Recent advancements in autonomous driving have relied on data-driven approaches, which are widely adopted but face challenges including dataset bias, overfitting, and uninterpretability. Drawing inspiration from the knowledge-driven nature of human driving, we explore the question of how to instill similar capabilities into autonomous driving systems and summarize a paradigm that integrates an interactive environment, a driver agent, as well as a memory component to address this question. Leveraging large language models with emergent abilities, we propose the DiLu framework, which combines a Reasoning and a Reflection module to enable the system to perform decision-making based on common-sense knowledge and evolve continuously. Extensive experiments prove DiLu's capability to accumulate experience and demonstrate a significant advantage in generalization ability over reinforcement learning-based methods. Moreover, DiLu is able to directly acquire experiences from real-world datasets which highlights its potential to be deployed on practical autonomous driving systems. To the best of our knowledge, we are the first to instill knowledge-driven capability into autonomous driving systems from the perspective of how humans drive.
The revolution of artificial intelligence content generation has been rapidly accelerated with the booming text-to-image (T2I) diffusion models. Within just two years of development, it was unprecedentedly of high-quality, diversity, and creativity that the state-of-the-art models could generate. However, a prevalent limitation persists in the effective communication with these popular T2I models, such as Stable Diffusion, using natural language descriptions. This typically makes an engaging image hard to obtain without expertise in prompt engineering with complex word compositions, magic tags, and annotations. Inspired by the recently released DALLE3 - a T2I model directly built-in ChatGPT that talks human language, we revisit the existing T2I systems endeavoring to align human intent and introduce a new task - interactive text to image (iT2I), where people can interact with LLM for interleaved high-quality image generation/edit/refinement and question answering with stronger images and text correspondences using natural language. In addressing the iT2I problem, we present a simple approach that augments LLMs for iT2I with prompting techniques and off-the-shelf T2I models. We evaluate our approach for iT2I in a variety of common-used scenarios under different LLMs, e.g., ChatGPT, LLAMA, Baichuan, and InternLM. We demonstrate that our approach could be a convenient and low-cost way to introduce the iT2I ability for any existing LLMs and any text-to-image models without any training while bringing little degradation on LLMs' inherent capabilities in, e.g., question answering and code generation. We hope this work could draw broader attention and provide inspiration for boosting user experience in human-machine interactions alongside the image quality of the next-generation T2I systems.
Recent works have successfully extended large-scale text-to-image models to the video domain, producing promising results but at a high computational cost and requiring a large amount of video data. In this work, we introduce ConditionVideo, a training-free approach to text-to-video generation based on the provided condition, video, and input text, by leveraging the power of off-the-shelf text-to-image generation methods (e.g., Stable Diffusion). ConditionVideo generates realistic dynamic videos from random noise or given scene videos. Our method explicitly disentangles the motion representation into condition-guided and scenery motion components. To this end, the ConditionVideo model is designed with a UNet branch and a control branch. To improve temporal coherence, we introduce sparse bi-directional spatial-temporal attention (sBiST-Attn). The 3D control network extends the conventional 2D controlnet model, aiming to strengthen conditional generation accuracy by additionally leveraging the bi-directional frames in the temporal domain. Our method exhibits superior performance in terms of frame consistency, clip score, and conditional accuracy, outperforming other compared methods.
There is an emerging line of research on multimodal instruction tuning, and a line of benchmarks have been proposed for evaluating these models recently. Instead of evaluating the models directly, in this paper we try to evaluate the Vision-Language Instruction-Tuning (VLIT) datasets themselves and further seek the way of building a dataset for developing an all-powerful VLIT model, which we believe could also be of utility for establishing a grounded protocol for benchmarking VLIT models. For effective analysis of VLIT datasets that remains an open question, we propose a tune-cross-evaluation paradigm: tuning on one dataset and evaluating on the others in turn. For each single tune-evaluation experiment set, we define the Meta Quality (MQ) as the mean score measured by a series of caption metrics including BLEU, METEOR, and ROUGE-L to quantify the quality of a certain dataset or a sample. On this basis, to evaluate the comprehensiveness of a dataset, we develop the Dataset Quality (DQ) covering all tune-evaluation sets. To lay the foundation for building a comprehensive dataset and developing an all-powerful model for practical applications, we further define the Sample Quality (SQ) to quantify the all-sided quality of each sample. Extensive experiments validate the rationality of the proposed evaluation paradigm. Based on the holistic evaluation, we build a new dataset, REVO-LION (REfining VisiOn-Language InstructiOn tuNing), by collecting samples with higher SQ from each dataset. With only half of the full data, the model trained on REVO-LION can achieve performance comparable to simply adding all VLIT datasets up. In addition to developing an all-powerful model, REVO-LION also includes an evaluation set, which is expected to serve as a convenient evaluation benchmark for future research.
