Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning

In-Context Learning (ICL) emerges as a key feature for Large Language Models (LLMs), allowing them to adapt to new tasks by leveraging task-specific examples without updating model parameters. However, ICL faces challenges with increasing numbers of examples due to performance degradation and quadratic computational costs. In this paper, we propose Logit Arithmetic Reweighting Approach (LARA), a novel framework that enhances ICL by using logit-based ensembling of multiple demonstrations. Our approach divides long input demonstrations into parallelizable shorter inputs to significantly reduce memory requirements, and then effectively aggregate the information by reweighting logits of each group via a non-gradient optimization approach. We further introduce Binary LARA (B-LARA), a variant that constrains weights to binary values to simplify the search space and reduces memory usage by filtering out less informative demonstration groups. Experiments on BBH and MMLU demonstrate that LARA and B-LARA outperform all baseline methods in both accuracy and memory efficiency. We also conduct extensive analysis to show that LARA generalizes well to scenarios of varying numbers of examples from limited to many-shot demonstrations.

Taming Overconfidence in LLMs: Reward Calibration in RLHF

Language model calibration refers to the alignment between the confidence of the model and the actual performance of its responses. While previous studies point out the overconfidence phenomenon in Large Language Models (LLMs) and show that LLMs trained with Reinforcement Learning from Human Feedback (RLHF) are overconfident with a more sharpened output probability, in this study, we reveal that RLHF tends to lead models to express verbalized overconfidence in their own responses. We investigate the underlying cause of this overconfidence and demonstrate that reward models used for Proximal Policy Optimization (PPO) exhibit inherent biases towards high-confidence scores regardless of the actual quality of responses. Building upon this insight, we propose two PPO variants: PPO-M: PPO with Calibrated Reward Modeling and PPO-C: PPO with Calibrated Reward Calculation. PPO-M integrates explicit confidence scores in reward model training, which calibrates reward models to better capture the alignment between response quality and verbalized confidence. PPO-C adjusts the reward score during PPO based on the difference between the current reward and the moving average of past rewards. Both PPO-M and PPO-C can be seamlessly integrated into the current PPO pipeline and do not require additional golden labels. We evaluate our methods on both Llama3-8B and Mistral-7B across six diverse datasets including multiple-choice and open-ended generation. Experiment results demonstrate that both of our methods can reduce calibration error and maintain performance comparable to standard PPO. We further show that they do not compromise model capabilities in open-ended conversation settings.

Efficient Depth-Guided Urban View Synthesis

Recent advances in implicit scene representation enable high-fidelity street view novel view synthesis. However, existing methods optimize a neural radiance field for each scene, relying heavily on dense training images and extensive computation resources. To mitigate this shortcoming, we introduce a new method called Efficient Depth-Guided Urban View Synthesis (EDUS) for fast feed-forward inference and efficient per-scene fine-tuning. Different from prior generalizable methods that infer geometry based on feature matching, EDUS leverages noisy predicted geometric priors as guidance to enable generalizable urban view synthesis from sparse input images. The geometric priors allow us to apply our generalizable model directly in the 3D space, gaining robustness across various sparsity levels. Through comprehensive experiments on the KITTI-360 and Waymo datasets, we demonstrate promising generalization abilities on novel street scenes. Moreover, our results indicate that EDUS achieves state-of-the-art performance in sparse view settings when combined with fast test-time optimization.

