The exploration of Bird's-Eye View (BEV) mapping technology has driven significant innovation in visual perception technology for autonomous driving. BEV mapping models need to be applied to the unlabeled real world, making the study of unsupervised domain adaptation models an essential path. However, research on unsupervised domain adaptation for BEV mapping remains limited and cannot perfectly accommodate all BEV mapping tasks. To address this gap, this paper proposes HierDAMap, a universal and holistic BEV domain adaptation framework with hierarchical perspective priors. Unlike existing research that solely focuses on image-level learning using prior knowledge, this paper explores the guiding role of perspective prior knowledge across three distinct levels: global, sparse, and instance levels. With these priors, HierDA consists of three essential components, including Semantic-Guided Pseudo Supervision (SGPS), Dynamic-Aware Coherence Learning (DACL), and Cross-Domain Frustum Mixing (CDFM). SGPS constrains the cross-domain consistency of perspective feature distribution through pseudo labels generated by vision foundation models in 2D space. To mitigate feature distribution discrepancies caused by spatial variations, DACL employs uncertainty-aware predicted depth as an intermediary to derive dynamic BEV labels from perspective pseudo-labels, thereby constraining the coarse BEV features derived from corresponding perspective features. CDFM, on the other hand, leverages perspective masks of view frustum to mix multi-view perspective images from both domains, which guides cross-domain view transformation and encoding learning through mixed BEV labels. The proposed method is verified on multiple BEV mapping tasks, such as BEV semantic segmentation, high-definition semantic, and vectorized mapping. The source code will be made publicly available at https://github.com/lynn-yu/HierDAMap.

How can "weak teacher models" such as average human annotators or existing AI systems, effectively supervise LLMs to improve performance on hard reasoning tasks, especially those that challenge and requires expertise or daily practice from the teacher models? In this paper, we seek for empirical answers to this question by investigating various data-driven strategies that offer supervision data at different quality levels upon tasks of varying complexity. Two intuitive strategies emerge for teacher models to provide supervision during alignment training: 1) using lower-quality supervision from complete tasks that match the difficulty of the target reasoning tasks, and 2) leveraging higher-quality supervision from easier subtasks that are less challenging. Interestingly, we find that even when the outcome error rate for hard task supervision is high (e.g., 90\%), training on such data can outperform perfectly correct supervision on easier subtasks on multiple hard math benchmarks. We further identify a more critical factor influencing training performance: step-wise error rates, which indicate the severity of errors in solutions. Specifically, training on hard task supervision with the same outcome error rates but disparate step-wise error rates can lead to a 30\% accuracy gap on MATH benchmark. Our results also reveal that supplementing hard task supervision with the corresponding subtask supervision can yield notable performance improvements than simply combining rephrased hard full task supervision, suggesting new avenues for data augmentation. Data and code are released at \url{https://github.com/hexuan21/Weak-to-Strong}.

The recent years have witnessed great advances in video generation. However, the development of automatic video metrics is lagging significantly behind. None of the existing metric is able to provide reliable scores over generated videos. The main barrier is the lack of large-scale human-annotated dataset. In this paper, we release VideoFeedback, the first large-scale dataset containing human-provided multi-aspect score over 37.6K synthesized videos from 11 existing video generative models. We train VideoScore (initialized from Mantis) based on VideoFeedback to enable automatic video quality assessment. Experiments show that the Spearman correlation between VideoScore and humans can reach 77.1 on VideoFeedback-test, beating the prior best metrics by about 50 points. Further result on other held-out EvalCrafter, GenAI-Bench, and VBench show that VideoScore has consistently much higher correlation with human judges than other metrics. Due to these results, we believe VideoScore can serve as a great proxy for human raters to (1) rate different video models to track progress (2) simulate fine-grained human feedback in Reinforcement Learning with Human Feedback (RLHF) to improve current video generation models.

