Search

Recent success in legged robot locomotion is attributed to the integration of reinforcement learning and physical simulators. However, these policies often encounter challenges when deployed in real-world environments due to sim-to-real gaps, as simulators typically fail to replicate visual realism and complex real-world geometry. Moreover, the lack of realistic visual rendering limits the ability of these policies to support high-level tasks requiring RGB-based perception like ego-centric navigation. This paper presents a Real-to-Sim-to-Real framework that generates photorealistic and physically interactive "digital twin" simulation environments for visual navigation and locomotion learning. Our approach leverages 3D Gaussian Splatting (3DGS) based scene reconstruction from multi-view images and integrates these environments into simulations that support ego-centric visual perception and mesh-based physical interactions. To demonstrate its effectiveness, we train a reinforcement learning policy within the simulator to perform a visual goal-tracking task. Extensive experiments show that our framework achieves RGB-only sim-to-real policy transfer. Additionally, our framework facilitates the rapid adaptation of robot policies with effective exploration capability in complex new environments, highlighting its potential for applications in households and factories., Comment: Project Page: https://vr-robo.github.io/

Long Context Language Models have drawn great attention in the past few years. There has been work discussing the impact of long context on Language Model performance: some find that long irrelevant context could harm performance, while some experimentally summarize loss reduction by relevant long context as Scaling Laws. This calls for a more thorough understanding on how long context impact Language Modeling. In this work, we (1) propose a clean and effective theoretical framework on explaining the impact of context length to Language Modeling, from an Intrinsic Space perspective; and (2) conduct experiments on natural language and synthetic data, validating our proposed theoretical assumptions and deductions. Our theoretical framework can provide practical insights such as establishing that training dataset size dictates an optimal context length and bounds context length scaling for certain case. We hope our work may inspire new long context Language Models, as well as future work studying Physics for Language Models. Code for our experiments is available at this url: https://github.com/JingzheShi/NLPCtlScalingAndBounds., Comment: 19 pages, 14 figures

Previous humanoid robot research works treat the robot as a bipedal mobile manipulation platform, where only the feet and hands contact the environment. However, we humans use all body parts to interact with the world, e.g., we sit in chairs, get up from the ground, or roll on the floor. Contacting the environment using body parts other than feet and hands brings significant challenges in both model-predictive control and reinforcement learning-based methods. An unpredictable contact sequence makes it almost impossible for model-predictive control to plan ahead in real time. The success of the zero-shot sim-to-real reinforcement learning method for humanoids heavily depends on the acceleration of GPU-based rigid-body physical simulator and simplification of the collision detection. Lacking extreme torso movement of the humanoid research makes all other components non-trivial to design, such as termination conditions, motion commands and reward designs. To address these potential challenges, we propose a general humanoid motion framework that takes discrete motion commands and controls the robot's motor action in real time. Using a GPU-accelerated rigid-body simulator, we train a humanoid whole-body control policy that follows the high-level motion command in the real world in real time, even with stochastic contacts and extremely large robot base rotation and not-so-feasible motion command. More details at https://project-instinct.github.io

Though end-to-end speech-to-text translation has been a great success, we argue that the cascaded speech-to-text translation model still has its place, which is usually criticized for the error propagation between automatic speech recognition (ASR) and machine translation (MT) models. In this paper, we explore the benefits of incorporating multiple candidates from ASR and self-supervised speech features into MT. Our analysis reveals that the primary cause of cascading errors stems from the increased divergence between similar samples in the speech domain when mapped to the text domain. By including multiple candidates and self-supervised speech features, our approach allows the machine translation model to choose the right words and ensure precise translation using various speech samples. This strategy minimizes error spread and takes advantage of large ASR and MT datasets, along with pre-trained ASR/MT models, while addressing associated issues.

Current research in speech-to-speech translation (S2ST) primarily concentrates on translation accuracy and speech naturalness, often overlooking key elements like paralinguistic information, which is essential for conveying emotions and attitudes in communication. To address this, our research introduces a novel, carefully curated multilingual dataset from various movie audio tracks. Each dataset pair is precisely matched for paralinguistic information and duration. We enhance this by integrating multiple prosody transfer techniques, aiming for translations that are accurate, natural-sounding, and rich in paralinguistic details. Our experimental results confirm that our model retains more paralinguistic information from the source speech while maintaining high standards of translation accuracy and naturalness.

Let $G$ be a countable infinite amenable group, $K$ a finite-dimensional compact metrizable space, and $(K^G,\sigma)$ the full $G$-shift on $K^G$. For any $r\in [0,{\rm mdim}(K^G,\sigma))$, we construct a minimal subshift $(X,\sigma)$ of $(K^G,\sigma)$ with mdim$(X,\sigma)=r$. Furthermore, we construct a subshift of $([0,1]^G,\sigma)$ such that its mean dimension is $1$, and that the set of all attainable values of the mean dimension of its minimal subsystems is exactly the interval $[0,1)$., Comment: arXiv admin note: text overlap with arXiv:2101.01458 by other authors

Both encoder-only models (e.g., BERT, RoBERTa) and large language models (LLMs, e.g., Llama3) have been widely used for text classification tasks. However, there is a lack of systematic studies comparing the performance of encoder-based models and LLMs in text classification, particularly when fine-tuning is involved. This study employed a diverse range of models and methods, varying in size and architecture, and including both fine-tuned and pre-trained approaches. We first assessed the performances of these LLMs on the 20 Newsgroups (20NG) and MASSIVE datasets, comparing them to encoder-only RoBERTa models. Additionally, we explored the multi-task capabilities of both model types by combining multiple classification tasks, including intent detection and slot-filling, into a single model using data from both datasets. Our results indicate that fully fine-tuned Llama3-70B models outperform RoBERTa-large and other decoder LLMs across various classification tasks and datasets. Moreover, the consolidated multi-task fine-tuned LLMs matched the performance of dual-model setups in both tasks across both datasets. Overall, our study provides a comprehensive benchmark of encoder-only and LLM models on text classification tasks and demonstrates a method to combine two or more fully fine-tuned decoder LLMs for reduced latency and equivalent performance., Comment: 9 pages, 3 tables

In this paper, we consider a class of affined Anosov mappings with quasi-periodic forces, and show that there is a unique positive integer $m$, which only depends on the system, such that the exponential growth rate of the cardinality of invariant tori of degree $m$ is equal to the topological entropy.

