20 papers
RelLedger: Relational Information Governance for LLM Agent Organizations
Junxi Huang, Wenshuo Chen, Nuoxuan Li +7
In LLM agent organizations, shared records determine which facts are available for later decisions. A sender consults interaction histories before deciding whether to report an eve…
BeamRMX: Radiation-Pattern-Driven Learning for Generalizable Beam Radio Map Prediction and Beam Management
Yue Zhang, Xiucheng Wang, Wenshuo Chen +1
The evolution toward sixth-generation (6G) wireless networks is driving larger antenna arrays and highly directional multi-beam transmission, making accurate knowledge of beam-depe…
When Efficiency Becomes Fragility: Exploiting Dynamic Routing Vulnerabilities in Adaptive UAV Tracking
Shaofeng Liang, Runwei Guan, Wenshuo Chen +7
Resource constraints on UAV platforms have driven a paradigm shift in aerial tracking, from pursuing performance toward balancing accuracy with efficiency. Adaptive Transformer Tra…
Traffic-CBM: A Structurally Interpretable Multimodal Framework for Encrypted Traffic Classification
Honglei Jin, Wenshuo Chen, Shaofeng Liang +6
Encrypted traffic classification has achieved strong performance, but its decision process remains difficult to interpret. Existing methods usually combine flow statistics, packet…
MemoGen: Can Past Experience Improve Future Text-to-Image Generation?
Wenshuo Chen, Kuimou Yu, Bowen Tian +10
Modern text-to-image models have achieved strong visual synthesis, yet remain unreliable when prompts require implicit visual constraints, relational reasoning, or external knowled…
ABLE: Representing and Mapping LLMs via Attribution-Based Large-model Embedding
Zirui Wang, Yusen Hou, Shaofeng Liang +4
The explosive growth of large language models (LLMs) has created a heterogeneous and poorly documented ecosystem, making systematic model comparison increasingly important for prov…
AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise
Bowen Tian, Caixue He, Jiemin Wu +4
Editing complex, long-form knowledge in Large Language Models remains a significant challenge due to the difficulty of maintaining generation coherence. Existing autoregressive met…
Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment
Haozhe Jia, Pengyu Yin, Wenshuo Chen +6
Physics-informed diffusion models typically enforce PDE constraints only on final outputs, leaving intermediate representations unconstrained and prone to shortcut learning under s…
Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Control
Haozhe Jia, Honglei Jin, Yuan Zhang +9
Natural language is an intuitive interface for humanoid robots, yet streaming whole-body control requires control representations that are executable now and anticipatory of future…
Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models
Haosen Li, Wenshuo Chen, Lei Wang +4
Diffusion models have achieved remarkable success in synthesizing complex static and temporal visuals, a breakthrough largely driven by Classifier-Free Guidance (CFG). However, des…
Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization
Haosen Li, Wenshuo Chen, Lei Wang +3
Text-to-image diffusion models have achieved remarkable generative capabilities, yet accurately aligning complex textual prompts with synthesized layouts remains an ongoing challen…
-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models
Haosen Li, Wenshuo Chen, Shaofeng Liang +3
Diffusion models have achieved unprecedented success in text-aligned generation, largely driven by Classifier-Free Guidance (CFG). However, standard CFG operates strictly on instan…
TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution
Yang Yang, Zining Zhong, Jindong Li +5
LLM-driven program evolution can discover high-quality programs, but high API cost and run-to-run variance hinder reliable progress. We propose TurboEvolve, a multi-island evolutio…
ECHO: Edge-Cloud Humanoid Orchestration for Language-to-Motion Control
Haozhe Jia, Jianfei Song, Yuan Zhang +5
We present ECHO, an edge--cloud framework for language-driven whole-body control of humanoid robots. A cloud-hosted diffusion-based text-to-motion generator synthesizes motion refe…
Neural Electromagnetic Fields for High-Resolution Material Parameter Reconstruction
Zhe Chen, Peilin Zheng, Wenshuo Chen +3
Creating functional Digital Twins, simulatable 3D replicas of the real world, is a central challenge in computer vision. Current methods like NeRF produce visually rich but functio…
Text2Weight: Bridging Natural Language and Neural Network Weight Spaces
Bowen Tian, Wenshuo Chen, Zexi Li +3
How far are we really from automatically generating neural networks? While neural network weight generation shows promise, current approaches struggle with generalization to unseen…
CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generation
Kaishen Yuan, Yuting Zhang, Shang Gao +3
Emotional Image Content Generation (EICG) aims to generate semantically clear and emotionally faithful images based on given emotion categories, with broad application prospects. W…
Physics-Informed Representation Alignment for Sparse Radio-Map Reconstruction
Haozhe Jia, Wenshuo Chen, Zhihui Huang +7
Radio map reconstruction is essential for enabling advanced applications, yet challenges such as complex signal propagation and sparse observational data hinder accurate reconstruc…
Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Models
Songning Lai, Yu Huang, Jiayu Yang +3
The increasing complexity of AI models, especially in deep learning, has raised concerns about transparency and accountability, particularly in high-stakes applications like medica…
Learning New Concepts, Remembering the Old: Continual Learning for Multimodal Concept Bottleneck Models
Songning Lai, Mingqian Liao, Zhangyi Hu +6
Concept Bottleneck Models (CBMs) enhance the interpretability of AI systems, particularly by bridging visual input with human-understandable concepts, effectively acting as a form…