While various models and computational tools have been proposed for structure and property analysis of molecules, generating molecules that conform to all desired structures and properties remains a challenge. Here, we introduce a multi-constraint molecular generation large language model, TSMMG, which, akin to a student, incorporates knowledge from various small models and tools, namely, the 'teachers'. To train TSMMG, we construct a large set of text-molecule pairs by extracting molecular knowledge from these 'teachers', enabling it to generate novel molecules that conform to the descriptions through various text prompts. We experimentally show that TSMMG remarkably performs in generating molecules meeting complex, natural language-described property requirements across two-, three-, and four-constraint tasks, with an average molecular validity of over 99% and success ratio of 88.08%, 65.27%, and 61.44%, respectively. The model also exhibits adaptability through zero-shot testing, creating molecules that satisfy combinations of properties that have not been encountered. It can comprehend text inputs with various language styles, extending beyond the confines of outlined prompts, as confirmed through empirical validation. Additionally, the knowledge distillation feature of TSMMG contributes to the continuous enhancement of small models, while the innovative approach to dataset construction effectively addresses the issues of data scarcity and quality, which positions TSMMG as a promising tool in the domains of drug discovery and materials science. Code is available at https://github.com/HHW-zhou/TSMMG.
This paper addresses the escalating challenge of redundant data transmission in networks. The surge in traffic has strained backhaul links and backbone networks, prompting the exploration of caching solutions at the edge router. Existing work primarily relies on Markov Decision Processes (MDP) for caching issues, assuming fixed-time interval decisions; however, real-world scenarios involve random request arrivals, and despite the critical role of various file characteristics in determining an optimal caching policy, none of the related existing work considers all these file characteristics in forming a caching policy. In this paper, first, we formulate the caching problem using a semi-Markov Decision Process (SMDP) to accommodate the continuous-time nature of real-world scenarios allowing for caching decisions at random times upon file requests. Then, we propose a double deep Q-learning-based caching approach that comprehensively accounts for file features such as lifetime, size, and importance. Simulation results demonstrate the superior performance of our approach compared to a recent Deep Reinforcement Learning-based method. Furthermore, we extend our work to include a Transfer Learning (TL) approach to account for changes in file request rates in the SMDP framework. The proposed TL approach exhibits fast convergence, even in scenarios with increased differences in request rates between source and target domains, presenting a promising solution to the dynamic challenges of caching in real-world environments.
Trajectory prediction in traffic scenes involves accurately forecasting the behaviour of surrounding vehicles. To achieve this objective it is crucial to consider contextual information, including the driving path of vehicles, road topology, lane dividers, and traffic rules. Although studies demonstrated the potential of leveraging heterogeneous context for improving trajectory prediction, state-of-the-art deep learning approaches still rely on a limited subset of this information. This is mainly due to the limited availability of comprehensive representations. This paper presents an approach that utilizes knowledge graphs to model the diverse entities and their semantic connections within traffic scenes. Further, we present nuScenes Knowledge Graph (nSKG), a knowledge graph for the nuScenes dataset, that models explicitly all scene participants and road elements, as well as their semantic and spatial relationships. To facilitate the usage of the nSKG via graph neural networks for trajectory prediction, we provide the data in a format, ready-to-use by the PyG library. All artefacts can be found here: https://github.com/boschresearch/nuScenes_Knowledge_Graph
Edge devices equipped with computer vision must deal with vast amounts of sensory data with limited computing resources. Hence, researchers have been exploring different energy-efficient solutions such as near-sensor processing, in-sensor processing, and in-pixel processing, bringing the computation closer to the sensor. In particular, in-pixel processing embeds the computation capabilities inside the pixel array and achieves high energy efficiency by generating low-level features instead of the raw data stream from CMOS image sensors. Many different in-pixel processing techniques and approaches have been demonstrated on conventional frame-based CMOS imagers, however, the processing-in-pixel approach for neuromorphic vision sensors has not been explored so far. In this work, we for the first time, propose an asynchronous non-von-Neumann analog processing-in-pixel paradigm to perform convolution operations by integrating in-situ multi-bit multi-channel convolution inside the pixel array performing analog multiply and accumulate (MAC) operations that consume significantly less energy than their digital MAC alternative. To make this approach viable, we incorporate the circuit's non-ideality, leakage, and process variations into a novel hardware-algorithm co-design framework that leverages extensive HSpice simulations of our proposed circuit using the GF22nm FD-SOI technology node. We verified our framework on state-of-the-art neuromorphic vision sensor datasets and show that our solution consumes ~2x lower backend-processor energy while maintaining almost similar front-end (sensor) energy on the IBM DVS128-Gesture dataset than the state-of-the-art while maintaining a high test accuracy of 88.36%.
Scene Text Recognition (STR) models have achieved high performance in recent years on benchmark datasets where text images are presented with minimal noise. Traditional STR recognition pipelines take a cropped image as sole input and attempt to identify the characters present. This infrastructure can fail in instances where the input image is noisy or the text is partially obscured. This paper proposes using semantic information from the greater scene to contextualise predictions. We generate semantic vectors using object tags and fuse this information into a transformer-based architecture. The results demonstrate that our multimodal approach yields higher performance than traditional benchmark models, particularly on noisy instances.