Effective toxic content detection relies heavily on high-quality and diverse data, which serve as the foundation for robust content moderation models. Synthetic data has become a common approach for training models across various NLP tasks. However, its effectiveness remains uncertain for highly subjective tasks like hate speech detection, with previous research yielding mixed results. This study explores the potential of open-source LLMs for harmful data synthesis, utilizing controlled prompting and supervised fine-tuning techniques to enhance data quality and diversity. We systematically evaluated 6 open source LLMs on 5 datasets, assessing their ability to generate diverse, high-quality harmful data while minimizing hallucination and duplication. Our results show that Mistral consistently outperforms other open models, and supervised fine-tuning significantly enhances data reliability and diversity. We further analyze the trade-offs between prompt-based vs. fine-tuned toxic data synthesis, discuss real-world deployment challenges, and highlight ethical considerations. Our findings demonstrate that fine-tuned open source LLMs provide scalable and cost-effective solutions to augment toxic content detection datasets, paving the way for more accessible and transparent content moderation tools., Comment: 14 pages

Large real-world driving datasets have sparked significant research into various aspects of data-driven motion planners for autonomous driving. These include data augmentation, model architecture, reward design, training strategies, and planner pipelines. These planners promise better generalizations on complicated and few-shot cases than previous methods. However, experiment results show that many of these approaches produce limited generalization abilities in planning performance due to overly complex designs or training paradigms. In this paper, we review and benchmark previous methods focusing on generalizations. The experimental results indicate that as models are appropriately scaled, many design elements become redundant. We introduce StateTransformer-2 (STR2), a scalable, decoder-only motion planner that uses a Vision Transformer (ViT) encoder and a mixture-of-experts (MoE) causal Transformer architecture. The MoE backbone addresses modality collapse and reward balancing by expert routing during training. Extensive experiments on the NuPlan dataset show that our method generalizes better than previous approaches across different test sets and closed-loop simulations. Furthermore, we assess its scalability on billions of real-world urban driving scenarios, demonstrating consistent accuracy improvements as both data and model size grow., Comment: 7 pages, 3 figures

Quadrupedal animals have the ability to perform agile while accurate tasks: a trained dog can chase and catch a flying frisbee before it touches the ground; a cat alone at home can jump and grab the door handle accurately. However, agility and precision are usually a trade-off in robotics problems. Recent works in quadruped robots either focus on agile but not-so-accurate tasks, such as locomotion in challenging terrain, or accurate but not-so-fast tasks, such as using an additional manipulator to interact with objects. In this work, we aim at an accurate and agile task, catching a small object hanging above the robot. We mount a passive gripper in front of the robot chassis, so that the robot has to jump and catch the object with extreme precision. Our experiment shows that our system is able to jump and successfully catch the ball at 1.05m high in simulation and 0.8m high in the real world, while the robot is 0.3m high when standing.

In different NLP tasks, detecting harmful content is crucial for online environments, especially with the growing influence of social media. However, previous research has two main issues: 1) a lack of data in low-resource settings, and 2) inconsistent definitions and criteria for judging harmful content, requiring classification models to be robust to spurious features and diverse. We propose Toxicraft, a novel framework for synthesizing datasets of harmful information to address these weaknesses. With only a small amount of seed data, our framework can generate a wide variety of synthetic, yet remarkably realistic, examples of toxic information. Experimentation across various datasets showcases a notable enhancement in detection model robustness and adaptability, surpassing or close to the gold labels. We release the generated data at Github upon acceptance.

Vision-based 3D occupancy prediction is significantly challenged by the inherent limitations of monocular vision in depth estimation. This paper introduces CVT-Occ, a novel approach that leverages temporal fusion through the geometric correspondence of voxels over time to improve the accuracy of 3D occupancy predictions. By sampling points along the line of sight of each voxel and integrating the features of these points from historical frames, we construct a cost volume feature map that refines current volume features for improved prediction outcomes. Our method takes advantage of parallax cues from historical observations and employs a data-driven approach to learn the cost volume. We validate the effectiveness of CVT-Occ through rigorous experiments on the Occ3D-Waymo dataset, where it outperforms state-of-the-art methods in 3D occupancy prediction with minimal additional computational cost. The code is released at \url{https://github.com/Tsinghua-MARS-Lab/CVT-Occ}., Comment: Accepted to ECCV 2024

We introduce Seed-Music, a suite of music generation systems capable of producing high-quality music with fine-grained style control. Our unified framework leverages both auto-regressive language modeling and diffusion approaches to support two key music creation workflows: controlled music generation and post-production editing. For controlled music generation, our system enables vocal music generation with performance controls from multi-modal inputs, including style descriptions, audio references, musical scores, and voice prompts. For post-production editing, it offers interactive tools for editing lyrics and vocal melodies directly in the generated audio. We encourage readers to listen to demo audio examples at https://team.doubao.com/seed-music "https://team.doubao.com/seed-music"., Comment: Seed-Music technical report, 20 pages, 5 figures

Quadruped robots must exhibit robust walking capabilities in practical applications. In this work, we propose a novel approach that enables quadruped robots to pass various small obstacles, or "tiny traps". Existing methods often rely on exteroceptive sensors, which can be unreliable for detecting such tiny traps. To overcome this limitation, our approach focuses solely on proprioceptive inputs. We introduce a two-stage training framework incorporating a contact encoder and a classification head to learn implicit representations of different traps. Additionally, we design a set of tailored reward functions to improve both the stability of training and the ease of deployment for goal-tracking tasks. To benefit further research, we design a new benchmark for tiny trap task. Extensive experiments in both simulation and real-world settings demonstrate the effectiveness and robustness of our method. Project Page: https://robust-robot-walker.github.io/, Comment: 10 pages, 17 figures

