Papers by Zezhong Wu
Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
Zhengyi Zhao, Shubo Zhang, Zezhong Wang, Yuxi Zhang, Huimin Wang, Yutian Zhao, Yefeng Zheng, Binyang Li, Kam-Fai Wong, Xian Wu
| Challenge: | Retrieval-Augmented Generation (RAG) provides access to external knowledge, but current research focuses on retrieval quality and 'integration bottleneck' . |
| Approach: | They propose a framework that explicitly decouples reasoning from evidence integration by generating an 'Inner-Answer' and a 'Refer-Aswer" they propose 'a joint decoding mechanism that dynamically fuses the logical coherence of the Inner-Andswer with the factual precision of the Refer-Adswer at the token level' |
| Outcome: | The proposed framework improves accuracy by 12.1% and reduces hallucinations by 16.3% on five QA benchmarks. |
MemeReaCon: Probing Contextual Meme Understanding in Large Vision-Language Models (2025.emnlp-main)
Copied to clipboard
Zhengyi Zhao, Shubo Zhang, Yuxi Zhang, Yanxi Zhao, Yifan Zhang, Zezhong Wang, Huimin Wang, Yutian Zhao, Bin Liang, Yefeng Zheng, Binyang Li, Kam-Fai Wong, Xian Wu
| Challenge: | Current approaches focus on isolated meme analysis, either for harmful content detection or standalone interpretation, overlooking a fundamental challenge: the same meme can express different intents depending on its conversational context. |
| Approach: | They propose a benchmark to evaluate how large vision language models understand memes in their original context. |
| Outcome: | The proposed benchmark evaluates how large vision language models understand meme intent in their original context. |
T2: An Adaptive Test-Time Scaling Strategy for Contextual Question Answering (2025.emnlp-main)
Copied to clipboard
Zhengyi Zhao, Shubo Zhang, Zezhong Wang, Huimin Wang, Yutian Zhao, Bin Liang, Yefeng Zheng, Binyang Li, Kam-Fai Wong, Xian Wu
| Challenge: | Existing efficient test-time scaling methods introduce budget constraints or early stop mechanisms to avoid overthinking for straightforward questions but add human bias to the reasoning process. |
| Approach: | They propose a framework that dynamically adapts reasoning depth based on question complexity. |
| Outcome: | Experimental results show that the proposed framework achieves higher accuracy than baseline methods and reduces computational overhead by up to 25.2%. |
JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialogue Policy Learning (2024.lrec-main)
Copied to clipboard
Wai-Chung Kwan, Huimin Wang, Hongru Wang, Zezhong Wang, Bin Liang, Xian Wu, Yefeng Zheng, Kam-Fai Wong
| Challenge: | Dialogue policy learning (DPL) aims to determine an abstract representation (also known as action) to guide what the response should be. |
| Approach: | They propose a joint Transformer-based model that generates a token-grained policy that allows more dynamic dialogue action generation without the need for predefined action candidates. |
| Outcome: | The proposed model outperforms existing models showing improvements of 9% and 13% in success rate and 34% and 37% in diversity of dialogue actions across two benchmark dialogue modeling tasks. |
MVP: Enhancing Video Large Language Models via Self-supervised Masked Video Prediction (2026.acl-long)
Copied to clipboard
| Challenge: | Recent research has attempted to transfer reinforcement learning paradigms to Video Large Language Models (MLLMs) but these methods lack explicit supervision for intrinsic temporal coherence and inter-frame correlations. |
| Approach: | They propose a novel post-training objective: Masked Video Prediction (MVP) that requires the model to reconstruct a masked continuous segment from a set of challenging distractors and employs Group Relative Policy Optimization (GRPO) with a fine-grained reward function to enhance the model's understanding of video context and temporal properties. |
| Outcome: | The proposed model improves video reasoning capabilities by reinforcing temporal reasoning and causal understanding. |