$\text{R}^2$-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations

Referring perception, which aims at grounding visual objects with multimodal referring guidance, is essential for bridging the gap between humans, who provide instructions, and the environment where intelligent systems perceive. Despite progress in this field, the robustness of referring perception models (RPMs) against disruptive perturbations is not well explored. This work thoroughly assesses the resilience of RPMs against various perturbations in both general and specific contexts. Recognizing the complex nature of referring perception tasks, we present a comprehensive taxonomy of perturbations, and then develop a versatile toolbox for synthesizing and evaluating the effects of composite disturbances. Employing this toolbox, we construct $\text{R}^2$-Bench, a benchmark for assessing the Robustness of Referring perception models under noisy conditions across five key tasks. Moreover, we propose the $\text{R}^2$-Agent, an LLM-based agent that simplifies and automates model evaluation via natural language instructions. Our investigation uncovers the vulnerabilities of current RPMs to various perturbations and provides tools for assessing model robustness, potentially promoting the safe and resilient integration of intelligent systems into complex real-world scenarios.

A Survey on Applications of Reinforcement Learning in Spatial Resource Allocation

The challenge of spatial resource allocation is pervasive across various domains such as transportation, industry, and daily life. As the scale of real-world issues continues to expand and demands for real-time solutions increase, traditional algorithms face significant computational pressures, struggling to achieve optimal efficiency and real-time capabilities. In recent years, with the escalating computational power of computers, the remarkable achievements of reinforcement learning in domains like Go and robotics have demonstrated its robust learning and sequential decision-making capabilities. Given these advancements, there has been a surge in novel methods employing reinforcement learning to tackle spatial resource allocation problems. These methods exhibit advantages such as rapid solution convergence and strong model generalization abilities, offering a new perspective on resolving spatial resource allocation problems. Therefore, this paper aims to summarize and review recent theoretical methods and applied research utilizing reinforcement learning to address spatial resource allocation problems. It provides a summary and comprehensive overview of its fundamental principles, related methodologies, and applied research. Additionally, it highlights several unresolved issues that urgently require attention in this direction for the future.

NPHardEval4V: A Dynamic Reasoning Benchmark of Multimodal Large Language Models

Understanding the reasoning capabilities of Multimodal Large Language Models (MLLMs) is an important area of research. In this study, we introduce a dynamic benchmark, NPHardEval4V, aimed at addressing the existing gaps in evaluating the pure reasoning abilities of MLLMs. Our benchmark aims to provide a venue to disentangle the effect of various factors such as image recognition and instruction following, from the overall performance of the models, allowing us to focus solely on evaluating their reasoning abilities. It is built by converting textual description of questions from NPHardEval to image representations. Our findings reveal significant discrepancies in reasoning abilities across different models and highlight the relatively weak performance of MLLMs compared to LLMs in terms of reasoning. We also investigate the impact of different prompting styles, including visual, text, and combined visual and text prompts, on the reasoning abilities of MLLMs, demonstrating the different impacts of multimodal inputs in model performance. Unlike traditional benchmarks, which focus primarily on static evaluations, our benchmark will be updated monthly to prevent overfitting and ensure a more authentic and fine-grained evaluation of the models. We believe that this benchmark can aid in understanding and guide the further development of reasoning abilities in MLLMs. The benchmark dataset and code are available at https://github.com/lizhouf/NPHardEval4V

Not all Layers of LLMs are Necessary during Inference

The inference phase of Large Language Models (LLMs) is very expensive. An ideal inference stage of LLMs could utilize fewer computational resources while still maintaining its capabilities (e.g., generalization and in-context learning ability). In this paper, we try to answer the question, "During LLM inference, can we use shallow layers for easy instances; and deep layers for hard ones?" To answer this question, we first indicate that Not all Layers are Necessary during Inference by statistically analyzing the activated layers across tasks. Then, we propose a simple algorithm named AdaInfer to determine the inference termination moment based on the input instance adaptively. More importantly, AdaInfer does not alter LLM parameters and maintains generalizability across tasks. Experiments on well-known LLMs (i.e., Llama2 series and OPT) show that AdaInfer saves an average of 14.8% of computational resources, even up to 50% on sentiment tasks, while maintaining comparable performance. Additionally, this method is orthogonal to other model acceleration techniques, potentially boosting inference efficiency further.

Dual-Granularity Medication Recommendation Based on Causal Inference

As medical demands grow and machine learning technology advances, AI-based diagnostic and treatment systems are garnering increasing attention. Medication recommendation aims to integrate patients' long-term health records with medical knowledge, recommending accuracy and safe medication combinations for specific conditions. However, most existing researches treat medication recommendation systems merely as variants of traditional recommendation systems, overlooking the heterogeneity between medications and diseases. To address this challenge, we propose DGMed, a framework for medication recommendation. DGMed utilizes causal inference to uncover the connections among medical entities and presents an innovative feature alignment method to tackle heterogeneity issues. Specifically, this study first applies causal inference to analyze the quantified therapeutic effects of medications on specific diseases from historical records, uncovering potential links between medical entities. Subsequently, we integrate molecular-level knowledge, aligning the embeddings of medications and diseases within the molecular space to effectively tackle their heterogeneity. Ultimately, based on relationships at the entity level, we adaptively adjust the recommendation probabilities of medication and recommend medication combinations according to the patient's current health condition. Experimental results on a real-world dataset show that our method surpasses existing state-of-the-art baselines in four evaluation metrics, demonstrating superior performance in both accuracy and safety aspects. Compared to the sub-optimal model, our approach improved accuracy by 4.40%, reduced the risk of side effects by 6.14%, and increased time efficiency by 47.15%.