The application of vision-language models (VLMs) has achieved impressive success in various robotics tasks. However, there are few explorations for these foundation models used in quadruped robot navigation through terrains in 3D environments. In this work, we introduce SARO (Space Aware Robot System for Terrain Crossing), an innovative system composed of a high-level reasoning module, a closed-loop sub-task execution module, and a low-level control policy. It enables the robot to navigate across 3D terrains and reach the goal position. For high-level reasoning and execution, we propose a novel algorithmic system taking advantage of a VLM, with a design of task decomposition and a closed-loop sub-task execution mechanism. For low-level locomotion control, we utilize the Probability Annealing Selection (PAS) method to effectively train a control policy by reinforcement learning. Numerous experiments show that our whole system can accurately and robustly navigate across several 3D terrains, and its generalization ability ensures the applications in diverse indoor and outdoor scenarios and terrains. Project page: https://saro-vlm.github.io/, Comment: 12 pages, 9 figures

CLIP, as a vision-language model, has significantly advanced Open-Vocabulary Semantic Segmentation (OVSS) with its zero-shot capabilities. Despite its success, its application to OVSS faces challenges due to its initial image-level alignment training, which affects its performance in tasks requiring detailed local context. Our study delves into the impact of CLIP's [CLS] token on patch feature correlations, revealing a dominance of "global" patches that hinders local feature discrimination. To overcome this, we propose CLIPtrase, a novel training-free semantic segmentation strategy that enhances local feature awareness through recalibrated self-correlation among patches. This approach demonstrates notable improvements in segmentation accuracy and the ability to maintain semantic coherence across objects.Experiments show that we are 22.3% ahead of CLIP on average on 9 segmentation benchmarks, outperforming existing state-of-the-art training-free methods.The code are made publicly available at: https://github.com/leaves162/CLIPtrase., Comment: ECCV24 accepted

Combinatorial Optimization (CO) problems are fundamentally important in numerous real-world applications across diverse industries, characterized by entailing enormous solution space and demanding time-sensitive response. Despite recent advancements in neural solvers, their limited expressiveness struggles to capture the multi-modal nature of CO landscapes. While some research has shifted towards diffusion models, these models still sample solutions indiscriminately from the entire NP-complete solution space with time-consuming denoising processes, which limit their practicality for large problem scales. We propose DISCO, an efficient DIffusion Solver for large-scale Combinatorial Optimization problems that excels in both solution quality and inference speed. DISCO's efficacy is twofold: First, it enhances solution quality by constraining the sampling space to a more meaningful domain guided by solution residues, while preserving the multi-modal properties of the output distributions. Second, it accelerates the denoising process through an analytically solvable approach, enabling solution sampling with minimal reverse-time steps and significantly reducing inference time. DISCO delivers strong performance on large-scale Traveling Salesman Problems and challenging Maximal Independent Set benchmarks, with inference time up to 5.28 times faster than other diffusion alternatives. By incorporating a divide-and-conquer strategy, DISCO can well generalize to solve unseen-scale problem instances, even surpassing models specifically trained for those scales.

Mixture-of-Experts (MoE) has been demonstrated as an efficient method to scale up models. By dynamically and sparsely selecting activated experts, MoE can effectively reduce computational costs. Despite the success, we observe that many tokens in the MoE models have uncertain routing results. These tokens have nearly equal scores for choosing each expert, and we demonstrate that this uncertainty can lead to incorrect selections. Inspired by the Global Workspace Theory (GWT), we propose a new fine-tuning method, GW-MoE, to address this issue. The core idea is to broadcast the uncertain tokens across experts during fine-tuning. Therefore, these tokens can acquire the necessary knowledge from any expert during inference and become less sensitive to the choice. GW-MoE does not introduce additional inference overhead. We validate that GW can mitigate the uncertain problem and consistently improve in different tasks (text classification, question answering, summarization, code generation, and mathematical problem solving) and model sizes (650M and 8B parameters).

Parkour is a grand challenge for legged locomotion, even for quadruped robots, requiring active perception and various maneuvers to overcome multiple challenging obstacles. Existing methods for humanoid locomotion either optimize a trajectory for a single parkour track or train a reinforcement learning policy only to walk with a significant amount of motion references. In this work, we propose a framework for learning an end-to-end vision-based whole-body-control parkour policy for humanoid robots that overcomes multiple parkour skills without any motion prior. Using the parkour policy, the humanoid robot can jump on a 0.42m platform, leap over hurdles, 0.8m gaps, and much more. It can also run at 1.8m/s in the wild and walk robustly on different terrains. We test our policy in indoor and outdoor environments to demonstrate that it can autonomously select parkour skills while following the rotation command of the joystick. We override the arm actions and show that this framework can easily transfer to humanoid mobile manipulation tasks. Videos can be found at https://humanoid4parkour.github.io, Comment: Published on CoRL 2024

Time series forecasting has become an increasingly popular research area due to its critical applications in various real-world domains such as traffic management, weather prediction, and financial analysis. Despite significant advancements, existing models face notable challenges, including the necessity of manual hyperparameter tuning for different datasets, and difficulty in effectively distinguishing signal from redundant features in data characterized by strong seasonality. These issues hinder the generalization and practical application of time series forecasting models. To solve this issues, we propose an innovative time series forecasting model TimeSieve designed to address these challenges. Our approach employs wavelet transforms to preprocess time series data, effectively capturing multi-scale features without the need for additional parameters or manual hyperparameter tuning. Additionally, we introduce the information bottleneck theory that filters out redundant features from both detail and approximation coefficients, retaining only the most predictive information. This combination reduces significantly improves the model's accuracy. Extensive experiments demonstrate that our model outperforms existing state-of-the-art methods on 70% of the datasets, achieving higher predictive accuracy and better generalization across diverse datasets. Our results validate the effectiveness of our approach in addressing the key challenges in time series forecasting, paving the way for more reliable and efficient predictive models in practical applications. The code for our model is available at https://github.com/xll0328/TimeSieve.