In the age of large-scale language models, benchmarks like the Massive Multitask Language Understanding (MMLU) have been pivotal in pushing the boundaries of what AI can achieve in language comprehension and reasoning across diverse domains. However, as models continue to improve, their performance on these benchmarks has begun to plateau, making it increasingly difficult to discern differences in model capabilities. This paper introduces MMLU-Pro, an enhanced dataset designed to extend the mostly knowledge-driven MMLU benchmark by integrating more challenging, reasoning-focused questions and expanding the choice set from four to ten options. Additionally, MMLU-Pro eliminates the trivial and noisy questions in MMLU. Our experimental results show that MMLU-Pro not only raises the challenge, causing a significant drop in accuracy by 16% to 33% compared to MMLU but also demonstrates greater stability under varying prompts. With 24 different prompt styles tested, the sensitivity of model scores to prompt variations decreased from 4-5% in MMLU to just 2% in MMLU-Pro. Additionally, we found that models utilizing Chain of Thought (CoT) reasoning achieved better performance on MMLU-Pro compared to direct answering, which is in stark contrast to the findings on the original MMLU, indicating that MMLU-Pro includes more complex reasoning questions. Our assessments confirm that MMLU-Pro is a more discriminative benchmark to better track progress in the field. Figure 1: Comparing between MMLU and MMLU-Pro: (Left) Performance gap; (Center) Accuracy distributions affected by 24 prompts, with taller and thinner profiles indicating more stability and shorter and wider profiles indicating greater fluctuations; (Right) Performance using CoT vs. Direct.

Large multimodal models (LMMs) have shown great results in single-image vision language tasks. However, their abilities to solve multi-image visual language tasks is yet to be improved. The existing LMMs like OpenFlamingo, Emu2, Idefics gain their multi-image ability through pre-training on hundreds of millions of noisy interleaved image-text data from the web, which is neither efficient nor effective. In this paper, we aim to build strong multi-image LMMs via instruction tuning with academic-level resources. Therefore, we meticulously construct Mantis-Instruct containing 721K multi-image instruction data to train a family of models Mantis. The instruction tuning empowers Mantis with different multi-image skills like co-reference, comparison, reasoning, and temporal understanding. We evaluate Mantis on five multi-image benchmarks and seven single-image benchmarks. Mantis-SigLIP can achieve SoTA results on all the multi-image benchmarks and beat the strongest multi-image baseline, Idefics2-8B by an average of 11 absolute points. Notably, Idefics2-8B was pre-trained on 140M interleaved multi-image data, which is 200x larger than Mantis-Instruct. We observe that Mantis performs equivalently well on the held-in and held-out benchmarks, which shows its generalization ability. Notably, we found that Mantis can even match the performance of GPT-4V on multi-image benchmarks. We further evaluate Mantis on single-image benchmarks and demonstrate that Mantis also maintains a strong single-image performance on par with CogVLM and Emu2. Our results show that multi-image abilities are not necessarily gained through massive pre-training, instead, it can be gained by the low-cost instruction tuning. Our work provides new perspectives on how to improve LMMs' multi-image abilities.

Mixture-of-Experts (MoE) architectures have recently gained increasing popularity within the domain of large language models (LLMs) due to their ability to significantly reduce training and inference overhead. However, MoE architectures face challenges, such as significant disparities in the number of tokens assigned to each expert and a tendency toward homogenization among experts, which adversely affects the model's semantic generation capabilities. In this paper, we introduce LocMoE+, a refined version of the low-overhead LocMoE, incorporating the following enhancements: (1) Quantification and definition of the affinity between experts and tokens. (2) Implementation of a global-level adaptive routing strategy to rearrange tokens based on their affinity scores. (3) Reestimation of the lower bound for expert capacity, which has been shown to progressively decrease as the token feature distribution evolves. Experimental results demonstrate that, without compromising model convergence or efficacy, the number of tokens each expert processes can be reduced by over 60%. Combined with communication optimizations, this leads to an average improvement in training efficiency ranging from 5.4% to 46.6%. After fine-tuning, LocMoE+ exhibits a performance improvement of 9.7% to 14.1% across the GDAD, C-Eval, and TeleQnA datasets.

End-to-end transformer-based detectors (DETRs) have shown exceptional performance in both closed-set and open-vocabulary object detection (OVD) tasks through the integration of language modalities. However, their demanding computational requirements have hindered their practical application in real-time object detection (OD) scenarios. In this paper, we scrutinize the limitations of two leading models in the OVDEval benchmark, OmDet and Grounding-DINO, and introduce OmDet-Turbo. This novel transformer-based real-time OVD model features an innovative Efficient Fusion Head (EFH) module designed to alleviate the bottlenecks observed in OmDet and Grounding-DINO. Notably, OmDet-Turbo-Base achieves a 100.2 frames per second (FPS) with TensorRT and language cache techniques applied. Notably, in zero-shot scenarios on COCO and LVIS datasets, OmDet-Turbo achieves performance levels nearly on par with current state-of-the-art supervised models. Furthermore, it establishes new state-of-the-art benchmarks on ODinW and OVDEval, boasting an AP of 30.1 and an NMS-AP of 26.86, respectively. The practicality of OmDet-Turbo in industrial applications is underscored by its exceptional performance on benchmark datasets and superior inference speed, positioning it as a compelling choice for real-time object detection tasks.