Current approaches for image-based keypoint detection on animal (including human) body and face are limited to specific keypoints and species. We address the limitation by proposing the Open-Vocabulary Keypoint Detection (OVKD) task. It aims to use text prompts to localize arbitrary keypoints of any species. To accomplish this objective, we propose Open-Vocabulary Keypoint Detection with Semantic-feature Matching (KDSM), which utilizes both vision and language models to harness the relationship between text and vision and thus achieve keypoint detection through associating text prompt with relevant keypoint features. Additionally, KDSM integrates domain distribution matrix matching and some special designs to reinforce the relationship between language and vision, thereby improving the model's generalizability and performance. Extensive experiments show that our proposed components bring significant performance improvements, and our overall method achieves impressive results in OVKD. Remarkably, our method outperforms the state-of-the-art few-shot keypoint detection methods using a zero-shot fashion. We will make the source code publicly accessible.
Language models (LMs), despite aligning well with an average labeler through reinforcement learning from human feedback (RLHF), may not universally suit diverse human preferences. Recent approaches therefore opt for customization by collecting multi-dimensional feedback and creating distinct rewards for each dimension (e.g., helpfulness, harmlessness, honesty). LMs can then be tailored to different preferences using multi-objective RL (MORL) with different reward weightings. Yet, RL fine-tuning is unstable and resource-heavy, especially for MORLHF with diverse and usually conflicting objectives. In this paper, we present Multi-Objective Direct Preference Optimization (MODPO), an RL-free algorithm that extends Direct Preference Optimization (DPO) for multiple alignment objectives. Essentially, MODPO trains different LMs to represent different collective reward models that combine all objectives with specific weightings. With a simple cross-entropy loss, the LMs optimized against the MODPO objective are analytically the exact solutions of the original MORLHF objective. Empirical results in safety alignment and long-form question answering confirm that MODPO matches or outperforms existing methods, efficiently producing a Pareto-optimal set of LMs that cater to diverse preferences with 3 times less computational resources compared with MORLHF.
Deep neural networks have demonstrated impressive accuracy in supervised learning tasks. However, their lack of transparency makes it hard for humans to trust their results, especially in safe-critic domains such as healthcare. To address this issue, recent explanation-guided learning approaches proposed to align the gradient-based attention map to image regions annotated by human experts, thereby obtaining an intrinsically human-centered model. However, the attention map these methods are based on may fail to causally attribute the model predictions, thus compromising their validity for alignment. To address this issue, we propose a novel human-centered framework based on counterfactual generation. In particular, we utilize the counterfactual generation's ability for causal attribution to introduce a novel loss called the CounterFactual Alignment (CF-Align) loss. This loss guarantees that the features attributed by the counterfactual generation for the classifier align with the human annotations. To optimize the proposed loss that entails a counterfactual generation with an implicit function form, we leverage the implicit function theorem for backpropagation. Our method is architecture-agnostic and, therefore can be applied to any neural network. We demonstrate the effectiveness of our method on a lung cancer diagnosis dataset, showcasing faithful alignment to humans.
We propose InternLM-XComposer, a vision-language large model that enables advanced image-text comprehension and composition. The innovative nature of our model is highlighted by three appealing properties: 1) Interleaved Text-Image Composition: InternLM-XComposer can effortlessly generate coherent and contextual articles that seamlessly integrate images, providing a more engaging and immersive reading experience. Simply provide a title, and our system will generate the corresponding manuscript. It can intelligently identify the areas in the text where images would enhance the content and automatically insert the most appropriate visual candidates. 2) Comprehension with Rich Multilingual Knowledge: The text-image comprehension is empowered by training on extensive multi-modal multilingual concepts with carefully crafted strategies, resulting in a deep understanding of visual content. 3) State-of-the-art Performance: Our model consistently achieves state-of-the-art results across various mainstream benchmarks for vision-language foundational models, including MME Benchmark, MMBench, MMBench-CN, Seed-Bench, and CCBench (Chinese Cultural Benchmark). Collectively, InternLM-XComposer seamlessly blends advanced text-image comprehension and composition, revolutionizing vision-language interaction and offering new insights and opportunities. The InternLM-XComposer model series with 7B parameters are publicly available at https://github.com/InternLM/InternLM-XComposer.
This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task to simultaneously a) accomplish the synthesis of visually realistic and temporally coherent videos while b) preserving the strong creative generation nature of the pre-trained T2I model. To this end, we propose LaVie, an integrated video generation framework that operates on cascaded video latent diffusion models, comprising a base T2V model, a temporal interpolation model, and a video super-resolution model. Our key insights are two-fold: 1) We reveal that the incorporation of simple temporal self-attentions, coupled with rotary positional encoding, adequately captures the temporal correlations inherent in video data. 2) Additionally, we validate that the process of joint image-video fine-tuning plays a pivotal role in producing high-quality and creative outcomes. To enhance the performance of LaVie, we contribute a comprehensive and diverse video dataset named Vimeo25M, consisting of 25 million text-video pairs that prioritize quality, diversity, and aesthetic appeal. Extensive experiments demonstrate that LaVie achieves state-of-the-art performance both quantitatively and qualitatively. Furthermore, we showcase the versatility of pre-trained LaVie models in various long video generation and personalized video synthesis applications.