PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training

This paper aims to address the challenge of hallucinations in Multimodal Large Language Models (MLLMs) particularly for dense image captioning tasks. To tackle the challenge, we identify the current lack of a metric that finely measures the caption quality in concept level. We hereby introduce HalFscore, a novel metric built upon the language graph and is designed to evaluate both the accuracy and completeness of dense captions at a granular level. Additionally, we identify the root cause of hallucination as the model's over-reliance on its language prior. To address this, we propose PerturboLLaVA, which reduces the model's reliance on the language prior by incorporating adversarially perturbed text during training. This method enhances the model's focus on visual inputs, effectively reducing hallucinations and producing accurate, image-grounded descriptions without incurring additional computational overhead. PerturboLLaVA significantly improves the fidelity of generated captions, outperforming existing approaches in handling multimodal hallucinations and achieving improved performance across general multimodal benchmarks.

DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks

Our primary goal here is to create a good, generalist perception model that can tackle multiple tasks, within limits on computational resources and training data. To achieve this, we resort to text-to-image diffusion models pre-trained on billions of images. Our exhaustive evaluation metrics demonstrate that DICEPTION effectively tackles multiple perception tasks, achieving performance on par with state-of-the-art models. We achieve results on par with SAM-vit-h using only 0.06% of their data (e.g., 600K vs. 1B pixel-level annotated images). Inspired by Wang et al., DICEPTION formulates the outputs of various perception tasks using color encoding; and we show that the strategy of assigning random colors to different instances is highly effective in both entity segmentation and semantic segmentation. Unifying various perception tasks as conditional image generation enables us to fully leverage pre-trained text-to-image models. Thus, DICEPTION can be efficiently trained at a cost of orders of magnitude lower, compared to conventional models that were trained from scratch. When adapting our model to other tasks, it only requires fine-tuning on as few as 50 images and 1% of its parameters. DICEPTION provides valuable insights and a more promising solution for visual generalist models. Homepage: https://aim-uofa.github.io/Diception, Huggingface Demo: https://huggingface.co/spaces/Canyu/Diception-Demo.

TUMTraffic-VideoQA: A Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes

We present TUMTraffic-VideoQA, a novel dataset and benchmark designed for spatio-temporal video understanding in complex roadside traffic scenarios. The dataset comprises 1,000 videos, featuring 85,000 multiple-choice QA pairs, 2,300 object captioning, and 5,700 object grounding annotations, encompassing diverse real-world conditions such as adverse weather and traffic anomalies. By incorporating tuple-based spatio-temporal object expressions, TUMTraffic-VideoQA unifies three essential tasks-multiple-choice video question answering, referred object captioning, and spatio-temporal object grounding-within a cohesive evaluation framework. We further introduce the TUMTraffic-Qwen baseline model, enhanced with visual token sampling strategies, providing valuable insights into the challenges of fine-grained spatio-temporal reasoning. Extensive experiments demonstrate the dataset's complexity, highlight the limitations of existing models, and position TUMTraffic-VideoQA as a robust foundation for advancing research in intelligent transportation systems. The dataset and benchmark are publicly available to facilitate further exploration.

MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation

Recent advancements in video generation models, like Stable Video Diffusion, show promising results, but primarily focus on short, single-scene videos. These models struggle with generating long videos that involve multiple scenes, coherent narratives, and consistent characters. Furthermore, there is no publicly available dataset tailored for the analysis, evaluation, and training of long video generation models. In this paper, we present MovieBench: A Hierarchical Movie-Level Dataset for Long Video Generation, which addresses these challenges by providing unique contributions: (1) movie-length videos featuring rich, coherent storylines and multi-scene narratives, (2) consistency of character appearance and audio across scenes, and (3) hierarchical data structure contains high-level movie information and detailed shot-level descriptions. Experiments demonstrate that MovieBench brings some new insights and challenges, such as maintaining character ID consistency across multiple scenes for various characters. The dataset will be public and continuously maintained, aiming to advance the field of long video generation. Data can be found at: https://weijiawu.github.io/MovieBench/.

WARM-3D: A Weakly-Supervised Sim2Real Domain Adaptation Framework for Roadside Monocular 3D Object Detection

Existing roadside perception systems are limited by the absence of publicly available, large-scale, high-quality 3D datasets. Exploring the use of cost-effective, extensive synthetic datasets offers a viable solution to tackle this challenge and enhance the performance of roadside monocular 3D detection. In this study, we introduce the TUMTraf Synthetic Dataset, offering a diverse and substantial collection of high-quality 3D data to augment scarce real-world datasets. Besides, we present WARM-3D, a concise yet effective framework to aid the Sim2Real domain transfer for roadside monocular 3D detection. Our method leverages cheap synthetic datasets and 2D labels from an off-the-shelf 2D detector for weak supervision. We show that WARM-3D significantly enhances performance, achieving a +12.40% increase in mAP 3D over the baseline with only pseudo-2D supervision. With 2D GT as weak labels, WARM-3D even reaches performance close to the Oracle baseline. Moreover, WARM-3D improves the ability of 3D detectors to unseen sample recognition across various real-world environments, highlighting its potential for practical applications.

