Papers by Yupeng Chang
BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards (2026.findings-acl)
Copied to clipboard
| Challenge: | Critic-free reinforcement learning with verifiable rewards (RLVR) is a practical paradigm for aligning Large Language Models. |
| Approach: | They propose a framework that stabilizes advantage estimation by combining prompt-local on-policy statistics with semantic-cluster-conditioned historical moments. |
| Outcome: | Experiments show that RLVR improves training stability and performance compared to critic-based methods . compared with other approaches, RL VR improves in cold-start regimes with binary verifiers . |
LoRA-MGPO: Mitigating Double Descent in Low-Rank Adaptation via Momentum-Guided Perturbation Optimization (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Low-Rank Adaptation (LoRA) adapts large language models by training only a small fraction of parameters, but as the rank of the low-rank matrices increases, LoRA exhibits an unstable “double descent” phenomenon, which delays convergence and impairs generalization by causing instability due to the attraction to sharp local minima. |
| Approach: | They propose a framework that incorporates Momentum-Guided Perturbation Optimization (MGPO) MGPO stabilizes training dynamics by mitigating double descent phenomenon and guiding weight perturbations using momentum vectors from the optimizer’s state. |
| Outcome: | The proposed framework improves performance on natural language understanding benchmarks and shows that it improves convergence and generalization. |
Context-Aware Conversation Thread Detection in Multi-Party Chat (D19-1)
Copied to clipboard
| Challenge: | In multi-party chat, it is common for multiple conversations to occur concurrently . a new model that automatically disentangles conversation threads is proposed . |
| Approach: | They propose a Context-Aware Thread Detection model that automatically disentangles conversation threads in chat logs. |
| Outcome: | The proposed model outperforms state-of-the-art models on four real-world chat logs. |
MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AI (2026.findings-acl)
Copied to clipboard
Wenpeng Xing, Zhonghao Qi, Yupeng Qin, Yilin Li, Caini Chang, Jiahui Yu, Changting Lin, Zhenzhen Xie, Meng Han
| Challenge: | Large Language Models (LLMs) are vulnerable to jailbreak, authors say . authors propose a robust, layered defense architecture designed for LLM–tool interactions . |
| Approach: | They propose a robust, layered defense architecture designed for LLM–tool interactions . they propose XCP-Guard, which employs a three-stage detection pipeline . |
| Outcome: | The proposed model achieves 96.01% accuracy in identifying adversarial prompts . the model is based on a three-stage detection pipeline that balances efficiency with accuracy . |
SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling (2026.acl-long)
Copied to clipboard
| Challenge: | Low-Rank Adaptation (LoRA) is a parameter-efficient fine-tuning method for large language models. |
| Approach: | They propose a drop-in extension that reparameterizes a rank-rtot update as a sum of K *static* low-rank experts. |
| Outcome: | Experiments on reasoning and knowledge-intensive benchmarks show consistent gains over matched-budget LoRA. |
Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Interactive Fiction (IF) games with real human-written natural language texts provide a new natural evaluation for language understanding techniques. |
| Approach: | They propose to re-formulate IF game solving as Multi-Passage Reading Comprehension tasks using context-query attention mechanisms and structured prediction to efficiently generate and evaluate action outputs. |
| Outcome: | The proposed methods achieve high winning rates and low data requirements on the recent IF benchmark (Jericho) |