Get started
Author

Yang Xiang

Instruction Anchor: Dissecting the Mechanistic Dynamics of Modality Arbitration
2026 · Zhang, Yu, Xu, Mufan, et al. · arXiv (Cornell University) · 14
PDF
Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm
2026 · Xiang, Bajian, Wen, Cheng, et al. · arXiv (Cornell University) · 10
PDF
Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning
2026 · Zhang, Hongbin, Wang, Chaozheng, et al. · arXiv (Cornell University) · 9
PDF
LinguaLIFT: An Effective Two-Stage Instruction Tuning Framework for Low-Resource Language Reasoning
2026 · Hongbin Zhang, Kehai Chen, et al. · IEEE Transactions on Audio Speech and Language Processing · 9
PDF
Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck
2026 · Zhang, Hongbin, Chen, Kehai, et al. · arXiv (Cornell University) · 6
PDF
Decoupling Skeleton and Flesh: Efficient Multimodal Table Reasoning with Disentangled Alignment and Structure-aware Guidance
2026 · Zhu, Yingjie, Bai, Xuefeng, et al. · arXiv (Cornell University) · 3
PDF
Five Queries Are Enough: Query-Efficient and Surrogate-Free Membership Inference Attacks on RAG via Entailment
2026 · Nguyen, Nguyen Linh Bao, Ma, Wanlun, et al. · arXiv (Cornell University) · 2
PDF
Rethinking Federated Unlearning via the Lens of Memorization
2026 · Wei, Jiaheng, Zhang, Yanjun, et al. · arXiv (Cornell University) · 1
PDF
Reason Analogically via Cross-domain Prior Knowledge: An Empirical Study of Cross-domain Knowledge Transfer for In-Context Learning
2026 · Liu, Le, Li, Zhiming, et al. · arXiv (Cornell University) · 1
PDF
Towards Effective In-context Cross-domain Knowledge Transfer via Domain-invariant-neurons-based Retrieval
2026 · Yan, Jianzhi, Li, Zhiming, et al. · arXiv (Cornell University) · 1
PDF
Functional Subnetwork Localization for Efficient Continual Learning in Large Language Models
2026 · Jiang, Shuoran, Zhu, Wentao, et al. · arXiv (Cornell University)
PDF
EvolvAttack: Backdooring self Evolving VLM Agents
2026 · Zou, Chuan, Xiang, Yang, et al. · arXiv (Cornell University)
PDF
MVGraph: Benchmarking LVLMs on Evidence Composition across Multi-View Visual Graph
2026 · Zhu, Yingjie, Cheng, Han, et al. · arXiv (Cornell University)
PDF
Not What a Child Expressed: Auditing the Sign-to-Text Safety Interface in Child-Facing AI
2026 · Memon, Muhammad Rafiullah, Vo, Viet, et al. · arXiv (Cornell University)
PDF
Verifier-Guided Synthetic Augmentation for 3D Human Shape Generation
2026 · Wu, Yuexuan, Xiang, Yang, et al. · arXiv (Cornell University)
PDF
DualAnchor: Preserving Language Priors and Improving Lexical Fidelity in Gloss-Free Sign Language Translation
2026 · Zhang, Hongbin, Liu, Junhao, et al. · arXiv (Cornell University)
PDF
Beyond Her: Safety Dynamics in Role-play AI Companions
2026 · Deng, Zehang, Xie, Zhaoyang, et al. · arXiv (Cornell University)
PDF
REG: Retrieval via Emotion Similarity for Guiding Empathetic Dialogue Generation
2026 · Association for Computational Linguistics 2026, Hou, Yuexian, et al. · Underline Science Inc.
When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning
2026 · Association for Computational Linguistics 2026, Ji, Yixin, et al. · Underline Science Inc.
PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis
2026 · Li, Bowen, Guo, Shaotong, et al. · arXiv (Cornell University)
PDF
ConSEAL: Connectivity-Informed Streamline Endpoint Alignment for Diffeomorphic Cortical Registration
2026 · Xiang, Yang, Cole, Martin, et al. · arXiv (Cornell University)
PDF
CoDA: Towards Effective Cross-domain Knowledge Transfer via CoT-guided Domain Adaptation
2026 · Yan, Jianzhi, Liu, Le, et al. · arXiv (Cornell University)
PDF
Linguistic Rule Induction Improves Adversarial and OOD Robustness in Large Language Models
2024 · Shuoran Jiang, Qingcai Chen, et al. · Language Resources and Evaluation Conference (LREC)
PDF
Works count: 24
Citation count: 58
H-index: 5
I10-index: 2
Year
Topic
Type