papers

Publications (22)

cs.RO2026

GeCo-SRT: Geometry-aware Continual Adaptation for Robotic Cross-Task Sim-to-Real Transfer

Wenbo Yu, Wenke Xia, Weitao Zhang +1

Bridging the sim-to-real gap is important for applying low-cost simulation data to real-world robotic systems. However, previous methods are severely limited by treating each trans…

cs.CV2026

Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization

Hao Fang, Wenbo Yu, Bin Chen +4

Federated Learning (FL) has emerged as a compelling paradigm for privacy-preserving distributed machine learning, allowing multiple clients to collaboratively train a global model…

cs.LG2026

A Probabilistic Approach to Wildfire Spread Prediction Using a Denoising Diffusion Surrogate Model

Wenbo Yu, Anirbit Ghosh, Tobias Sebastian Finn +3

Thanks to recent advances in generative AI, computers can now simulate realistic and complex natural processes. We apply this capability to predict how wildfires spread, a task mad…

cond-mat.mtrl-sci2023

Features of a nano-twist phase in the nanolayered Ti3AlC2 MAX phase

Julien Guénolé, Vincent Taupin, Maxime Vallet +2

Complex intermetallic materials known as MAX phases exhibit exceptional properties from both metals and ceramics, largely thanks to their nanolayered structure. With high-resolutio…

cs.CL2025

Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model

Ling Team, Anqi Shen, Baihui Li +101

We present Ring-1T, the first open-source, state-of-the-art thinking model with a trillion-scale parameter. It features 1 trillion total parameters and activates approximately 50 b…

cs.CV2024

Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses

Hao Fang, Yixiang Qiu, Hongyao Yu +7

Deep Neural Networks (DNNs) have revolutionized various domains with their exceptional performance across numerous applications. However, Model Inversion (MI) attacks, which disclo…

cs.RO2026

Affordance2Action: Task-Conditioned Scene-level Affordance Grounding for Real-Time Manipulation

Litao Liu, Yifan Han, Pengfei Yi +9

Task-conditioned manipulation requires grounding instructions to task-relevant functional parts rather than object categories. This setting is scene-dependent and often one-to-many…

cs.LG2026

GLM-5: from Vibe Coding to Agentic Engineering

GLM-5-Team, :, Aohan Zeng +184

We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (AR…

cs.CV2025

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models

Hao Fang, Jiawei Kong, Wenbo Yu +5

Vision-Language Pre-training (VLP) models have exhibited unprecedented capability in many applications by taking full advantage of the multimodal alignment. However, previous studi…

cs.AI2025

UDA: Unsupervised Debiasing Alignment for Pair-wise LLM-as-a-Judge

Yang Zhang, Cunxiang Wang, Lindong Wu +4

Pairwise evaluation of Large Language Models (LLMs) is a common paradigm, but it is prone to preference bias, where judges systematically favor certain outputs, such as their own.…

cs.CR2026

Bypassing Copyright Protection in Diffusion-based Customization via Two-Stage Latent Feature Optimization

Ziang Xu, Wenbo Yu, Hongyao Yu +6

With the growing concerns over copyright infringement in diffusion-based customization, adversarial attacks have emerged as a prominent defense strategy to prevent malicious conten…

cs.IT2024

Editable-DeepSC: Cross-Modal Editable Semantic Communication Systems

Wenbo Yu, Bin Chen, Qinshan Zhang +1

Different from data-oriented communication systems that primarily focus on how to accurately transmit every bit of data, task-oriented semantic communication systems only transmit…

cs.CL2026

CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment

Wenbo Yu, Bohua Wang, Hao Fang +10

Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns. While existing LLM safety guardrails excel in English or multilin…

cs.CL2026

Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation

Yanzhi Tian, Cunxiang Wang, Zeming Liu +5

Large Language Models (LLMs) have significantly advanced Machine Translation (MT), applying them to linguistically complex domains-such as Social Network Services, literature etc.…

cs.AI2026

TraceSIR: A Multi-Agent Framework for Structured Analysis and Reporting of Agentic Execution Traces

Shu-Xun Yang, Cunxiang Wang, Haoke Zhang +12

Agentic systems augment large language models with external tools and iterative decision making, enabling complex tasks such as deep research, function calling, and coding. However…

cs.CL2025

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

5 Team, Aohan Zeng, Xin Lv +167

We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that s…

cs.RO2026

Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning

Wenke Xia, Pei Ren, Wenbo Yu +10

Offline-to-online reinforcement learning is promising for generalizable robotic manipulation, yet its full-stack complexity obscures reproduction and diagnosis. Within such systems…

cs.CL2026

RAVEL: Reasoning Agents for Validating and Evaluating LLM Text Synthesis

Andrew Zhuoer Feng, Cunxiang Wang, Yu Luo +9

Large Language Models have evolved from single-round generators into long-horizon agents, capable of complex text synthesis scenarios. However, current evaluation frameworks lack t…

cs.AI2025

GI-NAS: Boosting Gradient Inversion Attacks Through Adaptive Neural Architecture Search

Wenbo Yu, Hao Fang, Bin Chen +5

Gradient Inversion Attacks invert the transmitted gradients in Federated Learning (FL) systems to reconstruct the sensitive data of local clients and have raised considerable priva…

cs.CV2025

MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defense

Yixiang Qiu, Hongyao Yu, Hao Fang +6

Model Inversion (MI) attacks aim at leveraging the output information of target models to reconstruct privacy-sensitive training data, raising critical concerns regarding the priva…

cs.IT2026

Editable-DeepSC: Reliable Cross-Modal Semantic Communications for Facial Editing

Bin Chen, Wenbo Yu, Qinshan Zhang +4

Interactive computer vision (CV) plays a crucial role in various real-world applications, whose performance is highly dependent on communication networks. Nonetheless, the data-ori…

cs.CV2019

Mcity Data Collection for Automated Vehicles Study

Yiqun Dong, Yuanxin Zhong, Wenbo Yu +5

The main goal of this paper is to introduce the data collection effort at Mcity targeting automated vehicle development. We captured a comprehensive set of data from a set of perce…