The field of time series forecasting has garnered significant attention in recent years, prompting the development of advanced models like TimeSieve, which demonstrates impressive performance. However, an analysis reveals certain unfaithfulness issues, including high sensitivity to random seeds, input and layer noise perturbations and parametric perturbations. Recognizing these challenges, we embark on a quest to define the concept of \textbf{\underline{F}aithful \underline{T}ime\underline{S}ieve \underline{(FTS)}}, a model that consistently delivers reliable and robust predictions. To address these issues, we propose a novel framework aimed at identifying and rectifying unfaithfulness in TimeSieve. Our framework is designed to enhance the model's stability and faithfulness, ensuring that its outputs are less susceptible to the aforementioned factors. Experimentation validates the effectiveness of our proposed framework, demonstrating improved faithfulness in the model's behavior.

In optimizing performance and extending the lifespan of lithium batteries, accurate state prediction is pivotal. Traditional regression and classification methods have achieved some success in battery state prediction. However, the efficacy of these data-driven approaches heavily relies on the availability and quality of public datasets. Additionally, generating electrochemical data predominantly through battery experiments is a lengthy and costly process, making it challenging to acquire high-quality electrochemical data. This difficulty, coupled with data incompleteness, significantly impacts prediction accuracy. Addressing these challenges, this study introduces the End of Life (EOL) and Equivalent Cycle Life (ECL) as conditions for generative AI models. By integrating an embedding layer into the CVAE model, we developed the Refined Conditional Variational Autoencoder (RCVAE). Through preprocessing data into a quasi-video format, our study achieves an integrated synthesis of electrochemical data, including voltage, current, temperature, and charging capacity, which is then processed by the RCVAE model. Coupled with customized training and inference algorithms, this model can generate specific electrochemical data for EOL and ECL under supervised conditions. This method provides users with a comprehensive electrochemical dataset, pioneering a new research domain for the artificial synthesis of lithium battery data. Furthermore, based on the detailed synthetic data, various battery state indicators can be calculated, offering new perspectives and possibilities for lithium battery performance prediction.

Autonomous vehicles are gradually entering city roads today, with the help of high-definition maps (HDMaps). However, the reliance on HDMaps prevents autonomous vehicles from stepping into regions without this expensive digital infrastructure. This fact drives many researchers to study online HDMap generation algorithms, but the performance of these algorithms at far regions is still unsatisfying. We present P-MapNet, in which the letter P highlights the fact that we focus on incorporating map priors to improve model performance. Specifically, we exploit priors in both SDMap and HDMap. On one hand, we extract weakly aligned SDMap from OpenStreetMap, and encode it as an additional conditioning branch. Despite the misalignment challenge, our attention-based architecture adaptively attends to relevant SDMap skeletons and significantly improves performance. On the other hand, we exploit a masked autoencoder to capture the prior distribution of HDMap, which can serve as a refinement module to mitigate occlusions and artifacts. We benchmark on the nuScenes and Argoverse2 datasets. Through comprehensive experiments, we show that: (1) our SDMap prior can improve online map generation performance, using both rasterized (by up to $+18.73$ $\rm mIoU$) and vectorized (by up to $+8.50$ $\rm mAP$) output representations. (2) our HDMap prior can improve map perceptual metrics by up to $6.34\%$. (3) P-MapNet can be switched into different inference modes that covers different regions of the accuracy-efficiency trade-off landscape. (4) P-MapNet is a far-seeing solution that brings larger improvements on longer ranges. Codes and models are publicly available at https://jike5.github.io/P-MapNet., Comment: Code: https://jike5.github.io/P-MapNet

Autonomous vehicles rely extensively on perception systems to navigate and interpret their surroundings. Despite significant advancements in these systems recently, challenges persist under conditions like occlusion, extreme lighting, or in unfamiliar urban areas. Unlike these systems, humans do not solely depend on immediate observations to perceive the environment. In navigating new cities, humans gradually develop a preliminary mental map to supplement real-time perception during subsequent visits. Inspired by this human approach, we introduce a novel framework, PreSight, that leverages past traversals to construct static prior memories, enhancing online perception in later navigations. Our method involves optimizing a city-scale neural radiance field with data from previous journeys to generate neural priors. These priors, rich in semantic and geometric details, are derived without manual annotations and can seamlessly augment various state-of-the-art perception models, improving their efficacy with minimal additional computational cost. Experimental results on the nuScenes dataset demonstrate the framework's high compatibility with diverse online perception models. Specifically, it shows remarkable improvements in HD-map construction and occupancy prediction tasks, highlighting its potential as a new perception framework for autonomous driving systems. Our code will be released at https://github.com/yuantianyuan01/PreSight.

A primary hurdle of autonomous driving in urban environments is understanding complex and long-tail scenarios, such as challenging road conditions and delicate human behaviors. We introduce DriveVLM, an autonomous driving system leveraging Vision-Language Models (VLMs) for enhanced scene understanding and planning capabilities. DriveVLM integrates a unique combination of reasoning modules for scene description, scene analysis, and hierarchical planning. Furthermore, recognizing the limitations of VLMs in spatial reasoning and heavy computational requirements, we propose DriveVLM-Dual, a hybrid system that synergizes the strengths of DriveVLM with the traditional autonomous driving pipeline. Experiments on both the nuScenes dataset and our SUP-AD dataset demonstrate the efficacy of DriveVLM and DriveVLM-Dual in handling complex and unpredictable driving conditions. Finally, we deploy the DriveVLM-Dual on a production vehicle, verifying it is effective in real-world autonomous driving environments., Comment: Project Page: https://tsinghua-mars-lab.github.io/DriveVLM/

In the realm of audio-language pre-training (ALP), the challenge of achieving cross-modal alignment is significant. Moreover, the integration of audio inputs with diverse distributions and task variations poses challenges in developing generic audio-language models. In this study, we present MINT, a novel ALP framework boosting audio-language models through multi-target pre-training and instruction tuning. MINT leverages the strength of frozen pre-trained audio encoders and large language models (LLM) to improve audio-language pre-training, enabling effective transferablility to both audio-text understanding and generation tasks. To address the modality gap, we introduce Bridge-Net, a trainable module that enhances cross-modality alignment and the model's ability to follow instructions for a variety of audio-text tasks. Bridge-Net is pivotal within MINT, initially enhancing audio-language representation learning through a multi-target pre-training approach. Subsequently, Bridge-Net further boosts audio-to-language generative learning by integrating a frozen language model with instruction tuning. This integration empowers MINT to extract features in a flexible and effective manner, specifically tailored to the provided instructions for diverse tasks. Experimental results demonstrate that MINT attains superior performance across various audio-language understanding and generation tasks, highlighting its robust generalization capabilities even in zero-shot scenarios.