Despite recent progress in video and language representation learning, the weak or sparse correspondence between the two modalities remains a bottleneck in the area. Most video-language models are trained via pair-level loss to predict whether a pair of video and text is aligned. However, even in paired video-text segments, only a subset of the frames are semantically relevant to the corresponding text, with the remainder representing noise; where the ratio of noisy frames is higher for longer videos. We propose FineCo (Fine-grained Contrastive Loss for Frame Sampling), an approach to better learn video and language representations with a fine-grained contrastive objective operating on video frames. It helps distil a video by selecting the frames that are semantically equivalent to the text, improving cross-modal correspondence. Building on the well established VideoCLIP model as a starting point, FineCo achieves state-of-the-art performance on YouCookII, a text-video retrieval benchmark with long videos. FineCo also achieves competitive results on text-video retrieval (MSR-VTT), and video question answering datasets (MSR-VTT QA and MSR-VTT MC) with shorter videos.
Today's high resolution, high frame rate cameras in autonomous vehicles generate a large volume of data that needs to be transferred and processed by a downstream processor or machine learning (ML) accelerator to enable intelligent computing tasks, such as multi-object detection and tracking. The massive amount of data transfer incurs significant energy, latency, and bandwidth bottlenecks, which hinders real-time processing. To mitigate this problem, we propose an algorithm-hardware co-design framework called Processing-in-Pixel-in-Memory-based object Detection and Tracking (P2M-DeTrack). P2M-DeTrack is based on a custom faster R-CNN-based model that is distributed partly inside the pixel array (front-end) and partly in a separate FPGA/ASIC (back-end). The proposed front-end in-pixel processing down-samples the input feature maps significantly with judiciously optimized strided convolution and pooling. Compared to a conventional baseline design that transfers frames of RGB pixels to the back-end, the resulting P2M-DeTrack designs reduce the data bandwidth between sensor and back-end by up to 24x. The designs also reduce the sensor and total energy (obtained from in-house circuit simulations at Globalfoundries 22nm technology node) per frame by 5.7x and 1.14x, respectively. Lastly, they reduce the sensing and total frame latency by an estimated 1.7x and 3x, respectively. We evaluate our approach on the multi-object object detection (tracking) task of the large-scale BDD100K dataset and observe only a 0.5% reduction in the mean average precision (0.8% reduction in the identification F1 score) compared to the state-of-the-art.
In traditional Visual Question Generation (VQG), most images have multiple concepts (e.g. objects and categories) for which a question could be generated, but models are trained to mimic an arbitrary choice of concept as given in their training data. This makes training difficult and also poses issues for evaluation -- multiple valid questions exist for most images but only one or a few are captured by the human references. We present Guiding Visual Question Generation - a variant of VQG which conditions the question generator on categorical information based on expectations on the type of question and the objects it should explore. We propose two variants: (i) an explicitly guided model that enables an actor (human or automated) to select which objects and categories to generate a question for; and (ii) an implicitly guided model that learns which objects and categories to condition on, based on discrete latent variables. The proposed models are evaluated on an answer-category augmented VQA dataset and our quantitative results show a substantial improvement over the current state of the art (over 9 BLEU-4 increase). Human evaluation validates that guidance helps the generation of questions that are grammatically coherent and relevant to the given image and objects.
Data augmentation is an approach that can effectively improve the performance of multimodal machine learning. This paper introduces a generative model for data augmentation by leveraging the correlations among multiple modalities. Different from conventional data augmentation approaches that apply low level operations with deterministic heuristics, our method proposes to learn an augmentation sampler that generates samples of the target modality conditioned on observed modalities in the variational auto-encoder framework. Additionally, the proposed model is able to quantify the confidence of augmented data by its generative probability, and can be jointly updated with a downstream pipeline. Experiments on Visual Question Answering tasks demonstrate the effectiveness of the proposed generative model, which is able to boost the strong UpDn-based models to the state-of-the-art performance.
Reinforcement Learning (RL) is a powerful framework to address the discrepancy between loss functions used during training and the final evaluation metrics to be used at test time. When applied to neural Machine Translation (MT), it minimises the mismatch between the cross-entropy loss and non-differentiable evaluation metrics like BLEU. However, the suitability of these metrics as reward function at training time is questionable: they tend to be sparse and biased towards the specific words used in the reference texts. We propose to address this problem by making models less reliant on such metrics in two ways: (a) with an entropy-regularised RL method that does not only maximise a reward function but also explore the action space to avoid peaky distributions; (b) with a novel RL method that explores a dynamic unsupervised reward function to balance between exploration and exploitation. We base our proposals on the Soft Actor-Critic (SAC) framework, adapting the off-policy maximum entropy model for language generation applications such as MT. We demonstrate that SAC with BLEU reward tends to overfit less to the training data and performs better on out-of-domain data. We also show that our dynamic unsupervised reward can lead to better translation of ambiguous words.