GOFA: A Generative One-For-All Model for Joint Graph Language Modeling

Foundation models, such as Large Language Models (LLMs) or Large Vision Models (LVMs), have emerged as one of the most powerful tools in the respective fields. However, unlike text and image data, graph data do not have a definitive structure, posing great challenges to developing a Graph Foundation Model (GFM). For example, current attempts at designing general graph models either transform graph data into a language format for LLM-based prediction or still train a GNN model with LLM as an assistant. The former can handle unlimited tasks, while the latter captures graph structure much better -- yet, no existing work can achieve both simultaneously. In this paper, we identify three key desirable properties of a GFM: self-supervised pretraining, fluidity in tasks, and graph awareness. To account for these properties, we extend the conventional language modeling to the graph domain and propose a novel generative graph language model GOFA to solve the problem. The model interleaves randomly initialized GNN layers into a frozen pre-trained LLM so that the semantic and structural modeling abilities are organically combined. GOFA is pre-trained on newly proposed graph-level next-word prediction, question-answering, and structural tasks to obtain the above GFM properties. The pre-trained model is further fine-tuned on downstream tasks to obtain task-solving ability. The fine-tuned model is evaluated on various downstream tasks, demonstrating a strong ability to solve structural and contextual problems in zero-shot scenarios. The code is available at https://github.com/JiaruiFeng/GOFA.

Optimizing Language Model's Reasoning Abilities with Weak Supervision

While Large Language Models (LLMs) have demonstrated proficiency in handling complex queries, much of the past work has depended on extensively annotated datasets by human experts. However, this reliance on fully-supervised annotations poses scalability challenges, particularly as models and data requirements grow. To mitigate this, we explore the potential of enhancing LLMs' reasoning abilities with minimal human supervision. In this work, we introduce self-reinforcement, which begins with Supervised Fine-Tuning (SFT) of the model using a small collection of annotated questions. Then it iteratively improves LLMs by learning from the differences in responses from the SFT and unfinetuned models on unlabeled questions. Our approach provides an efficient approach without relying heavily on extensive human-annotated explanations. However, current reasoning benchmarks typically only include golden-reference answers or rationales. Therefore, we present \textsc{PuzzleBen}, a weakly supervised benchmark that comprises 25,147 complex questions, answers, and human-generated rationales across various domains, such as brainteasers, puzzles, riddles, parajumbles, and critical reasoning tasks. A unique aspect of our dataset is the inclusion of 10,000 unannotated questions, enabling us to explore utilizing fewer supersized data to boost LLMs' inference capabilities. Our experiments underscore the significance of \textsc{PuzzleBen}, as well as the effectiveness of our methodology as a promising direction in future endeavors. Our dataset and code will be published soon on \texttt{Anonymity Link}.

Efficient Bi-manipulation using RGBD Multi-model Fusion based on Attention Mechanism

Dual-arm robots have great application prospects in intelligent manufacturing due to their human-like structure when deployed with advanced intelligence algorithm. However, the previous visuomotor policy suffers from perception deficiencies in environments where features of images are impaired by the various conditions, such as abnormal lighting, occlusion and shadow etc. The Focal CVAE framework is proposed for RGB-D multi-modal data fusion to address this challenge. In this study, a mixed focal attention module is designed for the fusion of RGB images containing color features and depth images containing 3D shape and structure information. This module highlights the prominent local features and focuses on the relevance of RGB and depth via cross-attention. A saliency attention module is proposed to improve its computational efficiency, which is applied in the encoder and the decoder of the framework. We illustrate the effectiveness of the proposed method via extensive simulation and experiments. It's shown that the performances of bi-manipulation are all significantly improved in the four real-world tasks with lower computational cost. Besides, the robustness is validated through experiments under different scenarios where there is a perception deficiency problem, demonstrating the feasibility of the method.

Practical Applications of Advanced Cloud Services and Generative AI Systems in Medical Image Analysis

The medical field is one of the important fields in the application of artificial intelligence technology. With the explosive growth and diversification of medical data, as well as the continuous improvement of medical needs and challenges, artificial intelligence technology is playing an increasingly important role in the medical field. Artificial intelligence technologies represented by computer vision, natural language processing, and machine learning have been widely penetrated into diverse scenarios such as medical imaging, health management, medical information, and drug research and development, and have become an important driving force for improving the level and quality of medical services.The article explores the transformative potential of generative AI in medical imaging, emphasizing its ability to generate syntheticACM-2 data, enhance images, aid in anomaly detection, and facilitate image-to-image translation. Despite challenges like model complexity, the applications of generative models in healthcare, including Med-PaLM 2 technology, show promising results. By addressing limitations in dataset size and diversity, these models contribute to more accurate diagnoses and improved patient outcomes. However, ethical considerations and collaboration among stakeholders are essential for responsible implementation. Through experiments leveraging GANs to augment brain tumor MRI datasets, the study demonstrates how generative AI can enhance image quality and diversity, ultimately advancing medical diagnostics and patient care.