This technical report introduces PIXART-{\delta}, a text-to-image synthesis framework that integrates the Latent Consistency Model (LCM) and ControlNet into the advanced PIXART-{\alpha} model. PIXART-{\alpha} is recognized for its ability to generate high-quality images of 1024px resolution through a remarkably efficient training process. The integration of LCM in PIXART-{\delta} significantly accelerates the inference speed, enabling the production of high-quality images in just 2-4 steps. Notably, PIXART-{\delta} achieves a breakthrough 0.5 seconds for generating 1024x1024 pixel images, marking a 7x improvement over the PIXART-{\alpha}. Additionally, PIXART-{\delta} is designed to be efficiently trainable on 32GB V100 GPUs within a single day. With its 8-bit inference capability (von Platen et al., 2023), PIXART-{\delta} can synthesize 1024px images within 8GB GPU memory constraints, greatly enhancing its usability and accessibility. Furthermore, incorporating a ControlNet-like module enables fine-grained control over text-to-image diffusion models. We introduce a novel ControlNet-Transformer architecture, specifically tailored for Transformers, achieving explicit controllability alongside high-quality image generation. As a state-of-the-art, open-source image generation model, PIXART-{\delta} offers a promising alternative to the Stable Diffusion family of models, contributing significantly to text-to-image synthesis., Comment: Technical Report

Latent Consistency Models (LCMs) have achieved impressive performance in accelerating text-to-image generative tasks, producing high-quality images with minimal inference steps. LCMs are distilled from pre-trained latent diffusion models (LDMs), requiring only ~32 A100 GPU training hours. This report further extends LCMs' potential in two aspects: First, by applying LoRA distillation to Stable-Diffusion models including SD-V1.5, SSD-1B, and SDXL, we have expanded LCM's scope to larger models with significantly less memory consumption, achieving superior image generation quality. Second, we identify the LoRA parameters obtained through LCM distillation as a universal Stable-Diffusion acceleration module, named LCM-LoRA. LCM-LoRA can be directly plugged into various Stable-Diffusion fine-tuned models or LoRAs without training, thus representing a universally applicable accelerator for diverse image generation tasks. Compared with previous numerical PF-ODE solvers such as DDIM, DPM-Solver, LCM-LoRA can be viewed as a plug-in neural PF-ODE solver that possesses strong generalization abilities. Project page: https://github.com/luosiallen/latent-consistency-model., Comment: Technical Report

Motion prediction and planning are vital tasks in autonomous driving, and recent efforts have shifted to machine learning-based approaches. The challenges include understanding diverse road topologies, reasoning traffic dynamics over a long time horizon, interpreting heterogeneous behaviors, and generating policies in a large continuous state space. Inspired by the success of large language models in addressing similar complexities through model scaling, we introduce a scalable trajectory model called State Transformer (STR). STR reformulates the motion prediction and motion planning problems by arranging observations, states, and actions into one unified sequence modeling task. Our approach unites trajectory generation problems with other sequence modeling problems, powering rapid iterations with breakthroughs in neighbor domains such as language modeling. Remarkably, experimental results reveal that large trajectory models (LTMs), such as STR, adhere to the scaling laws by presenting outstanding adaptability and learning efficiency. Qualitative results further demonstrate that LTMs are capable of making plausible predictions in scenarios that diverge significantly from the training data distribution. LTMs also learn to make complex reasonings for long-term planning, without explicit loss designs or costly high-level annotations.

Scene completion and forecasting are two popular perception problems in research for mobile agents like autonomous vehicles. Existing approaches treat the two problems in isolation, resulting in a separate perception of the two aspects. In this paper, we introduce a novel LiDAR perception task of Occupancy Completion and Forecasting (OCF) in the context of autonomous driving to unify these aspects into a cohesive framework. This task requires new algorithms to address three challenges altogether: (1) sparse-to-dense reconstruction, (2) partial-to-complete hallucination, and (3) 3D-to-4D prediction. To enable supervision and evaluation, we curate a large-scale dataset termed OCFBench from public autonomous driving datasets. We analyze the performance of closely related existing baseline models and our own ones on our dataset. We envision that this research will inspire and call for further investigation in this evolving and crucial area of 4D perception. Our code for data curation and baseline implementation is available at https://github.com/ai4ce/Occ4cast., Comment: IROS 2024

With the growing success of multi-modal learning, research on the robustness of multi-modal models, especially when facing situations with missing modalities, is receiving increased attention. Nevertheless, previous studies in this domain exhibit certain limitations, as they often lack theoretical insights or their methodologies are tied to specific network architectures or modalities. We model the scenarios of multi-modal models encountering missing modalities from an information-theoretic perspective and illustrate that the performance ceiling in such scenarios can be approached by efficiently utilizing the information inherent in non-missing modalities. In practice, there are two key aspects: (1) The encoder should be able to extract sufficiently good features from the non-missing modality; (2) The extracted features should be robust enough not to be influenced by noise during the fusion process across modalities. To this end, we introduce Uni-Modal Ensemble with Missing Modality Adaptation (UME-MMA). UME-MMA employs uni-modal pre-trained weights for the multi-modal model to enhance feature extraction and utilizes missing modality data augmentation techniques to better adapt to situations with missing modalities. Apart from that, UME-MMA, built on a late-fusion learning framework, allows for the plug-and-play use of various encoders, making it suitable for a wide range of modalities and enabling seamless integration of large-scale pre-trained encoders to further enhance performance. And we demonstrate UME-MMA's effectiveness in audio-visual datasets~(e.g., AV-MNIST, Kinetics-Sound, AVE) and vision-language datasets~(e.g., MM-IMDB, UPMC Food101).

