Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement

Large language model agents have exhibited exceptional performance across a range of complex interactive tasks. Recent approaches have utilized tuning with expert trajectories to enhance agent performance, yet they primarily concentrate on outcome rewards, which may lead to errors or suboptimal actions due to the absence of process supervision signals. In this paper, we introduce the Iterative step-level Process Refinement (IPR) framework, which provides detailed step-by-step guidance to enhance agent training. Specifically, we adopt the Monte Carlo method to estimate step-level rewards. During each iteration, the agent explores along the expert trajectory and generates new actions. These actions are then evaluated against the corresponding step of expert trajectory using step-level rewards. Such comparison helps identify discrepancies, yielding contrastive action pairs that serve as training data for the agent. Our experiments on three complex agent tasks demonstrate that our framework outperforms a variety of strong baselines. Moreover, our analytical findings highlight the effectiveness of IPR in augmenting action efficiency and its applicability to diverse models.

Technique Report of CVPR 2024 PBDL Challenges

The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to inform and enhance deep learning models, we can develop more robust and accurate vision systems. Physics-based vision aims to invert the processes to recover scene properties such as shape, reflectance, light distribution, and medium properties from images. In recent years, deep learning has shown promising improvements for various vision tasks, and when combined with physics-based vision, these approaches can enhance the robustness and accuracy of vision systems. This technical report summarizes the outcomes of the Physics-Based Vision Meets Deep Learning (PBDL) 2024 challenge, held in CVPR 2024 workshop. The challenge consisted of eight tracks, focusing on Low-Light Enhancement and Detection as well as High Dynamic Range (HDR) Imaging. This report details the objectives, methodologies, and results of each track, highlighting the top-performing solutions and their innovative approaches.

CulturePark: Boosting Cross-cultural Understanding in Large Language Models

Cultural bias is pervasive in many large language models (LLMs), largely due to the deficiency of data representative of different cultures. Typically, cultural datasets and benchmarks are constructed either by extracting subsets of existing datasets or by aggregating from platforms such as Wikipedia and social media. However, these approaches are highly dependent on real-world data and human annotations, making them costly and difficult to scale. Inspired by cognitive theories on social communication, this paper introduces CulturePark, an LLM-powered multi-agent communication framework for cultural data collection. CulturePark simulates cross-cultural human communication with LLM-based agents playing roles in different cultures. It generates high-quality cross-cultural dialogues encapsulating human beliefs, norms, and customs. Using CulturePark, we generated 41,000 cultural samples to fine-tune eight culture-specific LLMs. We evaluated these models across three downstream tasks: content moderation, cultural alignment, and cultural education. Results show that for content moderation, our GPT-3.5-based models either match or outperform GPT-4 on datasets. Regarding cultural alignment, our models surpass GPT-4 on Hofstede's VSM 13 framework. Furthermore, for cultural education of human participants, our models demonstrate superior outcomes in both learning efficacy and user experience compared to GPT-4. CulturePark proves an important step in addressing cultural bias and advancing the democratization of AI, highlighting the critical role of culturally inclusive data in model training.

Autonomous Sparse Mean-CVaR Portfolio Optimization

The $\ell_0$-constrained mean-CVaR model poses a significant challenge due to its NP-hard nature, typically tackled through combinatorial methods characterized by high computational demands. From a markedly different perspective, we propose an innovative autonomous sparse mean-CVaR portfolio model, capable of approximating the original $\ell_0$-constrained mean-CVaR model with arbitrary accuracy. The core idea is to convert the $\ell_0$ constraint into an indicator function and subsequently handle it through a tailed approximation. We then propose a proximal alternating linearized minimization algorithm, coupled with a nested fixed-point proximity algorithm (both convergent), to iteratively solve the model. Autonomy in sparsity refers to retaining a significant portion of assets within the selected asset pool during adjustments in pool size. Consequently, our framework offers a theoretically guaranteed approximation of the $\ell_0$-constrained mean-CVaR model, improving computational efficiency while providing a robust asset selection scheme.

MIPI 2024 Challenge on Demosaic for HybridEVS Camera: Methods and Results

The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algorithms in camera systems. However, the scarcity of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). Building on the achievements of the previous MIPI Workshops held at ECCV 2022 and CVPR 2023, we introduce our third MIPI challenge including three tracks focusing on novel image sensors and imaging algorithms. In this paper, we summarize and review the Nighttime Flare Removal track on MIPI 2024. In total, 170 participants were successfully registered, and 14 teams submitted results in the final testing phase. The developed solutions in this challenge achieved state-of-the-art performance on Nighttime Flare Removal. More details of this challenge and the link to the dataset can be found at https://mipi-challenge.org/MIPI2024/.

