All posts under category "General Research"
This paper presents a novel post-processing methodology for extracting high-quality geometries from density-based topology optimization results. Current post-processing approaches often struggle to simultaneously achieve smooth boundaries, preserve volume fraction, and maintain topological features.
Climate-driven reductions in Arctic sea-ice extent have renewed interest in trans-Arctic shipping, yet adoption remains limited by questions of route feasibility, safety, and excess distance. Existing work often compares idealised great-circle shortcuts or uses detailed weather-routing systems that
Mobile GUI Agents-AI agents capable of interacting with mobile applications on behalf of users-have the potential to transform human-computer interaction. However, current evaluation practices for GUI agents face two fundamental limitations. First, they either rely on single-path offline benchmarks
Equivariance is a powerful prior for learning physical dynamics, yet exact group equivariance can degrade performance if the symmetries are broken. We propose objectcentric world models built with geometric algebra neural networks, providing a soft geometric inductive bias. Our models are evaluated
fusion network as an ensemble of timestep-dependent visual experts and self-supervisedly aggregates their heterogeneous priors into a single, clean, and complete geometric prior. Meanwhile, we utilize task-specific supervision to seamlessly adapt this noise-free prior to dense prediction tasks. Exte
Security of quantum key distribution (QKD) relies on certifying that observed correlations arise from genuine quantum entanglement rather than eavesdropper manipulation. Theoretical security proofs assume idealized conditions, practical certification must contend with adaptive adversaries who optimi
The phenomenon of sound symbolism, the non-arbitrary mapping between word sounds and meanings, has long been demonstrated through anecdotal experiments like Bouba Kiki, but rarely tested at scale. We present the first computational cross-linguistic analysis of sound symbolism in the semantic domain
The integration of artificial intelligence (AI) into education continues to evoke both promise and skepticism. While past waves of technological optimism often fell short, recent advances in large language models (LLMs) have revived the vision of scalable, individualized tutoring. This paper present
Recommendation systems face challenges in dynamically adapting to evolving user preferences and interactions within complex social networks. Traditional approaches often fail to account for the intricate interactions within cyber-social systems and lack the flexibility to generalize across diverse d
This paper proposes DeepRule, an integrated framework for automated business rule generation in retail assortment and pricing optimization. Addressing the systematic misalignment between existing theoretical models and real-world economic complexities, we identify three critical gaps: (1) data modal
Despite significant advances in optimizers for training, most research works use common scheduler choices like Cosine or exponential decay. In this paper, we study emph{GreedyLR}, a novel scheduler that adaptively adjusts the learning rate during training based on the current loss. To validate the e
Zero-shot skeleton-based action recognition (ZS-SAR) is fundamentally constrained by prevailing approaches that rely on aligning skeleton features with static, class-level semantics. This coarse-grained alignment fails to bridge the domain shift between seen and unseen classes, thereby impeding the
Vision-language models (VLMs) show promise in automating reward design in humanoid locomotion, which could eliminate the need for tedious manual engineering. However, current VLM-based methods are essentially 'blind', as they lack the environmental perception required to navigate complex terrain. We
The latency and power consumption of large language models (LLMs) are major constraints when serving them across a wide spectrum of hardware platforms, from mobile edge devices to cloud GPU clusters. Benchmarking is crucial for optimizing efficiency in both model deployment and next-generation model
Large language models (LLMs) excel at explicit reasoning, but their implicit computational strategies remain underexplored. Decades of psychophysics research show that humans intuitively process and integrate noisy signals using near-optimal Bayesian strategies in perceptual tasks. We ask whether LL
While the technology for detecting AI-Generated Content (AIGC) images has advanced rapidly, the field still faces two core issues: poor reproducibility and insufficient gen eralizability, which hinder the practical application of such technologies. This study addresses these challenges by re viewing
The overall neural network (NN) performance is closely related to the properties of its embedding distribution in latent space (LS). It has recently been shown that predefined vector systems, specifically A n root system vectors, can be used as targets for latent space configurations (LSC) to ensure