Imitation learning (IL) enables agents to mimic expert behaviors. Most previous IL techniques focus on precisely imitating one policy through mass demonstrations. However, in many applications, what humans require is the ability to perform various tasks directly through a few demonstrations of corresponding tasks, where the agent would meet many unexpected changes when deployed. In this scenario, the agent is expected to not only imitate the demonstration but also adapt to unforeseen environmental changes. This motivates us to propose a new topic called imitator learning (ItorL), which aims to derive an imitator module that can on-the-fly reconstruct the imitation policies based on very limited expert demonstrations for different unseen tasks, without any extra adjustment. In this work, we focus on imitator learning based on only one expert demonstration. To solve ItorL, we propose Demo-Attention Actor-Critic (DAAC), which integrates IL into a reinforcement-learning paradigm that can regularize policies' behaviors in unexpected situations. Besides, for autonomous imitation policy building, we design a demonstration-based attention architecture for imitator policy that can effectively output imitated actions by adaptively tracing the suitable states in demonstrations. We develop a new navigation benchmark and a robot environment for \topic~and show that DAAC~outperforms previous imitation methods \textit{with large margins} both on seen and unseen tasks.

This paper investigates how to better leverage large-scale pre-trained uni-modal models to further enhance discriminative multi-modal learning. Even when fine-tuned with only uni-modal data, these models can outperform previous multi-modal models in certain tasks. It's clear that their incorporation into multi-modal learning would significantly improve performance. However, multi-modal learning with these models still suffers from insufficient learning of uni-modal features, which weakens the resulting multi-modal model's generalization ability. While fine-tuning uni-modal models separately and then aggregating their predictions is straightforward, it doesn't allow for adequate adaptation between modalities, also leading to sub-optimal results. To this end, we introduce Multi-Modal Low-Rank Adaptation learning (MMLoRA). By freezing the weights of uni-modal fine-tuned models, adding extra trainable rank decomposition matrices to them, and subsequently performing multi-modal joint training, our method enhances adaptation between modalities and boosts overall performance. We demonstrate the effectiveness of MMLoRA on three dataset categories: audio-visual (e.g., AVE, Kinetics-Sound, CREMA-D), vision-language (e.g., MM-IMDB, UPMC Food101), and RGB-Optical Flow (UCF101).

Latent Diffusion models (LDMs) have achieved remarkable results in synthesizing high-resolution images. However, the iterative sampling process is computationally intensive and leads to slow generation. Inspired by Consistency Models (song et al.), we propose Latent Consistency Models (LCMs), enabling swift inference with minimal steps on any pre-trained LDMs, including Stable Diffusion (rombach et al). Viewing the guided reverse diffusion process as solving an augmented probability flow ODE (PF-ODE), LCMs are designed to directly predict the solution of such ODE in latent space, mitigating the need for numerous iterations and allowing rapid, high-fidelity sampling. Efficiently distilled from pre-trained classifier-free guided diffusion models, a high-quality 768 x 768 2~4-step LCM takes only 32 A100 GPU hours for training. Furthermore, we introduce Latent Consistency Fine-tuning (LCF), a novel method that is tailored for fine-tuning LCMs on customized image datasets. Evaluation on the LAION-5B-Aesthetics dataset demonstrates that LCMs achieve state-of-the-art text-to-image generation performance with few-step inference. Project Page: https://latent-consistency-models.github.io/

We present a simple yet effective approach that can transform the OpenAI GPT-3.5 model into a reliable motion planner for autonomous vehicles. Motion planning is a core challenge in autonomous driving, aiming to plan a driving trajectory that is safe and comfortable. Existing motion planners predominantly leverage heuristic methods to forecast driving trajectories, yet these approaches demonstrate insufficient generalization capabilities in the face of novel and unseen driving scenarios. In this paper, we propose a novel approach to motion planning that capitalizes on the strong reasoning capabilities and generalization potential inherent to Large Language Models (LLMs). The fundamental insight of our approach is the reformulation of motion planning as a language modeling problem, a perspective not previously explored. Specifically, we represent the planner inputs and outputs as language tokens, and leverage the LLM to generate driving trajectories through a language description of coordinate positions. Furthermore, we propose a novel prompting-reasoning-finetuning strategy to stimulate the numerical reasoning potential of the LLM. With this strategy, the LLM can describe highly precise trajectory coordinates and also its internal decision-making process in natural language. We evaluate our approach on the large-scale nuScenes dataset, and extensive experiments substantiate the effectiveness, generalization ability, and interpretability of our GPT-based motion planner. Code is now available at https://github.com/PointsCoder/GPT-Driver., Comment: NeurIPS 2023 Foundation Models for Decision Making Workshop

Offline Reinforcement Learning (RL) enables policy learning without active interactions, making it especially appealing for self-driving tasks. Recent successes of Transformers inspire casting offline RL as sequence modeling, which, however, fails in stochastic environments with incorrect assumptions that identical actions can consistently achieve the same goal. In this paper, we introduce an UNcertainty-awaRE deciSion Transformer (UNREST) for planning in stochastic driving environments without introducing additional transition or complex generative models. Specifically, UNREST estimates uncertainties by conditional mutual information between transitions and returns. Discovering 'uncertainty accumulation' and 'temporal locality' properties of driving environments, we replace the global returns in decision transformers with truncated returns less affected by environments to learn from actual outcomes of actions rather than environment transitions. We also dynamically evaluate uncertainty at inference for cautious planning. Extensive experiments demonstrate UNREST's superior performance in various driving scenarios and the power of our uncertainty estimation strategy.

