Papers by Yifeng Liu
WW-CSL: A New Dataset for Word-Based Wearable Chinese Sign Language Detection (2024.lrec-main)
Copied to clipboard
| Challenge: | Sign language is an effective non-verbal communication mode for the hearingimpaired people. |
| Approach: | They propose a three-form scheme to represent dynamic CSL gestures using a word-based dataset. |
| Outcome: | The proposed framework integrates the local sequential sensor data derived from the wearable-based CSL gestures with the global, fine-grained skeleton representations captured from video-based gestures simultaneously. |
Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing jailbreak methods create a forced instruction-following scenario, or search adversarial prompts with prefix or suffix tokens to achieve a specific representation manually or automatically. |
| Approach: | They propose a method that rewrites the original instruction to achieve a jailbreak . they propose rewriting the original instructions to improve the attack strategy . |
| Outcome: | The proposed method is more efficient and easier to identify since no additional features are introduced. |
Beyond Logits: Aligning Feature Dynamics for Effective Knowledge Distillation (2025.acl-long)
Copied to clipboard
Guoqiang Gong, Jiaxing Wang, Jin Xu, Deping Xiang, Zicheng Zhang, Leqi Shen, Yifeng Zhang, JunhuaShu JunhuaShu, ZhaolongXing ZhaolongXing, Zhen Chen, Pengzhang Liu, Ke Zhang
| Challenge: | Knowledge distillation (KD) compresses large language models into lightweight versions called student models. |
| Approach: | They propose to align the entire feature dynamics between teacher and student models by using two additional loss terms to achieve this. |
| Outcome: | The proposed method matches the entire feature dynamics between teacher and student models rather than just the final states. |
\mathcal XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies focus on the data perspectives of instruction tuning, leaving room for exploring advanced training schemes. |
| Approach: | They argue that prior works overlook the possibility of improving code instruction tuning by advancing existing training schemes. |
| Outcome: | The proposed model is dense because all parameters are activated to predict the next token (assuming it is a decoder-only LLM). |
Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding (2023.acl-long)
Copied to clipboard
Haoli Bai, Zhiguang Liu, Xiaojun Meng, Li Wentao, Shuang Liu, Yifeng Luo, Nian Xie, Rongfu Zheng, Liangwei Wang, Lu Hou, Jiansheng Wei, Xin Jiang, Qun Liu
| Challenge: | Existing solutions for visual document understanding lack granularity of document textlines. |
| Approach: | They propose a supervised pre-training program to leverage structural knowledge nested in document textlines to achieve fine-grained alignment between visual regions and texts. |
| Outcome: | The proposed system performs better on various VDU tasks in English and Chinese. |
UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to extract rich correlations between entities and relations are not fully exploited by existing methods. |
| Approach: | They propose to unify entities and relations by jointly encoding them within a concatenated natural language sequence and unify the modeling of interactions with a proposed Interaction Map. |
| Outcome: | The proposed method is more efficient and efficient than existing methods and can be scaled up to 2021. |
R-PRM: Reasoning-Driven Process Reward Modeling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing Process Reward Models (PRMs) output evaluation scores directly, limiting both learning efficiency and evaluation accuracy. |
| Approach: | They propose a Reasoning-Driven Process Reward Modeling (R-PRM) which activates inherent reasoning to enhance process-level evaluation. |
| Outcome: | The proposed model outperforms baseline models on ProcessBench and PRMBench by 13.9 and 8.5 F1 scores. |
Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for training large language models rely heavily on high-quality parallel data, which are often scarce or unavailable for low-resource languages. |
| Approach: | They propose a reinforcement training method using only monolingual text to elevate LLMs’ translation capabilities on massive low-resource languages while retaining their performance on high-resourced languages. |
| Outcome: | The proposed model outperforms LLaMAX, one of the strongest open-source multilingual LLMs on 1,414 language directions on Flores-101 dataset. |