Get started
Author

Sheng Zhong

When Does Visual Generation Help Visual Understanding in Unified Multimodal Models?
2026 · Yubo Zhu, Zhehan Kan, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 5
PDF
Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots
2026 · Xu, Ling, Li, Borui, et al. · arXiv (Cornell University) · 4
PDF
Neural Implicit Action Fields: From Discrete Waypoints to Continuous Functions for Vision-Language-Action Models
2026 · Liu, Haoyun, Zhao, Jianzhuang, et al. · arXiv (Cornell University) · 4
PDF
Towards Privacy-Preserving LLM Inference via Covariant Obfuscation (Technical Report)
2026 · Lin, Yu, Zhang, Qizhi, et al. · arXiv (Cornell University) · 3
PDF
KFS-RAG: Mitigating Database Leakage in RAG Systems with Keyword-Grounded Fact Substitution
2026 · ZiLiang Zhang, Yubo Zhu, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 2
PDF
PURPOSE: Poisoning Conflict Resolution in RAG via Proxy-Fact-Grounded Updates
2026 · Wang, Zijian, Zhu, Yubo, et al. · arXiv (Cornell University) · 1
PDF
Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements
2026 · Li, Yue, Li, Xiao, et al. · arXiv (Cornell University) · 1
PDF
Gradient Mirage: Trainable yet Label-Unidentifiable Gradients in Large Language Model Split Learning
2026 · Miao, Shiyu, Mao, Yunlong, et al. · arXiv (Cornell University)
PDF
Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints
2026 · Huang, Zirui, Mao, Yunlong, et al. · arXiv (Cornell University)
PDF
TraceCLIP: Recovering Local Semantics from Patch-to-CLS Contributions
2026 · Liu, Xinran, Shi, Shouqian, et al. · arXiv (Cornell University)
PDF
Lens: Bringing the Right Semantic Perspective into Focus for Training-Free Multimodal Representation Learning
2026 · Liu, Xinran, Shi, Shouqian, et al. · arXiv (Cornell University)
PDF
Breaking the Synthetic-Real Domain Shortcut for Training-Free Generative Replay-based Class Incremental Learning
2026 · Zhang, Tao, Fan, Qixuan, et al. · arXiv (Cornell University)
PDF
SSV: Sparse Speculative Verification for Efficient LLM Inference
2026 · Wang, Zhibin, Zhong, Ziyu, et al. · arXiv (Cornell University)
PDF
Resolving the bias-precision paradox with stochastic causal representation learning for personalized medicine
2026 · Zhang, Peisong, Peng, Manqiang, et al. · arXiv (Cornell University)
PDF
Thorki: Decoupling General and Personalized Knowledge with Collaborative Fusion for Personalized Federated Learning
2026 · He, Qiang, Chen, Rui, et al. · Deakin Research Online (Deakin University)
Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors
2026 · Zi Li, Tian Zhou, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Works count: 17
Citation count: 20
H-index: 3
I10-index:
Year
Topic
Type