City modeling and generation have attracted an increased interest in various applications, including gaming, urban planning, and autonomous driving. Unlike previous works focused on the generation of single objects or indoor scenes, the huge volumes of spatial data in cities pose a challenge to the generative models. Furthermore, few publicly available 3D real-world city datasets also hinder the development of methods for city generation. In this paper, we first collect over 3,000,000 geo-referenced objects for the city of New York, Zurich, Tokyo, Berlin, Boston and several other large cities. Based on this dataset, we propose AETree, a tree-structured auto-encoder neural network, for city generation. Specifically, we first propose a novel Spatial-Geometric Distance (SGD) metric to measure the similarity between building layouts and then construct a binary tree over the raw geometric data of building based on the SGD metric. Next, we present a tree-structured network whose encoder learns to extract and merge spatial information from bottom-up iteratively. The resulting global representation is reversely decoded for reconstruction or generation. To address the issue of long-dependency as the level of the tree increases, a Long Short-Term Memory (LSTM) Cell is employed as a basic network element of the proposed AETree. Moreover, we introduce a novel metric, Overlapping Area Ratio (OAR), to quantitatively evaluate the generation results. Experiments on the collected dataset demonstrate the effectiveness of the proposed model on 2D and 3D city generation. Furthermore, the latent features learned by AETree can serve downstream urban planning applications.

Learning-based vehicle planning is receiving increasing attention with the emergence of diverse driving simulators and large-scale driving datasets. While offline reinforcement learning (RL) is well suited for these safety-critical tasks, it still struggles to plan over extended periods. In this work, we present a skill-based framework that enhances offline RL to overcome the long-horizon vehicle planning challenge. Specifically, we design a variational autoencoder (VAE) to learn skills from offline demonstrations. To mitigate posterior collapse of common VAEs, we introduce a two-branch sequence encoder to capture both discrete options and continuous variations of the complex driving skills. The final policy treats learned skills as actions and can be trained by any off-the-shelf offline RL algorithms. This facilitates a shift in focus from per-step actions to temporally extended skills, thereby enabling long-term reasoning into the future. Extensive results on CARLA prove that our model consistently outperforms strong baselines at both training and new scenarios. Additional visualizations and experiments demonstrate the interpretability and transferability of extracted skills.

Parkour is a grand challenge for legged locomotion that requires robots to overcome various obstacles rapidly in complex environments. Existing methods can generate either diverse but blind locomotion skills or vision-based but specialized skills by using reference animal data or complex rewards. However, autonomous parkour requires robots to learn generalizable skills that are both vision-based and diverse to perceive and react to various scenarios. In this work, we propose a system for learning a single end-to-end vision-based parkour policy of diverse parkour skills using a simple reward without any reference motion data. We develop a reinforcement learning method inspired by direct collocation to generate parkour skills, including climbing over high obstacles, leaping over large gaps, crawling beneath low barriers, squeezing through thin slits, and running. We distill these skills into a single vision-based parkour policy and transfer it to a quadrupedal robot using its egocentric depth camera. We demonstrate that our system can empower two different low-cost robots to autonomously select and execute appropriate parkour skills to traverse challenging real-world environments., Comment: CoRL 2023 (Oral). Project website at https://robot-parkour.github.io

High-Definition (HD) maps are essential for the safety of autonomous driving systems. While existing techniques employ camera images and onboard sensors to generate vectorized high-precision maps, they are constrained by their reliance on single-frame input. This approach limits their stability and performance in complex scenarios such as occlusions, largely due to the absence of temporal information. Moreover, their performance diminishes when applied to broader perception ranges. In this paper, we present StreamMapNet, a novel online mapping pipeline adept at long-sequence temporal modeling of videos. StreamMapNet employs multi-point attention and temporal information which empowers the construction of large-range local HD maps with high stability and further addresses the limitations of existing methods. Furthermore, we critically examine widely used online HD Map construction benchmark and datasets, Argoverse2 and nuScenes, revealing significant bias in the existing evaluation protocols. We propose to resplit the benchmarks according to geographical spans, promoting fair and precise evaluations. Experimental results validate that StreamMapNet significantly outperforms existing methods across all settings while maintaining an online inference speed of $14.2$ FPS. Our code is available at https://github.com/yuantianyuan01/StreamMapNet.

Millimeter wave (mmWave) based speech recognition provides more possibility for audio-related applications, such as conference speech transcription and eavesdropping. However, considering the practicality in real scenarios, latency and recognizable vocabulary size are two critical factors that cannot be overlooked. In this paper, we propose Radio2Text, the first mmWave-based system for streaming automatic speech recognition (ASR) with a vocabulary size exceeding 13,000 words. Radio2Text is based on a tailored streaming Transformer that is capable of effectively learning representations of speech-related features, paving the way for streaming ASR with a large vocabulary. To alleviate the deficiency of streaming networks unable to access entire future inputs, we propose the Guidance Initialization that facilitates the transfer of feature knowledge related to the global context from the non-streaming Transformer to the tailored streaming Transformer through weight inheritance. Further, we propose a cross-modal structure based on knowledge distillation (KD), named cross-modal KD, to mitigate the negative effect of low quality mmWave signals on recognition performance. In the cross-modal KD, the audio streaming Transformer provides feature and response guidance that inherit fruitful and accurate speech information to supervise the training of the tailored radio streaming Transformer. The experimental results show that our Radio2Text can achieve a character error rate of 5.7% and a word error rate of 9.4% for the recognition of a vocabulary consisting of over 13,000 words., Comment: Accepted by Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (ACM IMWUT/UbiComp 2023)

The growing demand for accurate control in varying and unknown environments has sparked a corresponding increase in the requirements for power supply components, including permanent magnet synchronous motors (PMSMs). To infer the unknown part of the system, machine learning techniques are widely employed, especially Gaussian process regression (GPR) due to its flexibility of continuous system modeling and its guaranteed performance. For practical implementation, distributed GPR is adopted to alleviate the high computational complexity. However, the study of distributed GPR from a control perspective remains an open problem. In this paper, a control-aware optimal aggregation strategy of distributed GPR for PMSMs is proposed based on the Lyapunov stability theory. This strategy exclusively leverages the posterior mean, thereby obviating the need for computationally intensive calculations associated with posterior variance in alternative approaches. Moreover, the straightforward calculation process of our proposed strategy lends itself to seamless implementation in high-frequency PMSM control. The effectiveness of the proposed strategy is demonstrated in the simulations.