Take A Step Back: Rethinking the Two Stages in Visual Reasoning

Visual reasoning, as a prominent research area, plays a crucial role in AI by facilitating concept formation and interaction with the world. However, current works are usually carried out separately on small datasets thus lacking generalization ability. Through rigorous evaluation of diverse benchmarks, we demonstrate the shortcomings of existing ad-hoc methods in achieving cross-domain reasoning and their tendency to data bias fitting. In this paper, we revisit visual reasoning with a two-stage perspective: (1) symbolization and (2) logical reasoning given symbols or their representations. We find that the reasoning stage is better at generalization than symbolization. Thus, it is more efficient to implement symbolization via separated encoders for different data domains while using a shared reasoner. Given our findings, we establish design principles for visual reasoning frameworks following the separated symbolization and shared reasoning. The proposed two-stage framework achieves impressive generalization ability on various visual reasoning tasks, including puzzles, physical prediction, and visual question answering (VQA), encompassing both 2D and 3D modalities. We believe our insights will pave the way for generalizable visual reasoning.

MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence

Recent advancements in video generation have primarily leveraged diffusion models for short-duration content. However, these approaches often fall short in modeling complex narratives and maintaining character consistency over extended periods, which is essential for long-form video production like movies. We propose MovieDreamer, a novel hierarchical framework that integrates the strengths of autoregressive models with diffusion-based rendering to pioneer long-duration video generation with intricate plot progressions and high visual fidelity. Our approach utilizes autoregressive models for global narrative coherence, predicting sequences of visual tokens that are subsequently transformed into high-quality video frames through diffusion rendering. This method is akin to traditional movie production processes, where complex stories are factorized down into manageable scene capturing. Further, we employ a multimodal script that enriches scene descriptions with detailed character information and visual style, enhancing continuity and character identity across scenes. We present extensive experiments across various movie genres, demonstrating that our approach not only achieves superior visual and narrative quality but also effectively extends the duration of generated content significantly beyond current capabilities. Homepage: https://aim-uofa.github.io/MovieDreamer/.

Look Within, Why LLMs Hallucinate: A Causal Perspective

The emergence of large language models (LLMs) is a milestone in generative artificial intelligence, achieving significant success in text comprehension and generation tasks. Despite the tremendous success of LLMs in many downstream tasks, they suffer from severe hallucination problems, posing significant challenges to the practical applications of LLMs. Most of the works about LLMs' hallucinations focus on data quality. Self-attention is a core module in transformer-based LLMs, while its potential relationship with LLMs' hallucination has been hardly investigated. To fill this gap, we study this problem from a causal perspective. We propose a method to intervene in LLMs' self-attention layers and maintain their structures and sizes intact. Specifically, we disable different self-attention layers in several popular open-source LLMs and then compare their degrees of hallucination with the original ones. We evaluate the intervened LLMs on hallucination assessment benchmarks and conclude that disabling some specific self-attention layers in the front or tail of the LLMs can alleviate hallucination issues. The study paves a new way for understanding and mitigating LLMs' hallucinations.

A Transformer variant for multi-step forecasting of water level and hydrometeorological sensitivity analysis based on explainable artificial intelligence technology

Understanding the combined influences of meteorological and hydrological factors on water level and flood events is essential, particularly in today's changing climate environments. Transformer, as one kind of the cutting-edge deep learning methods, offers an effective approach to model intricate nonlinear processes, enables the extraction of key features and water level predictions. EXplainable Artificial Intelligence (XAI) methods play important roles in enhancing the understandings of how different factors impact water level. In this study, we propose a Transformer variant by integrating sparse attention mechanism and introducing nonlinear output layer for the decoder module. The variant model is utilized for multi-step forecasting of water level, by considering meteorological and hydrological factors simultaneously. It is shown that the variant model outperforms traditional Transformer across different lead times with respect to various evaluation metrics. The sensitivity analyses based on XAI technology demonstrate the significant influence of meteorological factors on water level evolution, in which temperature is shown to be the most dominant meteorological factor. Therefore, incorporating both meteorological and hydrological factors is necessary for reliable hydrological prediction and flood prevention. In the meantime, XAI technology provides insights into certain predictions, which is beneficial for understanding the prediction results and evaluating the reasonability.

GraphRelate3D: Context-Dependent 3D Object Detection with Inter-Object Relationship Graphs

Accurate and effective 3D object detection is critical for ensuring the driving safety of autonomous vehicles. Recently, state-of-the-art two-stage 3D object detectors have exhibited promising performance. However, these methods refine proposals individually, ignoring the rich contextual information in the object relationships between the neighbor proposals. In this study, we introduce an object relation module, consisting of a graph generator and a graph neural network (GNN), to learn the spatial information from certain patterns to improve 3D object detection. Specifically, we create an inter-object relationship graph based on proposals in a frame via the graph generator to connect each proposal with its neighbor proposals. Afterward, the GNN module extracts edge features from the generated graph and iteratively refines proposal features with the captured edge features. Ultimately, we leverage the refined features as input to the detection head to obtain detection results. Our approach improves upon the baseline PV-RCNN on the KITTI validation set for the car class across easy, moderate, and hard difficulty levels by 0.82%, 0.74%, and 0.58%, respectively. Additionally, our method outperforms the baseline by more than 1% under the moderate and hard levels BEV AP on the test server.