Ying Wu
YOU?
Author Swipe
View article: Tackling the Kidnapped Robot Problem via Sparse Feasible Hypothesis Sampling and Reliable Batched Multi-Stage Inference
Tackling the Kidnapped Robot Problem via Sparse Feasible Hypothesis Sampling and Reliable Batched Multi-Stage Inference Open
This paper addresses the Kidnapped Robot Problem (KRP), a core localization challenge of relocalizing a robot in a known map without prior pose estimate when localization loss or at SLAM initialization. For this purpose, a passive 2-D glob…
View article: Implementation of Digital Management Platform for Art Design Works Based on B/S Architecture
Implementation of Digital Management Platform for Art Design Works Based on B/S Architecture Open
This paper designs and implements a digital management platform for art design works based on BS (Browser-Server) architecture, which solves the problems of inconvenient storage, low retrieval efficiency, and difficult cross-platform acces…
View article: Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR Open
Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a key paradigm for post-training Large Language Models (LLMs), particularly for complex reasoning tasks. However, vanilla RLVR training has been shown to improve…
View article: Cavity QED Based on Strongly Localized Modes: Exponentially Enhancing Single-Atom Cooperativity
Cavity QED Based on Strongly Localized Modes: Exponentially Enhancing Single-Atom Cooperativity Open
Large single-atom cooperativity in quantum systems is important for quantum information processing. Here, we propose to exponentially enhance the single-atom cooperativity parameter by exploiting the strongly localized effect of modes in c…
View article: SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning
SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning Open
Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for training large language models (LLMs) on complex reasoning tasks, such as mathematical problem solving. A prerequisite for the scalability of RLVR is a high-qua…
View article: Place Cells as Multi-Scale Position Embeddings: Random Walk Transition Kernels for Path Planning
Place Cells as Multi-Scale Position Embeddings: Random Walk Transition Kernels for Path Planning Open
The hippocampus supports spatial navigation by encoding cognitive maps through collective place cell activity. We model the place cell population as non-negative spatial embeddings derived from the spectral decomposition of multi-step rand…
View article: Monitoring Primitive Interactions During the Training of DNNs
Monitoring Primitive Interactions During the Training of DNNs Open
This paper focuses on the newly emerged research topic, i.e., whether the complex decision-making logic of a DNN can be mathematically summarized into a few simple logics. Beyond the explanation of a static DNN, in this paper, we hope to s…
View article: Latent Thought Models with Variational Bayes Inference-Time Computation
Latent Thought Models with Variational Bayes Inference-Time Computation Open
We propose a novel class of language models, Latent Thought Models (LTMs), which incorporate explicit latent thought vectors that follow an explicit prior model in latent space. These latent thought vectors guide the autoregressive generat…
View article: Blur-Deblur Algorithm for Pressure-Sensitive Paint Image Based on Variable Attention Convolution
Blur-Deblur Algorithm for Pressure-Sensitive Paint Image Based on Variable Attention Convolution Open
View article: Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts
Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts Open
View article: On the Analysis and Distillation of Emergent Outlier Properties in Pre-trained Language Models
On the Analysis and Distillation of Emergent Outlier Properties in Pre-trained Language Models Open
View article: StarWhisper Telescope: An AI framework for automating end-to-end astronomical observations
StarWhisper Telescope: An AI framework for automating end-to-end astronomical observations Open
The exponential growth of large-scale telescope arrays has boosted time-domain astronomy development but introduced operational bottlenecks, including labor-intensive observation planning, data processing, and real-time decision-making. He…
View article: Floquet Chern Vector Topological Insulators in Three Dimensions
Floquet Chern Vector Topological Insulators in Three Dimensions Open
We theoretically and numerically investigate Chern vector insulators and topological surface states in a three-dimensional lattice, based on phase-delayed temporal-periodic interactions within the tight-binding model. These Floquet interac…
View article: Understanding Galaxy Morphology Evolution Through Cosmic Time via Redshift Conditioned Diffusion Models
Understanding Galaxy Morphology Evolution Through Cosmic Time via Redshift Conditioned Diffusion Models Open
Redshift measures the distance to galaxies and underlies our understanding of the origin of the Universe and galaxy evolution. Spectroscopic redshift is the gold-standard method for measuring redshift, but it requires about $1000$ times mo…
View article: Unlocking the Potential of Text-to-Image Diffusion with PAC-Bayesian Theory
Unlocking the Potential of Text-to-Image Diffusion with PAC-Bayesian Theory Open
Text-to-image (T2I) diffusion models have revolutionized generative modeling by producing high-fidelity, diverse, and visually realistic images from textual prompts. Despite these advances, existing models struggle with complex prompts inv…
View article: Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts
Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts Open
The recent progress in Vision-Language Models (VLMs) has broadened the scope of multimodal applications. However, evaluations often remain limited to functional tasks, neglecting abstract dimensions such as personality traits and human val…