This study investigates AI integration in architectural education through a teaching experiment in Zhejiang University's 2024-25 grade three undergraduate design studio. Adopting a dual-module framework (20-hour AI training + embedded ethics discussions), the course introduced deep learning models,
The validation and verification of artificial intelligence (AI) models through robustness assessment are essential to guarantee the reliable performance of intelligent systems facing real-world challenges, such as image corruptions including noise, blurring, and weather variations. Despite the globa
Large language models (LLMs) are increasingly used to simulate human behavior, but common practices to use LLM-generated data are inefficient. Treating an LLM's output ('model choice') as a single data point underutilizes the information inherent to the probabilistic nature of LLMs. This paper intro
We present INTELLECT-3, a 106B-parameter Mixture-of-Experts model (12B active) trained with large-scale reinforcement learning on our end-to-end RL infrastructure stack. INTELLECT-3 achieves state of the art performance for its size across math, code, science and reasoning benchmarks, outperforming
Agentic memory is emerging as a key enabler for large language models (LLM) to maintain continuity, personalization, and long-term context in extended user interactions, critical capabilities for deploying LLMs as truly interactive and adaptive agents. Agentic memory refers to the memory that provid
For decades, sampling-based techniques have been the de facto standard for accelerating microarchitecture simulation, with the Basic Block Vector (BBV) serving as the cornerstone program representation. Yet, the BBV's fundamental limitations: order-dependent IDs that prevent cross-program knowledge
The resource requirements of neural networks can be significantly reduced through pruning - the removal of seemingly less important parameters. However, for LLMs, full retraining to recover pruning-induced performance degradation is often prohibitive and classical approaches such as magnitude prunin
Large Language Models (LLMs) can generate reasoning tokens before their final answer to boost performance on complex tasks. While these sequences seem like human thought processes, empirical evidence reveals that they are not a faithful explanation of the model's actual reasoning process. To address
Machine unlearning aims to remove the influence of specific data points from a trained model to satisfy privacy, copyright, and safety requirements. In real deployments, providers distribute a global model to many edge devices, where each client personalizes the model using private data. When a dele
Chest radiography remains one of the most widely used imaging modalities for thoracic diagnosis, yet increasing imaging volumes and radiologist workload continue to challenge timely interpretation. In this work, we investigate the use of MedImageInsight, a medical imaging foundational model, for aut
A global shortage of radiologists has been exacerbated by the significant volume of chest X-ray workloads, particularly in primary care. Although multimodal large language models show promise, existing evaluations predominantly rely on automated metrics or retrospective analyses, lacking rigorous pr
Real-time decoding of target variables from multiple simultaneously recorded neural time-series modalities, such as discrete spiking activity and continuous field potentials, is important across various neuroscience applications. However, a major challenge for doing so is that different neural modal
We point out that EXP3 can be implemented in constant time per round, propose more practical algorithms, and analyze the trade-offs between the regret bounds and time complexities of these algorithms.
Loss functions are fundamental to learning accurate 3D point cloud models, yet common choices trade geometric fidelity for computational cost. Chamfer Distance is efficient but permits many-to-one correspondences, while Earth Mover Distance better reflects one-to-one transport at high computational
Over a billion users across the globe interact with AI systems engineered with increasing sophistication to mimic human traits. This shift has triggered urgent debate regarding Anthropomorphism, the attribution of human characteristics to synthetic agents, and its potential to induce misplaced trust
Insider threat detection (ITD) is challenging due to the subtle and concealed nature of malicious activities performed by trusted users. This paper proposes a post-hoc ITD framework that integrates explicit and implicit graph representations with temporal modelling to capture complex user behaviour
Manufacturing planners face complex operational challenges that require seamless collaboration between human expertise and intelligent systems to achieve optimal performance in modern production environments. Traditional approaches to analyzing simulation-based manufacturing data often create barrie
Since the Internet of Things (IoT) is widely adopted using Android applications, detecting malicious Android apps is essential. In recent years, Android graph-based deep learning research has proposed many approaches to extract relationships from applications as graphs to generate graph embeddings.