This paper introduces the task of Auditory Referring Multi-Object Tracking (AR-MOT), which dynamically tracks specific objects in a video sequence based on audio expressions and appears as a challenging problem in autonomous driving. Due to the lack of semantic modeling capacity in audio and video, existing works have mainly focused on text-based multi-object tracking, which often comes at the cost of tracking quality, interaction efficiency, and even the safety of assistance systems, limiting the application of such methods in autonomous driving. In this paper, we delve into the problem of AR-MOT from the perspective of audio-video fusion and audio-video tracking. We put forward EchoTrack, an end-to-end AR-MOT framework with dual-stream vision transformers. The dual streams are intertwined with our Bidirectional Frequency-domain Cross-attention Fusion Module (Bi-FCFM), which bidirectionally fuses audio and video features from both frequency- and spatiotemporal domains. Moreover, we propose the Audio-visual Contrastive Tracking Learning (ACTL) regime to extract homogeneous semantic features between expressions and visual objects by learning homogeneous features between different audio and video objects effectively. Aside from the architectural design, we establish the first set of large-scale AR-MOT benchmarks, including Echo-KITTI, Echo-KITTI+, and Echo-BDD. Extensive experiments on the established benchmarks demonstrate the effectiveness of the proposed EchoTrack model and its components. The source code and datasets will be made publicly available at https://github.com/lab206/EchoTrack.

The Mixtures-of-Experts (MoE) model is a widespread distributed and integrated learning method for large language models (LLM), which is favored due to its ability to sparsify and expand models efficiently. However, the performance of MoE is limited by load imbalance and high latency of All-To-All communication, along with relatively redundant computation owing to large expert capacity. Load imbalance may result from existing routing policies that consistently tend to select certain experts. The frequent inter-node communication in the All-To-All procedure also significantly prolongs the training time. To alleviate the above performance problems, we propose a novel routing strategy that combines load balance and locality by converting partial inter-node communication to that of intra-node. Notably, we elucidate that there is a minimum threshold for expert capacity, calculated through the maximal angular deviation between the gating weights of the experts and the assigned tokens. We port these modifications on the PanGu-Sigma model based on the MindSpore framework with multi-level routing and conduct experiments on Ascend clusters. The experiment results demonstrate that the proposed LocMoE reduces training time per epoch by 12.68% to 22.24% compared to classical routers, such as hash router and switch router, without impacting the model accuracy.

Recently, transformer-based methods have shown exceptional performance in monocular 3D object detection, which can predict 3D attributes from a single 2D image. These methods typically use visual and depth representations to generate query points on objects, whose quality plays a decisive role in the detection accuracy. However, current unsupervised attention mechanisms without any geometry appearance awareness in transformers are susceptible to producing noisy features for query points, which severely limits the network performance and also makes the model have a poor ability to detect multi-category objects in a single training process. To tackle this problem, this paper proposes a novel "Supervised Shape&Scale-perceptive Deformable Attention" (S$^3$-DA) module for monocular 3D object detection. Concretely, S$^3$-DA utilizes visual and depth features to generate diverse local features with various shapes and scales and predict the corresponding matching distribution simultaneously to impose valuable shape&scale perception for each query. Benefiting from this, S$^3$-DA effectively estimates receptive fields for query points belonging to any category, enabling them to generate robust query features. Besides, we propose a Multi-classification-based Shape$\&$Scale Matching (MSM) loss to supervise the above process. Extensive experiments on KITTI and Waymo Open datasets demonstrate that S$^3$-DA significantly improves the detection accuracy, yielding state-of-the-art performance of single-category and multi-category 3D object detection in a single training process compared to the existing approaches. The source code will be made publicly available at https://github.com/mikasa3lili/S3-MonoDETR.