Dynamic Resource Allocation for Virtual Machine Migration Optimization using Machine Learning

The paragraph is grammatically correct and logically coherent. It discusses the importance of mobile terminal cloud computing migration technology in meeting the demands of evolving computer and cloud computing technologies. It emphasizes the need for efficient data access and storage, as well as the utilization of cloud computing migration technology to prevent additional time delays. The paragraph also highlights the contributions of cloud computing migration technology to expanding cloud computing services. Additionally, it acknowledges the role of virtualization as a fundamental capability of cloud computing while emphasizing that cloud computing and virtualization are not inherently interconnected. Finally, it introduces machine learning-based virtual machine migration optimization and dynamic resource allocation as a critical research direction in cloud computing, citing the limitations of static rules or manual settings in traditional cloud computing environments. Overall, the paragraph effectively communicates the importance of machine learning technology in addressing resource allocation and virtual machine migration challenges in cloud computing.

Application of Machine Learning Optimization in Cloud Computing Resource Scheduling and Management

In recent years, cloud computing has been widely used. Cloud computing refers to the centralized computing resources, users through the access to the centralized resources to complete the calculation, the cloud computing center will return the results of the program processing to the user. Cloud computing is not only for individual users, but also for enterprise users. By purchasing a cloud server, users do not have to buy a large number of computers, saving computing costs. According to a report by China Economic News Network, the scale of cloud computing in China has reached 209.1 billion yuan. At present, the more mature cloud service providers in China are Ali Cloud, Baidu Cloud, Huawei Cloud and so on. Therefore, this paper proposes an innovative approach to solve complex problems in cloud computing resource scheduling and management using machine learning optimization techniques. Through in-depth study of challenges such as low resource utilization and unbalanced load in the cloud environment, this study proposes a comprehensive solution, including optimization methods such as deep learning and genetic algorithm, to improve system performance and efficiency, and thus bring new breakthroughs and progress in the field of cloud computing resource management.Rational allocation of resources plays a crucial role in cloud computing. In the resource allocation of cloud computing, the cloud computing center has limited cloud resources, and users arrive in sequence. Each user requests the cloud computing center to use a certain number of cloud resources at a specific time.

Fractal Gripper: Adaptive manipulator with mode switching

Although the multi-jointed underactuated manipulator is highly dexterous, its grasping capacity does not match that of the parallel jaw gripper. This work introduces a fractal gripper to enhance the grasping capacity of multi-joint underactuated manipulators, preserving their passive clamping features. We describe in detail the working principle and manufacturing process of the fractal gripper. This work, inspired by the 'Fractal Vise' structure, resulted in the invention of a fractal gripper with mode switching capabilities. The fractal gripper inherits the inherent adaptive properties of the fractal structure and realizes the self-resetting function by integrating spring into the original design, thereby enhancing the efficiency of object grasping tasks. The fractal gripper prevents object damage by distributing pressure evenly and applying it at multiple points through its fractal structure during closure. Objects of various shapes are effectively grasped by the fractal gripper, which ensures a safe and secure grasp. The superior performance was provided by the force distribution characteristics of the fractal gripper. By applying the flexible polymer PDMS, which possesses superior elasticity, to the fractal structure's wrapping surface, potential scratching during grasping is effectively prevented, thus protecting the object's geometric surface. Grab experiments with objects of diverse shapes and sizes confirm fractal gripper multi-scale adaptability and superior grasping stability.