View article: A minimalistic representation model for head direction system
A minimalistic representation model for head direction system Open
We present a minimalistic representation model for the head direction (HD) system, aiming to learn a high-dimensional representation of head direction that captures essential properties of HD cells. Our model is a representation of rotatio…
View article: Effect of modified balanced cupping therapy based on Traditional Chinese Medicine meridian theory combined with head scraping in the treatment of wind-cold type cold
Effect of modified balanced cupping therapy based on Traditional Chinese Medicine meridian theory combined with head scraping in the treatment of wind-cold type cold Open
Objective To observed the effect of modified balanced cupping therapy based on Traditional Chinese Medicine meridian theory combined with head scraping in the treatment of wind-cold type cold. Methods Totally 30 patients with wind-cold typ…
View article: DODT: Enhanced Online Decision Transformer Learning through Dreamer's Actor-Critic Trajectory Forecasting
DODT: Enhanced Online Decision Transformer Learning through Dreamer's Actor-Critic Trajectory Forecasting Open
Advancements in reinforcement learning have led to the development of sophisticated models capable of learning complex decision-making tasks. However, efficiently integrating world models with decision transformers remains a challenge. In …
View article: Long-range gene expression prediction with token alignment of large language model
Long-range gene expression prediction with token alignment of large language model Open
Gene expression is a cellular process that plays a fundamental role in human phenotypical variations and diseases. Despite advances of deep learning models for gene expression prediction, recent benchmarks have revealed their inability to …
View article: Power-law-exponential interaction induced quantum spiral phases
Power-law-exponential interaction induced quantum spiral phases Open
We theoretically predict a kind of power-law-exponential (PLE) dipole-dipole interaction between quantum emitters in a 1D waveguide QED system. This unconventional long-range interaction is the combination of power-law growth and exponenti…
View article: Visual Agents as Fast and Slow Thinkers
Visual Agents as Fast and Slow Thinkers Open
Achieving human-level intelligence requires refining cognitive distinctions between System 1 and System 2 thinking. While contemporary AI, driven by large language models, demonstrates human-like traits, it falls short of genuine cognition…
View article: InterPreT: Interactive Predicate Learning from Language Feedback for Generalizable Task Planning
InterPreT: Interactive Predicate Learning from Language Feedback for Generalizable Task Planning Open
Learning abstract state representations and knowledge is crucial for long-horizon robot planning. We present InterPreT, an LLM-powered framework for robots to learn symbolic predicates from language feedback of human non-experts during emb…
View article: Latent Energy-Based Odyssey: Black-Box Optimization via Expanded Exploration in the Energy-Based Latent Space
Latent Energy-Based Odyssey: Black-Box Optimization via Expanded Exploration in the Energy-Based Latent Space Open
Offline Black-Box Optimization (BBO) aims at optimizing a black-box function using the knowledge from a pre-collected offline dataset of function values and corresponding input designs. However, the high-dimensional and highly-multimodal i…
View article: Optimization Strategies for Self-Supervised Learning in the Use of Unlabeled Data
Optimization Strategies for Self-Supervised Learning in the Use of Unlabeled Data Open
This study explores optimization strategies for self-supervised learning in the use of unlabeled data. By deeply analyzing existing research, we propose a novel method that significantly enhances the performance of algorithms on unlabeled …
View article: Watermarking Generative Tabular Data
Watermarking Generative Tabular Data Open
In this paper, we introduce a simple yet effective tabular data watermarking mechanism with statistical guarantees. We show theoretically that the proposed watermark can be effectively detected, while faithfully preserving the data fidelit…
View article: Object-Conditioned Energy-Based Attention Map Alignment in Text-to-Image Diffusion Models
Object-Conditioned Energy-Based Attention Map Alignment in Text-to-Image Diffusion Models Open
Text-to-image diffusion models have shown great success in generating high-quality text-guided images. Yet, these models may still fail to semantically align generated images with the provided text prompts, leading to problems like incorre…
View article: No Head Left Behind – Multi-Head Alignment Distillation for Transformers
No Head Left Behind – Multi-Head Alignment Distillation for Transformers Open
Knowledge distillation aims at reducing model size without compromising much performance. Recent work has applied it to large vision-language (VL) Transformers, and has shown that attention maps in the multi-head attention modules of visio…
View article: LLM3:Large Language Model-based Task and Motion Planning with Motion Failure Reasoning
LLM3:Large Language Model-based Task and Motion Planning with Motion Failure Reasoning Open
Conventional Task and Motion Planning (TAMP) approaches rely on manually crafted interfaces connecting symbolic task planning with continuous motion generation. These domain-specific and labor-intensive modules are limited in addressing em…
View article: Molecule Design by Latent Prompt Transformer
Molecule Design by Latent Prompt Transformer Open
This work explores the challenging problem of molecule design by framing it as a conditional generative modeling task, where target biological properties or desired chemical constraints serve as conditioning variables. We propose the Laten…