Jiahao Xu

Venues

Frequent coauthors

Papers

1. EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving
   ACL 2026 ·

   Mukai Li

   DBLP profile ↗ORCID search ↗
2. QA-GraphRAG: Query-Adaptive Plug-and-Play Retrieval Integration for Graph-based Retrieval-Augmented Generation
   VLDB 2026 ·

   Zeang Sheng

   DBLP profile ↗ORCID search ↗
3. XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts
   ACL 2026 · Jiahao Xu
4. Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregation
   WACV 2025 · Jiahao Xu
5. Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
   ICML 2025 ·

   Zicheng Lin

   DBLP profile ↗ORCID search ↗
6. Data-Efficient Alignment in Medical Imaging via Reconfigurable Generative Networks
   WACV 2025 ·

   Divya Saxena

   DBLP profile ↗ORCID search ↗
7. Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection
   CVPR 2025 · Jiahao Xu
8. Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning Models
   ICML 2025 ·

   Xingyu Chen

   DBLP profile ↗ORCID search ↗
9. Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation
   EMNLP 2025 ·

   Ziyin Zhang

   DBLP profile ↗ORCID search ↗
10. FanChuan: A Multilingual and Graph-Structured Benchmark For Parody Detection and Analysis
    ACL 2025 ·

    Yilun Zheng

    DBLP profile ↗ORCID search ↗
11. Identify Backdoored Model in Federated Learning via Individual Unlearning
    WACV 2025 · Jiahao Xu
12. Improving Identity Preservation in Video Generation with Multi-Branch Models
    ACM MM 2025 · Jiahao Xu
13. RaSA: Rank-Sharing Low-Rank Adaptation
    ICLR 2025 ·

    Zhiwei He

    DBLP profile ↗ORCID search ↗
14. Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
    ACL 2025 ·

    Youliang Yuan

    DBLP profile ↗ORCID search ↗
15. The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
    NeurIPS 2025 ·

    Ke Ji

    DBLP profile ↗ORCID search ↗
16. Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models
    NeurIPS 2025 ·

    Yue Wang

    DBLP profile ↗ORCID search ↗
17. Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
    NeurIPS 2025 ·

    Xiaoyuan Liu

    DBLP profile ↗ORCID search ↗
18. Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
    NeurIPS 2025 ·

    Mengru Wang

    DBLP profile ↗ORCID search ↗
19. LB-UNet: A Lightweight Boundary-Assisted UNet for Skin Lesion Segmentation
    MICCAI 2024 · Jiahao Xu
20. RG-GAN: Dynamic Regenerative Pruning for Data-Efficient Generative Adversarial Networks
    AAAI 2024 ·

    Divya Saxena

    DBLP profile ↗ORCID search ↗
21. TransAgents: Build Your Translation Company with Language Agents
    EMNLP 2024 ·

    Minghao Wu

    DBLP profile ↗ORCID search ↗