Research
Research
Research
Research
346,661+ open-access research outputs.
This paper investigates the so-called reward-balancing methods, a novel class of algorithms for solving discounted-return reinforcement learning (RL) problems. These methods consist of iteratively adj…
We study an Ising model with long-range interactions undergoing a time-periodic kicking. For different initial states we observe persistent period doubling. When there is period doubling we find that …
We introduce and study the problem of calibrating conditional risk, which involves estimating the expected loss of a prediction model conditional on input features. We analyze this problem in both cla…
Fault location in distribution grids is critical for reliability and minimizing outage durations. Yet, it remains challenging due to partial observability, given sparse measurement infrastructure. Rec…
While Large Language Models (LLMs) excel at function-level code generation, project-level tasks such as generating functional and visually aesthetic multi-page websites remain highly challenging. Exis…
With the development of deep learning, ViT-based stereo matching methods have made significant progress due to their remarkable robustness and zero-shot ability. However, due to the limitations of ViT…
Vision Transformers (ViTs) dominate self-supervised learning (SSL). While they have proven highly effective for large-scale pretraining, they are computationally inefficient and scale poorly with imag…
Quality-Diversity (QD) algorithms excel at discovering diverse repertoires of skills, but are hindered by poor sample efficiency and often require tens of millions of environment steps to solve comple…
In frequency division duplex massive multiple-input multiple-output systems, downlink channel state information must be fed back within a limited uplink budget. While transform coding with Karhunen-Lo…
We report the first systematic evidence of hallucination in AI models of fluid dynamics, demonstrated in the canonical problem of hydrodynamically unstable transport known as viscous fingering. AI-bas…
Forecasting the life-cycle trajectory of a newly launched product is important for launch planning, resource allocation, and early risk assessment. This task is especially difficult in the pre-launch …
While Central Pattern Generators (CPGs) and Multi-Layer Perceptrons (MLP) are widely used paradigms in robot control, few systematic studies have been performed on the relative merits of large paramet…
The Composed Image Retrieval (CIR) task provides a flexible retrieval paradigm via a reference image and modification text, but it heavily relies on expensive and error-prone triplet annotations. This…
Sign-language datasets are difficult to preprocess consistently because they vary in annotation schema, clip timing, signer framing, and privacy constraints. Existing work usually reports downstream m…
The exact microscopic origin, symmetry, and thermal melting mechanism of the charge density wave (CDW) phase in TiSe$_{2}$ remain a subject of intense debate, particularly regarding the presence of ch…
Language Models (LLMs) have emerged as powerful reasoning engines for embodied control. In particular, In-Context Learning (ICL) enables off-the-shelf, text-only LLMs to predict robot actions without …
Fault diagnosis under unseen operating conditions remains highly challenging when labeled data are scarce. Semi-supervised domain generalization fault diagnosis (SSDGFD) provides a practical solution …
Chain-of-Thought (CoT) reasoning significantly elevates the complex problem-solving capabilities of multimodal large language models (MLLMs). However, adapting CoT to vision typically discretizes sign…
Preprints are essential for the timely and open dissemination of research. arXiv, the most widely used preprint service, takes the idea of open science one step further by not only publishing the actu…
Composed image retrieval, multi-turn composed image retrieval, and composed video retrieval all share a common paradigm: composing the reference visual with modification text to retrieve the desired t…
Free open-access publishing with Google Scholar indexing.
Submission Guide →