Jiawei Kong

Affiliations:
  • Tsinghua University, Tsinghua Shenzhen International Graduate School, Shenzhen, China
  • Harbin Institute of Technology, Shenzhen, China


According to our database1, Jiawei Kong authored at least 15 papers between 2024 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference Optimization.
CoRR, May, 2026

Looking Back and Forth: Cross-Image Attention Calibration and Attentive Preference Learning for Multi-Image Hallucination Mitigation.
CoRR, March, 2026

Towards Distillation-Resistant Large Language Models: An Information-Theoretic Perspective.
CoRR, February, 2026

Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization.
CoRR, February, 2026

Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025
Wolf Hidden in Sheep's Conversations: Toward Harmless Data-Based Backdoor Attacks for Jailbreaking Large Language Models.
CoRR, May, 2025

Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in Pre-trained Vision-Language Models.
CoRR, February, 2025

Retrievals Can Be Detrimental: A Contrastive Backdoor Attack Paradigm on Retrieval-Augmented Diffusion Models.
CoRR, January, 2025

Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

One Perturbation is Enough: On Generating Universal Adversarial Perturbations Against Vision-Language Pre-Training Models.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024
CLIP-Guided Networks for Transferable Targeted Attacks.
CoRR, 2024

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models.
CoRR, 2024

Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses.
CoRR, 2024

CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks.
Proceedings of the Computer Vision - ECCV 2024, 2024


  Loading...