Public Code Review (PCR) can be implemented through a Software Question Answering (SQA) community, which facilitates high knowledge dissemination. Current methods mainly focus on the reviewer's perspective, including finding a capable reviewer, predicting comment quality, and recommending/generating review comments. Our intuition is that satisfying review necessity requests can increase their visibility, which in turn is a prerequisite for better review responses. To this end, we propose a unified framework called UniPCR to complete developer-based request quality assurance (i.e., predicting request necessity and recommending tags subtask) under a Masked Language Model (MLM). Specifically, we reformulate both subtasks via 1) text prompt tuning, which converts two subtasks into MLM by constructing prompt templates using hard prompt; 2) code prefix tuning, which optimizes a small segment of generated continuous vectors as the prefix of the code representation using soft prompt. Experimental results on the Public Code Review dataset for the time span 2011-2022 demonstrate that our UniPCR framework adapts to the two subtasks and outperforms comparable accuracy-based results with state-of-the-art methods for request quality assurance. These conclusions highlight the effectiveness of our unified framework from the developer's perspective in public code review.
Evaluating and Rethinking the current landscape of Large Multimodal Models (LMMs), we observe that widely-used visual-language projection approaches (e.g., Q-former or MLP) focus on the alignment of image-text descriptions yet ignore the visual knowledge-dimension alignment, i.e., connecting visuals to their relevant knowledge. Visual knowledge plays a significant role in analyzing, inferring, and interpreting information from visuals, helping improve the accuracy of answers to knowledge-based visual questions. In this paper, we mainly explore improving LMMs with visual-language knowledge alignment, especially aimed at challenging knowledge-based visual question answering (VQA). To this end, we present a Cognitive Visual-Language Mapper (CVLM), which contains a pretrained Visual Knowledge Aligner (VKA) and a Fine-grained Knowledge Adapter (FKA) used in the multimodal instruction tuning stage. Specifically, we design the VKA based on the interaction between a small language model and a visual encoder, training it on collected image-knowledge pairs to achieve visual knowledge acquisition and projection. FKA is employed to distill the fine-grained visual knowledge of an image and inject it into Large Language Models (LLMs). We conduct extensive experiments on knowledge-based VQA benchmarks and experimental results show that CVLM significantly improves the performance of LMMs on knowledge-based VQA (average gain by 5.0%). Ablation studies also verify the effectiveness of VKA and FKA, respectively.
Long video understanding is a significant and ongoing challenge in the intersection of multimedia and artificial intelligence. Employing large language models (LLMs) for comprehending video becomes an emerging and promising method. However, this approach incurs high computational costs due to the extensive array of video tokens, experiences reduced visual clarity as a consequence of token aggregation, and confronts challenges arising from irrelevant visual tokens while answering video-related questions. To alleviate these issues, we present an Interactive Visual Adapter (IVA) within LLMs, designed to enhance interaction with fine-grained visual elements. Specifically, we first transform long videos into temporal video tokens via leveraging a visual encoder alongside a pretrained causal transformer, then feed them into LLMs with the video instructions. Subsequently, we integrated IVA, which contains a lightweight temporal frame selector and a spatial feature interactor, within the internal blocks of LLMs to capture instruction-aware and fine-grained visual signals. Consequently, the proposed video-LLM facilitates a comprehensive understanding of long video content through appropriate long video modeling and precise visual interactions. We conducted extensive experiments on nine video understanding benchmarks and experimental results show that our interactive visual adapter significantly improves the performance of video LLMs on long video QA tasks. Ablation studies further verify the effectiveness of IVA in long and short video understandings.
The emergence of multimodal large models (MLMs) has significantly advanced the field of visual understanding, offering remarkable capabilities in the realm of visual question answering (VQA). Yet, the true challenge lies in the domain of knowledge-intensive VQA tasks, which necessitate not just recognition of visual elements, but also a deep comprehension of the visual information in conjunction with a vast repository of learned knowledge. To uncover such capabilities of MLMs, particularly the newly introduced GPT-4V, we provide an in-depth evaluation from three perspectives: 1) Commonsense Knowledge, which assesses how well models can understand visual cues and connect to general knowledge; 2) Fine-grained World Knowledge, which tests the model's skill in reasoning out specific knowledge from images, showcasing their proficiency across various specialized fields; 3) Comprehensive Knowledge with Decision-making Rationales, which examines model's capability to provide logical explanations for its inference, facilitating a deeper analysis from the interpretability perspective. Extensive experiments indicate that GPT-4V achieves SOTA performance on above three tasks. Interestingly, we find that: a) GPT-4V demonstrates enhanced reasoning and explanation when using composite images as few-shot; b) GPT-4V produces severe hallucinations when dealing with world knowledge, highlighting the future need for advancements in this research direction.
