Abstract:This paper presents a real-time, energy-efficient embedded system implementing an array of Cascade of Asymmetric Resonators with Fast-Acting Compression (CARFAC) cochlea models for underwater sound analysis. Built on the AMD Kria KV260 System-on-Module (SoM), the system integrates a Rust-based software framework on the processor for real-time interfacing and synchronization with multiple hydrophone inputs, and a hardware-accelerated implementation of the CARFAC models on a Field-Programmable Gate Array (FPGA) for real-time sound pre-processing. Compared to prior work, the CARFAC accelerator achieves improved scalability and processing speed while reducing resource usage through optimized time-multiplexing, pipelined design, and elimination of costly division circuits. Experimental results demonstrate 13.5% hardware utilization for a single 64-channel CARFAC instance and a whole board power consumption of 3.11 W when processing a 256 kHz input signal in real time.
Abstract:Nearly all human work is collaborative; thus, the evaluation of real-world NLP applications often requires multiple dimensions that align with diverse human perspectives. As real human evaluator resources are often scarce and costly, the emerging "LLM-as-a-judge" paradigm sheds light on a promising approach to leverage LLM agents to believably simulate human evaluators. Yet, to date, existing LLM-as-a-judge approaches face two limitations: persona descriptions of agents are often arbitrarily designed, and the frameworks are not generalizable to other tasks. To address these challenges, we propose MAJ-EVAL, a Multi-Agent-as-Judge evaluation framework that can automatically construct multiple evaluator personas with distinct dimensions from relevant text documents (e.g., research papers), instantiate LLM agents with the personas, and engage in-group debates with multi-agents to Generate multi-dimensional feedback. Our evaluation experiments in both the educational and medical domains demonstrate that MAJ-EVAL can generate evaluation results that better align with human experts' ratings compared with conventional automated evaluation metrics and existing LLM-as-a-judge methods.
Abstract:Knowledge tracing (KT) aims to estimate a student's evolving knowledge state and predict their performance on new exercises based on performance history. Many realistic classroom settings for KT are typically low-resource in data and require online updates as students' exercise history grows, which creates significant challenges for existing KT approaches. To restore strong performance under low-resource conditions, we revisit the hierarchical knowledge concept (KC) information, which is typically available in many classroom settings and can provide strong prior when data are sparse. We therefore propose Knowledge-Tree-based Knowledge Tracing (KT$^2$), a probabilistic KT framework that models student understanding over a tree-structured hierarchy of knowledge concepts using a Hidden Markov Tree Model. KT$^2$ estimates student mastery via an EM algorithm and supports personalized prediction through an incremental update mechanism as new responses arrive. Our experiments show that KT$^2$ consistently outperforms strong baselines in realistic online, low-resource settings.
Abstract:Recent advancements in large multimodal models have led to the emergence of remarkable generalist capabilities in digital domains, yet their translation to physical agents such as robots remains a significant challenge. This report introduces a new family of AI models purposefully designed for robotics and built upon the foundation of Gemini 2.0. We present Gemini Robotics, an advanced Vision-Language-Action (VLA) generalist model capable of directly controlling robots. Gemini Robotics executes smooth and reactive movements to tackle a wide range of complex manipulation tasks while also being robust to variations in object types and positions, handling unseen environments as well as following diverse, open vocabulary instructions. We show that with additional fine-tuning, Gemini Robotics can be specialized to new capabilities including solving long-horizon, highly dexterous tasks, learning new short-horizon tasks from as few as 100 demonstrations and adapting to completely novel robot embodiments. This is made possible because Gemini Robotics builds on top of the Gemini Robotics-ER model, the second model we introduce in this work. Gemini Robotics-ER (Embodied Reasoning) extends Gemini's multimodal reasoning capabilities into the physical world, with enhanced spatial and temporal understanding. This enables capabilities relevant to robotics including object detection, pointing, trajectory and grasp prediction, as well as multi-view correspondence and 3D bounding box predictions. We show how this novel combination can support a variety of robotics applications. We also discuss and address important safety considerations related to this new class of robotics foundation models. The Gemini Robotics family marks a substantial step towards developing general-purpose robots that realizes AI's potential in the physical world.
Abstract:The rapid development of deep learning and generative AI technologies has profoundly transformed the digital contact landscape, creating realistic Deepfake that poses substantial challenges to public trust and digital media integrity. This paper introduces a novel Deepfake detention framework, Volume of Differences (VoD), designed to enhance detection accuracy by exploiting temporal and spatial inconsistencies between consecutive video frames. VoD employs a progressive learning approach that captures differences across multiple axes through the use of consecutive frame differences (CFD) and a network with stepwise expansions. We evaluate our approach with intra-dataset and cross-dataset testing scenarios on various well-known Deepfake datasets. Our findings demonstrate that VoD excels with the data it has been trained on and shows strong adaptability to novel, unseen data. Additionally, comprehensive ablation studies examine various configurations of segment length, sampling steps, and intervals, offering valuable insights for optimizing the framework. The code for our VoD framework is available at https://github.com/xuyingzhongguo/VoD.