Satellite-collected nighttime light provides a unique perspective on human activities, including urbanization, population growth, and epidemics. Yet, long-term and fine-grained nighttime light observations are lacking, leaving the analysis and applications of decades of light changes in urban facilities undeveloped. To fill this gap, we developed an innovative framework and used it to design a new super-resolution model that reconstructs low-resolution nighttime light data into high resolution. The validation of one billion data points shows that the correlation coefficient of our model at the global scale reaches 0.873, which is significantly higher than that of other existing models (maximum = 0.713). Our model also outperforms existing models at the national and urban scales. Furthermore, through an inspection of airports and roads, only our model's image details can reveal the historical development of these facilities. We provide the long-term and fine-grained nighttime light observations to promote research on human activities. The dataset is available at \url{https://doi.org/10.5281/zenodo.7859205}.

The Video-to-Audio (V2A) model has recently gained attention for its practical application in generating audio directly from silent videos, particularly in video/film production. However, previous methods in V2A have limited generation quality in terms of temporal synchronization and audio-visual relevance. We present Diff-Foley, a synchronized Video-to-Audio synthesis method with a latent diffusion model (LDM) that generates high-quality audio with improved synchronization and audio-visual relevance. We adopt contrastive audio-visual pretraining (CAVP) to learn more temporally and semantically aligned features, then train an LDM with CAVP-aligned visual features on spectrogram latent space. The CAVP-aligned features enable LDM to capture the subtler audio-visual correlation via a cross-attention module. We further significantly improve sample quality with `double guidance'. Diff-Foley achieves state-of-the-art V2A performance on current large scale V2A dataset. Furthermore, we demonstrate Diff-Foley practical applicability and generalization capabilities via downstream finetuning. Project Page: see https://diff-foley.github.io/

Depth estimation is a cornerstone of perception in autonomous driving and robotic systems. The considerable cost and relatively sparse data acquisition of LiDAR systems have led to the exploration of cost-effective alternatives, notably, self-supervised depth estimation. Nevertheless, current self-supervised depth estimation methods grapple with several limitations: (1) the failure to adequately leverage informative multi-camera views. (2) the limited capacity to handle dynamic objects effectively. To address these challenges, we present BEVScope, an innovative approach to self-supervised depth estimation that harnesses Bird's-Eye-View (BEV) features. Concurrently, we propose an adaptive loss function, specifically designed to mitigate the complexities associated with moving objects. Empirical evaluations conducted on the Nuscenes dataset validate our approach, demonstrating competitive performance. Code will be released at https://github.com/myc634/BEVScope.

Robots rely heavily on sensors, especially RGB and depth cameras, to perceive and interact with the world. RGB cameras record 2D images with rich semantic information while missing precise spatial information. On the other side, depth cameras offer critical 3D geometry data but capture limited semantics. Therefore, integrating both modalities is crucial for learning representations for robotic perception and control. However, current research predominantly focuses on only one of these modalities, neglecting the benefits of incorporating both. To this end, we present $\textbf{Semantic-Geometric Representation} (\textbf{SGR})$, a universal perception module for robotics that leverages the rich semantic information of large-scale pre-trained 2D models and inherits the merits of 3D spatial reasoning. Our experiments demonstrate that SGR empowers the agent to successfully complete a diverse range of simulated and real-world robotic manipulation tasks, outperforming state-of-the-art methods significantly in both single-task and multi-task settings. Furthermore, SGR possesses the capability to generalize to novel semantic attributes, setting it apart from the other methods. Project website: https://semantic-geometric-representation.github.io., Comment: CoRL 2023. Project website: https://semantic-geometric-representation.github.io

Monocular scene understanding is a foundational component of autonomous systems. Within the spectrum of monocular perception topics, one crucial and useful task for holistic 3D scene understanding is semantic scene completion (SSC), which jointly completes semantic information and geometric details from RGB input. However, progress in SSC, particularly in large-scale street views, is hindered by the scarcity of high-quality datasets. To address this issue, we introduce SSCBench, a comprehensive benchmark that integrates scenes from widely used automotive datasets (e.g., KITTI-360, nuScenes, and Waymo). SSCBench follows an established setup and format in the community, facilitating the easy exploration of SSC methods in various street views. We benchmark models using monocular, trinocular, and point cloud input to assess the performance gap resulting from sensor coverage and modality. Moreover, we have unified semantic labels across diverse datasets to simplify cross-domain generalization testing. We commit to including more datasets and SSC models to drive further advancements in this field., Comment: IROS 2024

Large language models (LLMs) with memory are computationally universal. However, mainstream LLMs are not taking full advantage of memory, and the designs are heavily influenced by biological brains. Due to their approximate nature and proneness to the accumulation of errors, conventional neural memory mechanisms cannot support LLMs to simulate complex reasoning. In this paper, we seek inspiration from modern computer architectures to augment LLMs with symbolic memory for complex multi-hop reasoning. Such a symbolic memory framework is instantiated as an LLM and a set of SQL databases, where the LLM generates SQL instructions to manipulate the SQL databases. We validate the effectiveness of the proposed memory framework on a synthetic dataset requiring complex reasoning. The project website is available at https://chatdatabase.github.io/ .

This paper tries to address a fundamental question in point cloud self-supervised learning: what is a good signal we should leverage to learn features from point clouds without annotations? To answer that, we introduce a point cloud representation learning framework, based on geometric feature reconstruction. In contrast to recent papers that directly adopt masked autoencoder (MAE) and only predict original coordinates or occupancy from masked point clouds, our method revisits differences between images and point clouds and identifies three self-supervised learning objectives peculiar to point clouds, namely centroid prediction, normal estimation, and curvature prediction. Combined with occupancy prediction, these four objectives yield an nontrivial self-supervised learning task and mutually facilitate models to better reason fine-grained geometry of point clouds. Our pipeline is conceptually simple and it consists of two major steps: first, it randomly masks out groups of points, followed by a Transformer-based point cloud encoder; second, a lightweight Transformer decoder predicts centroid, normal, and curvature for points in each voxel. We transfer the pre-trained Transformer encoder to a downstream peception model. On the nuScene Datset, our model achieves 3.38 mAP improvment for object detection, 2.1 mIoU gain for segmentation, and 1.7 AMOTA gain for multi-object tracking. We also conduct experiments on the Waymo Open Dataset and achieve significant performance improvements over baselines as well., Comment: Accepted to CVPR 2023