1 citations · 2 across the 13 of their papers we have counts for
19 papers
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation
Weijie Wang, Haomin Zhang, Ye Li +7
Long-form agentic video generation must turn a screenplay into shots that remain spatially and temporally consistent across nonconsecutive requests. Passing prompts or recent frame…
Do Defenses Against LLM Extraction Work Across Attacks? A Lifecycle Benchmark of Black-Box Model Extraction
Shuze Liu, Kaixiang Zhao, Runyang Xu +4
Large language models (LLMs) deployed through text-only APIs face model extraction risks, as adversaries can collect their responses to train surrogates that reproduce their capabi…
REVO: Rollout-Efficient Off-Policy Distillation via Variance-Guided Reuse
Yuxiao Yang, Shangzhe Li, Tianrun Yu +3
On-policy distillation (OPD) trains language models using dense token-level teacher supervision on student-generated trajectories. However, its reliance on frequently refreshed stu…
An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning
Shangzhe Li, Yuxiao Yang, Tianrun Yu +4
We study on-policy distillation (OPD) through the lens of reinforcement learning, establishing a connection between the reverse-KL objective in OPD and KL-regularized policy optimi…
Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It
Tianrun Yu, Kaixiang Zhao, Shangzhe Li +4
We study training-inference mismatch in reinforcement learning with verifiable rewards (RLVR) for large language models, where rollouts are sampled by an inference engine while gra…
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation
Yuxiao Yang, Tianrun Yu, Shangzhe Li +6
We study length inflation in on-policy distillation (OPD), where student responses can become excessively long and even exhaust the generation budget. We identify \emph{termination…
Community-Aware Assessment of Social Textual Engagement and Resonance: A Human-Centric Perspective on User-Generated Content Evaluation
Tianjiao Li, Kai Zhao, Xiang Li +2
Traditional Video Quality Assessment (VQA) focuses narrowly on aesthetic fidelity, overlooking the complex social dynamics that define quality in User-Generated Content (UGC). In t…
Self-Correction Can Amplify Hallucinations: Fact-Level Repair with Graph-Based Evidence Routing in Multimodal Generation
Kaixiang Zhao, Tianrun Yu, Shawn Huang +3
We study fact-level repair for multimodal generation, where a fluent output may contain specific facts that are not supported by the input. Existing inference-time repair methods o…
LARK: Learnability-Grounded Trajectory Selection for Efficient Reasoning Distillation
Tianrun Yu, Kaixiang Zhao, Chih-Chun Chen +5
We study trajectory selection for reasoning distillation, where teacher-generated reasoning trajectories are selectively used as supervision for a student model. Existing methods r…
GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
Kaixiang Zhao, Bolin Shen, Yuyang Dai +2
Graph neural networks (GNNs) deployed as cloud services can be stolen through model-extraction attacks, which train a surrogate from query responses to reproduce the target's behav…
FRAME: Forensic Routing and Adaptive Multi-path Evidence Fusion for Image Manipulation Detection
Kaixiang Zhao, Tianrun Yu, Aoxu Zhang +3
The proliferation of sophisticated image editing tools and generative artificial intelligence models has made verifying the authenticity of digital images increasingly challenging,…
FACTOR: Counterfactual Training-Free Test-Time Adaptation for Open-Vocabulary Object Detection
Kaixiang Zhao, Mao Ye, Lihua Zhou +4
Open-vocabulary object detection often fails under distribution shifts, as it can be misled by spurious correlations between non-causal visual attributes (e.g., brightness, texture…
Provable and Practical In-Context Policy Optimization for Self-Improvement
Tianrun Yu, Yuxiao Yang, Zhaoyang Wang +6
We study test-time scaling, where a model improves its answer through multi-round self-reflection at inference. We introduce In-Context Policy Optimization (ICPO), in which an agen…
When the Server Steps In: Calibrated Updates for Fair Federated Learning
Tianrun Yu, Kaixiang Zhao, Cheng Zhang +4
Federated learning (FL) has emerged as a transformative distributed learning paradigm, enabling multiple clients to collaboratively train a global model under the coordination of a…
Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses
Lincan Li, Bolin Shen, Chenxi Zhao +4
Graph-structured data, which captures non-Euclidean relationships and interactions between entities, is growing in scale and complexity. As a result, training state-of-the-art grap…
A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives
Kaixiang Zhao, Lincan Li, Kaize Ding +3
Machine learning (ML) models have significantly grown in complexity and utility, driving advances across multiple domains. However, substantial computational resources and speciali…
DESIGN: Encrypted GNN Inference via Server-Side Input Graph Pruning
Kaixiang Zhao, Joseph Yousry Attalla, Qian Lou +1
Graph Neural Networks (GNNs) have achieved state-of-the-art performance in various graph-based learning tasks. However, enabling privacy-preserving GNNs in encrypted domains, such…
A Survey on Model Extraction Attacks and Defenses for Large Language Models
Kaixiang Zhao, Lincan Li, Kaize Ding +3
Model extraction attacks pose significant security threats to deployed language models, potentially compromising intellectual property and user privacy. This survey provides a comp…
A Survey of Model Extraction Attacks and Defenses in Distributed Computing Environments
Kaixiang Zhao, Lincan Li, Kaize Ding +3
Model Extraction Attacks (MEAs) threaten modern machine learning systems by enabling adversaries to steal models, exposing intellectual property and training data. With the increas…