Abstract:The traditional heat-load generation pattern of combined heat and power generators has become a problem leading to renewable energy source (RES) power curtailment in cold regions, motivating the proposal of a planning model for alternative heat sources. The model aims to identify non-dominant capacity allocation schemes for heat pumps, thermal energy storage, electric boilers, and combined storage heaters to construct a Pareto front, considering both economic and sustainable objectives. The integration of various heat sources from both generation and consumption sides enhances flexibility in utilization. The study introduces a novel optimization algorithm, the adaptive multi-objective Bayesian optimization (AMBO). Compared to other widely used multi-objective optimization algorithms, AMBO eliminates predefined parameters that may introduce subjectivity from planners. Beyond the algorithm, the proposed model incorporates a noise term to account for inevitable simulation deviations, enabling the identification of better-performing planning results that meet the unique requirements of cold regions. What's more, the characteristics of electric-thermal coupling scenarios are captured and reflected in the operation simulation model to make sure the simulation is close to reality. Numerical simulation verifies the superiority of the proposed approach in generating a more diverse and evenly distributed Pareto front in a sample-efficient manner, providing comprehensive and objective planning choices.
Abstract:The growing penetration of renewable energy sources (RESs) in active distribution networks (ADNs) leads to complex and uncertain operation scenarios, resulting in significant deviations and risks for the ADN operation. In this study, a collaborative capacity planning of the distributed energy resources in an ADN is proposed to enhance the RES accommodation capability. The variability of RESs, characteristics of adjustable demand response resources, ADN bi-directional power flow, and security operation limitations are considered in the proposed model. To address the noise term caused by the inevitable deviation between the operation simulation and real-world environments, an improved noise-aware Bayesian optimization algorithm with the probabilistic surrogate model is proposed to overcome the interference from the environmental noise and sample-efficiently optimize the capacity planning model under noisy circumstances. Numerical simulation results verify the superiority of the proposed approach in coping with environmental noise and achieving lower annual cost and higher computation efficiency.
Abstract:Cluster deletion is an NP-hard graph clustering objective with applications in computational biology and social network analysis, where the goal is to delete a minimum number of edges to partition a graph into cliques. We first provide a tighter analysis of two previous approximation algorithms, improving their approximation guarantees from 4 to 3. Moreover, we show that both algorithms can be derandomized in a surprisingly simple way, by greedily taking a vertex of maximum degree in an auxiliary graph and forming a cluster around it. One of these algorithms relies on solving a linear program. Our final contribution is to design a new and purely combinatorial approach for doing so that is far more scalable in theory and practice.
Abstract:Large Language Models (LLMs) have emerged as potent tools for advancing the United Nations' Sustainable Development Goals (SDGs). However, the attitudinal disparities between LLMs and humans towards these goals can pose significant challenges. This study conducts a comprehensive review and analysis of the existing literature on the attitudes of LLMs towards the 17 SDGs, emphasizing the comparison between their attitudes and support for each goal and those of humans. We examine the potential disparities, primarily focusing on aspects such as understanding and emotions, cultural and regional differences, task objective variations, and factors considered in the decision-making process. These disparities arise from the underrepresentation and imbalance in LLM training data, historical biases, quality issues, lack of contextual understanding, and skewed ethical values reflected. The study also investigates the risks and harms that may arise from neglecting the attitudes of LLMs towards the SDGs, including the exacerbation of social inequalities, racial discrimination, environmental destruction, and resource wastage. To address these challenges, we propose strategies and recommendations to guide and regulate the application of LLMs, ensuring their alignment with the principles and goals of the SDGs, and therefore creating a more just, inclusive, and sustainable future.
Abstract:Graphs are commonly used to model complex networks prevalent in modern social media and literacy applications. Our research investigates the vulnerability of these graphs through the application of feature based adversarial attacks, focusing on both decision-time attacks and poisoning attacks. In contrast to state-of-the-art models like Net Attack and Meta Attack, which target node attributes and graph structure, our study specifically targets node attributes. For our analysis, we utilized the text dataset Hellaswag and graph datasets Cora and CiteSeer, providing a diverse basis for evaluation. Our findings indicate that decision-time attacks using Projected Gradient Descent (PGD) are more potent compared to poisoning attacks that employ Mean Node Embeddings and Graph Contrastive Learning strategies. This provides insights for graph data security, pinpointing where graph-based models are most vulnerable and thereby informing the development of stronger defense mechanisms against such attacks.