Papers by Jingyuan Ma
SDC-LoRA: Singular-Subspace Drift Controlled LoRA to Mitigate Knowledge Forgetting (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to adapt LLMs to new tasks focus on limiting knowledge forgetting . et al., 2023b) suggest a solution to this problem by limiting update energy in the principal singular subspace of W0 . |
| Approach: | They propose a low-rank Adaptation (LoRA) that steers early updates away from principal directions and mitigates forgetting by constraining update energy in the principal singular subspace of W0. |
| Outcome: | The proposed model mitigates forgetting on MMLU, TruthfulQA, and HellaSwag while keeping minor-subspace updates unchanged. |
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors (2024.findings-emnlp)
Copied to clipboard
Zhexin Zhang, Yida Lu, Jingyuan Ma, Di Zhang, Rui Li, Pei Ke, Hao Sun, Lei Sha, Zhifang Sui, Hongning Wang, Minlie Huang
| Challenge: | Existing tools for detecting safety issues in LLMs are expensive and inefficient. |
| Approach: | They propose an LLM-based safety detector which annotates the safety of queries and provides explanations for its decisions. |
| Outcome: | The proposed detector outperforms baselines on four sets of query-response pairs and is effective as a safety evaluator for advanced LLMs. |
SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent large reasoning models have shown exceptional performance on various tasks, but they consume excessive tokens even for simple queries, leading to resource waste and prolonged user latency. |
| Approach: | They propose a self-adaptive reasoning strategy that automatically allocates budgets according to problem complexity and introduces GRPO for reinforcement learning to reduce output length. |
| Outcome: | The proposed model achieves an average response length compression of 61% on math reasoning tasks while maintaining accuracy. |
Temporally Grounding Natural Sentence in Video (D18-1)
Copied to clipboard
| Challenge: | Existing methods for grounding natural sentences in video are limited to a single pass. |
| Approach: | They propose a Temporal GroundNet (TGN) method that captures the evolving fine-grained frame-by-word interactions between video and sentence to ground the segment corresponding to the sentence. |
| Outcome: | The proposed method significantly improves on the state-of-the-art methods on three public datasets and shows significant improvements in performance. |
FalconCopilot: Empowering LLMs Towards Integrated Human-Machine Systems for Aviation Autonomy (2026.findings-acl)
Copied to clipboard
| Challenge: | Complex flight tasks require both intricate, long-horizon decision-making and precise operations. |
| Approach: | They propose a LLM-based copilot system that addresses deficiencies in adaptability and fine-grained decision support while integrating with a high-fidelity environment. |
| Outcome: | The proposed system shortens task completion time while attaining a level of performance approaching that of a human instructor. |
A Survey on In-context Learning (2024.emnlp-main)
Copied to clipboard
Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Jingyuan Ma, Rui Li, Heming Xia, Jingjing Xu, Zhiyong Wu, Baobao Chang, Xu Sun, Lei Li, Zhifang Sui
| Challenge: | In-context learning (ICL) is a new paradigm for natural language processing . large language models (LLMs) demonstrate the ability to learn from a few examples . |
| Approach: | They propose to explore ICL to evaluate and extrapolate the ability of large language models. |
| Outcome: | The proposed methods can be used to evaluate and extrapolate the ability of large language models. |
HAUNTATTACK: When Attack Follows Reasoning as a Shadow (2026.findings-acl)
Copied to clipboard
| Challenge: | Emerging Large Reasoning Models (LRMs) excel in mathematical and reasoning tasks, showcasing remarkable capabilities. |
| Approach: | They propose a framework that embeds harmful instructions into reasoning questions . they evaluate 11 LRMs and observe an average attack success rate of over 70% . |
| Outcome: | The proposed framework improves reasoning models by 13 percentage points over baseline. |
Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have gained increasing attention for their capacity to generate harmful content. |
| Approach: | They propose a scalable evolution framework to evolve red teaming prompts across breadth and depth dimensions, facilitating automatic generation of numerous high-quality and diverse red team prompts. |
| Outcome: | The proposed framework surpasses existing red teaming methods on attack success rate and diversity. |