All posts under category "General Research"
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
Predicting the evolving microstructure of hydrating cement is essential for understanding and modeling its mechanical property development. Physicsbased continuum approaches offer a rigorous framework for capturing the thermodynamics of dissolution and precipitation processes at the microstructural
While visual data augmentation remains a cornerstone for training robust vision models, it has received limited attention in visual language models (VLMs), which predominantly rely on large-scale real data acquisition or synthetic diversity. Consequently, they may struggle with basic perception task
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
In democracies, major policy decisions typically require some form of majority or consensus, so elites must secure mass support to govern. Historically, elites could shape support only through limited instruments like schooling and mass media; advances in AI-driven persuasion sharply reduce the cost
Although scaling laws and many empirical results suggest that increasing the size of Vision Transformers often improves performance, model accuracy and training behavior are not always monotonically increasing with scale. Focusing on ViT-B/16 trained on ImageNet-1K, we study two simple parameter-red
This work proposes a unified control architecture that couples a Reinforcement Learning (RL)-driven controller with a disturbance-rejection Extended State Observer (ESO), complemented by an Event-Triggered Mechanism (ETM) to limit unnecessary computations. The ESO is utilized to estimate the system
Figure 1: SPACECONTROL enables spatially controlled 3D asset generation from simple geometric primitives such as superquadrics (light blue) and other geometry types such as polygon meshes. Top: rapid asset generation. From quick 3D sketches and brief text prompts, we can generate high quality assets
Imitation learning with diffusion models has advanced robotic control by capturing the multimodal action distributions. However, existing methods typically treat observations only as highlevel conditions to the denoising network, rather than integrating them into the stochastic dynamics of the diffu
Figure 1 : Comparison of 3DGS, 2DGS, and our EGGS. While 3DGS achieves high-fidelity appearance, it often produces inaccurate geometry, with imprecise surfaces and blurred edges. 2DGS improves geometric consistency across views but suffers from reduced appearance quality due to over-smoothed surfac
We investigate machine learning approaches to approximating the emph{domination number} of graphs, the minimum size of a dominating set. Exact computation of this parameter is NP-hard, restricting classical methods to small instances. We compare two neural paradigms: Convolutional Neural Networks (C
Supervised fine-tuning (SFT) is a standard approach for adapting large language models to specialized domains, yet its application to protein sequence modeling and protein language models (PLMs) remains ad hoc. This is in part because highquality annotated data are far more difficult to obtain for p
Accurate perception of the vehicle's 3D surroundings, including fine-scale road geometry, such as bumps, slopes, and surface irregularities, is essential for safe and comfortable vehicle control. However, conventional monocular depth estimation often oversmooths these features, losing critical infor
Precise access control decisions are crucial to the security of both traditional applications and emerging agent-based systems. Typically, these decisions are made by users during app installation or at runtime. Due to the increasing complexity and automation of systems, making these access control
Hysteresis is a nonlinear phenomenon with memory effects, where a system's output depends on both its current state and past states. It is prevalent in various physical and mechanical systems, such as yielding structures under seismic excitation, ferromagnetic materials, and piezoelectric actuators.
We introduce a two-stage self-supervised framework that combines the Joint-Embedding Predictive Architecture (JEPA) with a Density Adaptive Attention Mechanism (DAAM) for learning robust speech representations. Stage 1 uses JEPA with DAAM to learn semantic audio features via masked prediction in lat
In recent years, the development of multimodal autoencoders has gained significant attention due to their potential to handle multimodal complex data types and improve model performance. Understanding the stability and robustness of these models is crucial for optimizing their training, architecture
The proliferation of Large Language Models (LLMs) has catalyzed a shift towards autonomous agents capable of complex reasoning and tool use. However, current agent architectures are frequently constructed using imperative, ad hoc patterns. This results in brittle systems plagued by difficulties in s
Radio frequency (RF)-based indoor localization offers significant promise for applications such as indoor navigation, augmented reality, and pervasive computing. While deep learning has greatly enhanced localization accuracy and robustness, existing localization models still face major challenges in
As artificial intelligence (AI) rapidly advances, especially in multimodal large language models (MLLMs), research focus is shifting from single-modality text processing to the more complex domains of multimodal and embodied AI. Embodied intelligence focuses on training agents within realistic simul
Modeling daily hand interactions often struggles with severe occlusions, such as when two hands overlap, which highlights the need for robust feature learning in 3D hand pose estimation (HPE). To handle such occluded hand images, it is vital to effectively learn the relationship between local image
We present the Generalized Policy Gradient (GPG) Theorem, specifically designed for Transformer-based policies. Notably, we demonstrate that both standard Policy Gradient Theorem and GRPO emerge as special cases within our GPG framework. Furthermore, we explore its practical applications in training
Multimodal Artificial Intelligence (AI) systems, particularly Vision-Language Models (VLMs), have become integral to critical applications ranging from autonomous decisionmaking to automated document processing. As these systems scale, they rely heavily on preprocessing pipelines to handle diverse i
Large Vision-Language Models (VLMs) often exhibit text inertia, where attention drifts from visual evidence toward linguistic priors, resulting in object hallucinations. Existing decoding strategies intervene only at the output logits and thus cannot correct internal reasoning drift, while recent in
Comprehensive experiments demonstrate that ViSAudio outperforms existing state-of-the-art methods across both objective metrics and subjective evaluations, generating high-quality binaural audio with spatial immersion that adapts effectively to viewpoint changes, sound-source motion, and diverse aco
Free-viewpoint video (FVV) enables immersive viewing experiences by allowing users to view scenes from arbitrary perspectives. As a prominent reconstruction technique for FVV generation, 4D Gaussian Splatting (4DGS) models dynamic scenes with time-varying 3D Gaussian ellipsoids and achieves high-qua
Reinforcement learning with verifiable rewards (RLVR) has demonstrated superior performance in enhancing the reasoning capability of large language models (LLMs). However, this accuracy-oriented learning paradigm often suffers from entropy collapse, which reduces policy exploration and limits reason
Malicious WebShells pose a significant and evolving threat by compromising critical digital infrastructures and endangering public services in sectors such as healthcare and finance. While the research community has made significant progress in WebShell detection (i.e., distinguishing malicious samp
Online incivility has emerged as a widespread and persistent problem in digital communities, imposing substantial social and psychological burdens on users. Although many platforms attempt to curb incivility through moderation and automated detection, the performance of existing approaches often rem
Large Language Models (LLMs) have transformed natural language processing and hold growing promise for advancing science, healthcare, and decision-making. Yet their training paradigms remain dominated by affirmation-based inference, akin to modus ponens, where accepted premises yield predicted conse
Applying reinforcement learning (RL) to real-world tasks requires converting informal descriptions into a formal Markov decision process (MDP), implementing an executable environment, and training a policy agent. Automating this process is challenging due to modeling errors, fragile code, and misali
We introduce Cube Bench, a Rubik's-cube benchmark for evaluating spatial and sequential reasoning in multimodal large language models (MLLMs). The benchmark decomposes performance into five skills: (i) reconstructing cube faces from images and text, (ii) choosing the optimal next move, (iii) predict
Neural networks have shown remarkable success in supervised learning when trained on a single task using a fixed dataset. However, when neural networks are trained on a reinforcement learning task, their ability to continue learning from new experiences declines over time. This decline in learning a
Latent inpainting in diffusion models still relies almost universally on linearly interpolating VAE latents under a downsampled mask. We propose a key principle for compositing image latents: Pixel-Equivalent Latent Compositing (PELC). An equivalent latent compositor should be the same as compositin
Enter keywords to search articles