A Literature Review of Literature Reviews in Pattern Analysis and Machine Intelligence

By consolidating scattered knowledge, the literature review provides a comprehensive understanding of the investigated topic. However, excessive reviews, especially in the booming field of pattern analysis and machine intelligence (PAMI), raise concerns for both researchers and reviewers. In response to these concerns, this Analysis aims to provide a thorough review of reviews in the PAMI field from diverse perspectives. First, large language model-empowered bibliometric indicators are proposed to evaluate literature reviews automatically. To facilitate this, a meta-data database dubbed RiPAMI, and a topic dataset are constructed, which are utilized to obtain statistical characteristics of PAMI reviews. Unlike traditional bibliometric measurements, the proposed article-level indicators provide real-time and field-normalized quantified assessments of reviews without relying on user-defined keywords. Second, based on these indicators, the study presents comparative analyses of different reviews, unveiling the characteristics of publications across various fields, periods, and journals. The newly emerging AI-generated literature reviews are also appraised, and the observed differences suggest that most AI-generated reviews still lag behind human-authored reviews in several aspects. Third, we briefly provide a subjective evaluation of representative PAMI reviews and introduce a paper structure-based typology of literature reviews. This typology may improve the clarity and effectiveness for scholars in reading and writing reviews, while also serving as a guide for AI systems in generating well-organized reviews. Finally, this Analysis offers insights into the current challenges of literature reviews and envisions future directions for their development.

Contact-Implicit Model Predictive Control for Dexterous In-hand Manipulation: A Long-Horizon and Robust Approach

Dexterous in-hand manipulation is an essential skill of production and life. Nevertheless, the highly stiff and mutable features of contacts cause limitations to real-time contact discovery and inference, which degrades the performance of model-based methods. Inspired by recent advancements in contact-rich locomotion and manipulation, this paper proposes a novel model-based approach to control dexterous in-hand manipulation and overcome the current limitations. The proposed approach has the attractive feature, which allows the robot to robustly execute long-horizon in-hand manipulation without pre-defined contact sequences or separated planning procedures. Specifically, we design a contact-implicit model predictive controller at high-level to generate real-time contact plans, which are executed by the low-level tracking controller. Compared with other model-based methods, such a long-horizon feature enables replanning and robust execution of contact-rich motions to achieve large-displacement in-hand tasks more efficiently; Compared with existing learning-based methods, the proposed approach achieves the dexterity and also generalizes to different objects without any pre-training. Detailed simulations and ablation studies demonstrate the efficiency and effectiveness of our method. It runs at 20Hz on the 23-degree-of-freedom long-horizon in-hand object rotation task.

MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs

We present the design, implementation and engineering experience in building and deploying MegaScale, a production system for training large language models (LLMs) at the scale of more than 10,000 GPUs. Training LLMs at this scale brings unprecedented challenges to training efficiency and stability. We take a full-stack approach that co-designs the algorithmic and system components across model block and optimizer design, computation and communication overlapping, operator optimization, data pipeline, and network performance tuning. Maintaining high efficiency throughout the training process (i.e., stability) is an important consideration in production given the long extent of LLM training jobs. Many hard stability issues only emerge at large scale, and in-depth observability is the key to address them. We develop a set of diagnosis tools to monitor system components and events deep in the stack, identify root causes, and derive effective techniques to achieve fault tolerance and mitigate stragglers. MegaScale achieves 55.2% Model FLOPs Utilization (MFU) when training a 175B LLM model on 12,288 GPUs, improving the MFU by 1.34x compared to Megatron-LM. We share our operational experience in identifying and fixing failures and stragglers. We hope by articulating the problems and sharing our experience from a systems perspective, this work can inspire future LLM systems research.

Reasoning before Comparison: LLM-Enhanced Semantic Similarity Metrics for Domain Specialized Text Analysis

In this study, we leverage LLM to enhance the semantic analysis and develop similarity metrics for texts, addressing the limitations of traditional unsupervised NLP metrics like ROUGE and BLEU. We develop a framework where LLMs such as GPT-4 are employed for zero-shot text identification and label generation for radiology reports, where the labels are then used as measurements for text similarity. By testing the proposed framework on the MIMIC data, we find that GPT-4 generated labels can significantly improve the semantic similarity assessment, with scores more closely aligned with clinical ground truth than traditional NLP metrics. Our work demonstrates the possibility of conducting semantic analysis of the text data using semi-quantitative reasoning results by the LLMs for highly specialized domains. While the framework is implemented for radiology report similarity analysis, its concept can be extended to other specialized domains as well.