Therapeutic decision-making in clinical medicine constitutes a high-stakes domain in which AI guidance interacts with complex interactions among patient characteristics, disease processes, and pharmacological agents. Tasks such as drug recommendation, treatment planning, and adverse-effect predictio
Breast ultrasound (BUS) segmentation provides lesion boundaries essential for computer-aided diagnosis and treatment planning. While promptable methods can improve segmentation performance and tumor delineation when text or spatial prompts are available, many public BUS datasets lack reliable metada
Semantic Abstraction's key observation is that 2D VLMs' relevancy activations roughly correspond to their confidence of whether and where an object is in the scene. Thus, relevancy maps are treated as 'abstract object' representations. We use this framework for learning 3D localization and completio
Assigning tasks to robots often involves supplying the robot with an overarching goal, such as through natural language, and then relying on the robot to uncover and execute a plan to achieve that goal. In many settings common to human-robot interaction, however, the world is only partially observab
This short note comments on Aerts et al. [1] , which proposes that ranked word frequencies in texts should be read through the lens of Bose-Einstein (BE) statistics and even used to illuminate the origin of quantum statistics in physics. The core message here is modest: the paper offers an interest
The development of tabular foundation models (TFMs) has accelerated in recent years, showing strong potential to outperform traditional ML methods for structured data. A key finding is that TFMs can be pretrained entirely on synthetic datasets, opening opportunities to design data generators that en
This paper derives `Scaling Laws for Economic Impacts' -- empirical relationships between the training compute of Large Language Models (LLMs) and professional productivity. In a preregistered experiment, over 500 consultants, data analysts, and managers completed professional tasks using one of 13
We extend the moduli-theoretic framework of psychometric batteries to the domain of dynamical systems. While previous work established the AAI capability score as a static functional on the space of agent representations, this paper formalizes the agent as a flow $ฮฝ_r$ parameterized by computational
College students often face academic challenges that hamper their productivity and well-being. Although self-help books and productivity apps are popular, they often fall short. Books provide generalized, non-interactive guidance, and apps are not inherently educational and can hinder the developmen
proj.github.io (a) Training accuracy 50% Fewer Steps (b) Validation accuracy (c) Generalization performance Figure 1. Performance overview of MSSR: (a-b) Training and validation accuracy of MVSR (Multimodal Vanilla Single-Rollout), GRPO [28] and our MSSR, trained on the Vision-R1-RL [15] training se
Accurate and rapid state-of-health (SOH) monitoring plays an important role in indicating energy information for lithium-ion battery-powered portable mobile devices. To confront their variable working conditions, transfer learning (TL) emerges as a promising technique for leveraging knowledge from d
As modern neural networks become increasingly memory-bound, inference throughput is limited by DRAM bandwidth rather than compute. We present Arithmetic-Intensity-Aware Quantization (AIQ), a mixed precision quantization framework that chooses per-layer bit-widths to maximize arithmetic intensity (AI
Fossil gas is sometimes presented as an enabler of variable solar and wind generation beyond 2050, despite being a primary source of greenhouse gas emissions from methane leakage and combustion. We find that balancing solar and wind generation with pumped hydro energy storage eliminates the need for
The ability to compose acquired skills to plan and execute behaviors is a hallmark of natural intelligence. Yet, despite remarkable cross-disciplinary efforts, a principled account of how task structure shapes gating and how such computations could be delivered in neural circuits, remains elusive. H
To enhance the performance of large language models (LLMs) in various domain-specific applications, sensitive data such as healthcare, law, and finance are being used to privately customize or fine-tune these models. Such privately adapted LLMs are regarded as either personal privacy assets or corpo
Enter keywords to search articles