through long and noisy audio recordings to locate questions (and answers) of interest. Our proposed framework, INDENT, uses a cross-attention-based model and prior information on the temporal ordering of sentences to learn speech embeddings that capture the semantics of the underlying spoken text. These learnt embeddings are used to retrieve the corresponding audio segment based on text queries at inference time. We empirically demonstrate the significant effectiveness (improvement in R-avg of about 3%) of our model over those obtained using text-based heuristics. We also show how noisy ASR, generated using state-of-the-art ASR models for Indian languages, yields better results when used in place of speech. INDENT, trained only on Hindi data is able to cater to all languages supported by the (semantically) shared text space. We illustrate this empirically on 11 Indic languages.
Generative Adversarial Networks (GANs) can synthesize realistic images, with the learned latent space shown to encode rich semantic information with various interpretable directions. However, due to the unstructured nature of the learned latent space, it inherits the bias from the training data where specific groups of visual attributes that are not causally related tend to appear together, a phenomenon also known as spurious correlations, e.g., age and eyeglasses or women and lipsticks. Consequently, the learned distribution often lacks the proper modelling of the missing examples. The interpolation following editing directions for one attribute could result in entangled changes with other attributes. To address this problem, previous works typically adjust the learned directions to minimize the changes in other attributes, yet they still fail on strongly correlated features. In this work, we study the entanglement issue in both the training data and the learned latent space for the StyleGAN2-FFHQ model. We propose a novel framework SC$^2$GAN that achieves disentanglement by re-projecting low-density latent code samples in the original latent space and correcting the editing directions based on both the high-density and low-density regions. By leveraging the original meaningful directions and semantic region-specific layers, our framework interpolates the original latent codes to generate images with attribute combination that appears infrequently, then inverts these samples back to the original latent space. We apply our framework to pre-existing methods that learn meaningful latent directions and showcase its strong capability to disentangle the attributes with small amounts of low-density region samples added.
Due to the rise of user-generated content, social media is increasingly adopted as a channel to deliver customer service. Given the public character of these online platforms, the automatic detection of emotions forms an important application in monitoring customer satisfaction and preventing negative word-of-mouth. This paper introduces EmoTwiCS, a corpus of 9,489 Dutch customer service dialogues on Twitter that are annotated for emotion trajectories. In our business-oriented corpus, we view emotions as dynamic attributes of the customer that can change at each utterance of the conversation. The term `emotion trajectory' refers therefore not only to the fine-grained emotions experienced by customers (annotated with 28 labels and valence-arousal-dominance scores), but also to the event happening prior to the conversation and the responses made by the human operator (both annotated with 8 categories). Inter-annotator agreement (IAA) scores on the resulting dataset are substantial and comparable with related research, underscoring its high quality. Given the interplay between the different layers of annotated information, we perform several in-depth analyses to investigate (i) static emotions in isolated tweets, (ii) dynamic emotions and their shifts in trajectory, and (iii) the role of causes and response strategies in emotion trajectories. We conclude by listing the advantages and limitations of our dataset, after which we give some suggestions on the different types of predictive modelling tasks and open research questions to which EmoTwiCS can be applied. The dataset is available upon request and will be made publicly available upon acceptance of the paper.
The task of assigning diagnostic ICD codes to patient hospital admissions is typically performed by expert human coders. Efforts towards automated ICD coding are dominated by supervised deep learning models. However, difficulties in learning to predict the large number of rare codes remain a barrier to adoption in clinical practice. In this work, we leverage off-the-shelf pre-trained generative large language models (LLMs) to develop a practical solution that is suitable for zero-shot and few-shot code assignment. Unsupervised pre-training alone does not guarantee precise knowledge of the ICD ontology and specialist clinical coding task, therefore we frame the task as information extraction, providing a description of each coded concept and asking the model to retrieve related mentions. For efficiency, rather than iterating over all codes, we leverage the hierarchical nature of the ICD ontology to sparsely search for relevant codes. Then, in a second stage, which we term 'meta-refinement', we utilise GPT-4 to select a subset of the relevant labels as predictions. We validate our method using Llama-2, GPT-3.5 and GPT-4 on the CodiEsp dataset of ICD-coded clinical case documents. Our tree-search method achieves state-of-the-art performance on rarer classes, achieving the best macro-F1 of 0.225, whilst achieving slightly lower micro-F1 of 0.157, compared to 0.216 and 0.219 respectively from PLM-ICD. To the best of our knowledge, this is the first method for automated ICD coding requiring no task-specific learning.
Optical communication is the standard for high-bandwidth information transfer in today's digital age. The increasing demand for bandwidth has led to the maturation of coherent transceivers that use phase- and amplitude-modulated optical signals to encode more bits of information per transmitted pulse. Such encoding schemes achieve higher information density, but also require more complicated receivers to discriminate the signaling states. In fact, achieving the ultimate limit of optical communication capacity, especially in the low light regime, requires coherent joint detection of multiple pulses. Despite their superiority, such joint detection receivers are not in widespread use because of the difficulty of constructing them in the optical domain. In this work we describe how optomechanical transduction of phase information from coherent optical pulses to superconducting qubit states followed by the execution of trained short-depth variational quantum circuits can perform joint detection of communication codewords with error probabilities that surpass all classical, individual pulse detection receivers. Importantly, we utilize a model of optomechanical transduction that captures non-idealities such as thermal noise and loss in order to understand the transduction performance necessary to achieve a quantum advantage with such a scheme. We also execute the trained variational circuits on an IBM-Q device with the modeled transduced states as input to demonstrate that a quantum advantage is possible even with current levels of quantum computing hardware noise.
Charts are common in literature across different scientific fields, conveying rich information easily accessible to readers. Current chart-related tasks focus on either chart perception which refers to extracting information from the visual charts, or performing reasoning given the extracted data, e.g. in a tabular form. In this paper, we aim to establish a unified and label-efficient learning paradigm for joint perception and reasoning tasks, which can be generally applicable to different downstream tasks, beyond the question-answering task as specifically studied in peer works. Specifically, StructChart first reformulates the chart information from the popular tubular form (specifically linearized CSV) to the proposed Structured Triplet Representations (STR), which is more friendly for reducing the task gap between chart perception and reasoning due to the employed structured information extraction for charts. We then propose a Structuring Chart-oriented Representation Metric (SCRM) to quantitatively evaluate the performance for the chart perception task. To enrich the dataset for training, we further explore the possibility of leveraging the Large Language Model (LLM), enhancing the chart diversity in terms of both chart visual style and its statistical information. Extensive experiments are conducted on various chart-related tasks, demonstrating the effectiveness and promising potential for a unified chart perception-reasoning paradigm to push the frontier of chart understanding.