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.
The ability for robotic systems to understand human language and execute grasping actions is a pivotal challenge in the field of robotics. In target-oriented grasping, prior researches achieve matching human textual commands with images of target objects. However, these works are hard to understand complex or flexible instructions. Moreover, these works lack the capability to autonomously assess the feasibility of instructions, leading to blindly execute grasping tasks even there is no target object. In this paper, we introduce a combination model called QwenGrasp, which combines a large vision language model with a 6-DoF grasp network. By leveraging a pre-trained large vision language model, our approach is capable of working in open-world with natural human language environments, accepting complex and flexible instructions. Furthermore, the specialized grasp network ensures the effectiveness of the generated grasp pose. A series of experiments conducted in real world environment show that our method exhibits a superior ability to comprehend human intent. Additionally, when accepting erroneous instructions, our approach has the capability to suspend task execution and provide feedback to humans, improving safety.
In this paper, we measure the linear separability of hidden layer outputs to study the characteristics of deep neural networks. In particular, we first propose Minkowski difference based linear separability measures (MD-LSMs) to evaluate the linear separability degree of two points sets. Then, we demonstrate that there is a synchronicity between the linear separability degree of hidden layer outputs and the network training performance, i.e., if the updated weights can enhance the linear separability degree of hidden layer outputs, the updated network will achieve a better training performance, and vice versa. Moreover, we study the effect of activation function and network size (including width and depth) on the linear separability of hidden layers. Finally, we conduct the numerical experiments to validate our findings on some popular deep networks including multilayer perceptron (MLP), convolutional neural network (CNN), deep belief network (DBN), ResNet, VGGNet, AlexNet, vision transformer (ViT) and GoogLeNet.
The random forest (RF) algorithm has become a very popular prediction method for its great flexibility and promising accuracy. In RF, it is conventional to put equal weights on all the base learners (trees) to aggregate their predictions. However, the predictive performances of different trees within the forest can be very different due to the randomization of the embedded bootstrap sampling and feature selection. In this paper, we focus on RF for regression and propose two optimal weighting algorithms, namely the 1 Step Optimal Weighted RF (1step-WRF$_\mathrm{opt}$) and 2 Steps Optimal Weighted RF (2steps-WRF$_\mathrm{opt}$), that combine the base learners through the weights determined by weight choice criteria. Under some regularity conditions, we show that these algorithms are asymptotically optimal in the sense that the resulting squared loss and risk are asymptotically identical to those of the infeasible but best possible model averaging estimator. Numerical studies conducted on real-world data sets indicate that these algorithms outperform the equal-weight forest and two other weighted RFs proposed in existing literature in most cases.
Conditional inference on joint textual and visual clues is a multi-modal reasoning task that textual clues provide prior permutation or external knowledge, which are complementary with visual content and pivotal to deducing the correct option. Previous methods utilizing pretrained vision-language models (VLMs) have achieved impressive performances, yet they show a lack of multimodal context reasoning capability, especially for text-modal information. To address this issue, we propose a Multi-modal Context Reasoning approach, named ModCR. Compared to VLMs performing reasoning via cross modal semantic alignment, it regards the given textual abstract semantic and objective image information as the pre-context information and embeds them into the language model to perform context reasoning. Different from recent vision-aided language models used in natural language processing, ModCR incorporates the multi-view semantic alignment information between language and vision by introducing the learnable alignment prefix between image and text in the pretrained language model. This makes the language model well-suitable for such multi-modal reasoning scenario on joint textual and visual clues. We conduct extensive experiments on two corresponding data sets and experimental results show significantly improved performance (exact gain by 4.8% on PMR test set) compared to previous strong baselines. Code Link: \url{https://github.com/YunxinLi/Multimodal-Context-Reasoning}.