DeepMpMRI: Tensor-decomposition Regularized Learning for Fast and High-Fidelity Multi-Parametric Microstructural MR Imaging

Deep learning has emerged as a promising approach for learning the nonlinear mapping between diffusion-weighted MR images and tissue parameters, which enables automatic and deep understanding of the brain microstructures. However, the efficiency and accuracy in the multi-parametric estimations are still limited since previous studies tend to estimate multi-parametric maps with dense sampling and isolated signal modeling. This paper proposes DeepMpMRI, a unified framework for fast and high-fidelity multi-parametric estimation from various diffusion models using sparsely sampled q-space data. DeepMpMRI is equipped with a newly designed tensor-decomposition-based regularizer to effectively capture fine details by exploiting the correlation across parameters. In addition, we introduce a Nesterov-based adaptive learning algorithm that optimizes the regularization parameter dynamically to enhance the performance. DeepMpMRI is an extendable framework capable of incorporating flexible network architecture. Experimental results demonstrate the superiority of our approach over 5 state-of-the-art methods in simultaneously estimating multi-parametric maps for various diffusion models with fine-grained details both quantitatively and qualitatively, achieving 4.5 - 22.5$\times$ acceleration compared to the dense sampling of a total of 270 diffusion gradients.

NegativePrompt: Leveraging Psychology for Large Language Models Enhancement via Negative Emotional Stimuli

Large Language Models (LLMs) have become integral to a wide spectrum of applications, ranging from traditional computing tasks to advanced artificial intelligence (AI) applications. This widespread adoption has spurred extensive research into LLMs across various disciplines, including the social sciences. Notably, studies have revealed that LLMs possess emotional intelligence, which can be further developed through positive emotional stimuli. This discovery raises an intriguing question: can negative emotions similarly influence LLMs, potentially enhancing their performance? In response to this question, we introduce NegativePrompt, a novel approach underpinned by psychological principles, involving ten specifically designed negative emotional stimuli. We embark on rigorous experimental evaluations of five LLMs including Flan-T5-Large, Vicuna, Llama 2, ChatGPT, and GPT-4, across a set of 45 tasks. The results are revealing: NegativePrompt markedly enhances the performance of LLMs, evidenced by relative improvements of 12.89% in Instruction Induction tasks and 46.25% in BIG-Bench tasks. Moreover, we conduct attention visualization experiments to decipher the underlying mechanisms of NegativePrompt's influence. Our research contributes significantly to the understanding of LLMs and emotion interaction, demonstrating the practical efficacy of NegativePrompt as an emotion-driven method and offering novel insights for the enhancement of LLMs in real-world applications. The code is available at https://github.com/wangxu0820/NegativePrompt.

CSR-dMRI: Continuous Super-Resolution of Diffusion MRI with Anatomical Structure-assisted Implicit Neural Representation Learning

Deep learning-based dMRI super-resolution methods can effectively enhance image resolution by leveraging the learning capabilities of neural networks on large datasets. However, these methods tend to learn a fixed scale mapping between low-resolution (LR) and high-resolution (HR) images, overlooking the need for radiologists to scale the images at arbitrary resolutions. Moreover, the pixel-wise loss in the image domain tends to generate over-smoothed results, losing fine textures and edge information. To address these issues, we propose a novel continuous super-resolution of dMRI with anatomical structure-assisted implicit neural representation learning method, called CSR-dMRI. Specifically, the CSR-dMRI model consists of two components. The first is the latent feature extractor, which primarily extracts latent space feature maps from LR dMRI and anatomical images while learning structural prior information from the anatomical images. The second is the implicit function network, which utilizes voxel coordinates and latent feature vectors to generate voxel intensities at corresponding positions. Additionally, a frequency-domain-based loss is introduced to preserve the structural and texture information, further enhancing the image quality. Extensive experiments on the publicly available HCP dataset validate the effectiveness of our approach. Furthermore, our method demonstrates superior generalization capability and can be applied to arbitrary-scale super-resolution, including non-integer scale factors, expanding its applicability beyond conventional approaches.

Automating Vessel Segmentation in the Heart and Brain: A Trend to Develop Multi-Modality and Label-Efficient Deep Learning Techniques

Cardio-cerebrovascular diseases are the leading causes of mortality worldwide, whose accurate blood vessel segmentation is significant for both scientific research and clinical usage. However, segmenting cardio-cerebrovascular structures from medical images is very challenging due to the presence of thin or blurred vascular shapes, imbalanced distribution of vessel and non-vessel pixels, and interference from imaging artifacts. These difficulties make manual or semi-manual segmentation methods highly time-consuming, labor-intensive, and prone to errors with interobserver variability, where different experts may produce different segmentations from a variety of modalities. Consequently, there is a growing interest in developing automated algorithms. This paper provides an up-to-date survey of deep learning techniques, for cardio-cerebrovascular segmentation. It analyzes the research landscape, surveys recent approaches, and discusses challenges such as the scarcity of accurately annotated data and variability. This paper also illustrates the urgent needs for developing multi-modality label-efficient deep learning techniques. To the best of our knowledge, this paper is the first comprehensive survey of deep learning approaches that effectively segment vessels in both the heart and brain. It aims to advance automated segmentation techniques for cardio-cerebrovascular diseases, benefiting researchers and healthcare professionals.

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

In this report, we present the latest model of the Gemini family, Gemini 1.5 Pro, a highly compute-efficient multimodal mixture-of-experts model capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. Gemini 1.5 Pro achieves near-perfect recall on long-context retrieval tasks across modalities, improves the state-of-the-art in long-document QA, long-video QA and long-context ASR, and matches or surpasses Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5 Pro's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 2.1 (200k) and GPT-4 Turbo (128k). Finally, we highlight surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.