Papers by Jiaqi Ma

18 papers
Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings (2025.findings-acl)

Copied to clipboard

Challenge: Visualized Document Retrieval (VDR) uses large vision-language models to encode document pages into embeddings.
Approach: They evaluate methods to reduce patch embeddings per page while minimizing performance degradation.
Outcome: The proposed method maintains 98.2% of retrieval performance with only 11.8% of original memory usage and preserves 94.6% effectiveness at 2% memory footprint.
Unity in Diversity: Collaborative Pre-training Across Multimodal Medical Sources (2024.acl-long)

Copied to clipboard

Challenge: Current pre-training techniques rely on a limited scope of medical data, limiting the range of downstream tasks.
Approach: They propose a pre-training strategy that unifies patient data within individual sources and captures explicit and implicit correlations between patients across different sources.
Outcome: The proposed strategy bridges the gap between multimodal medical sources by aggregating patient data within individual sources and capturing explicit and implicit correlations between patients across sources.
CoRelation: Boosting Automatic ICD Coding through Contextualized Code Relation Learning (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for boosting ICD coding performance lack a model for complex code relations . current methods overlook the importance of context in clinical notes .
Approach: They propose a contextualized and flexible framework to enhance learning of ICD code relations . they use clinical notes to model all possible code relations using a dependent learning paradigm .
Outcome: The proposed approach improves on six public ICD coding datasets compared to state-of-the-art models.
Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for long chain-of-thought (LCoT) are coarse-grained, reward hacking, and poor generalization.
Approach: They propose a Long Chain-of-Thought (LCoT) model that integrates reinforcement learning with verifiable rewards with a process-aware verification approach.
Outcome: The proposed model improves reasoning and code generation tasks while reducing the cost of training and performance bottlenecks.
Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications (2024.naacl-long)

Copied to clipboard

Challenge: Recent studies suggest using large language models to make tabular classifications . however, LLMs have been shown to exhibit harmful social biases based on stereotypes and inequalities present in society.
Approach: They propose to use large language models to make tabular classifications . they show that LLMs inherit biases from their training data .
Outcome: The proposed models exhibit harmful biases that reflect stereotypes and inequalities in society.
Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for streaming video understanding are query-agnostic and implicitly model video evidence.
Approach: They propose a framework that establishes explicit, structured alignment between the accumulated video evidence and the query’s expected response conditions via scene graphs.
Outcome: The proposed model achieves more interpretable and accurate response timing decisions on both proactive and reactive tasks.
LongVideoAgent: Multi-Agent Reasoning with Long Videos (2026.acl-long)

Copied to clipboard

Challenge: a key emerging challenge is robust long video understanding, authors say . current methods compress content into lossy summaries or rely on limited toolsets .
Approach: They propose a multi-agent framework where a master LLM coordinates a grounding agent and a vision agent to extract targeted textual observations.
Outcome: The proposed model outperforms strong non-agent baselines on episode-level datasets . the proposed model significantly outperformed existing models on other datasets.
FEDKIM: Adaptive Federated Knowledge Injection into Medical Foundation Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing foundation models are limited in access to diverse modalities and privacy regulations restrict the development of comprehensive foundation models.
Approach: They propose a knowledge injection approach to extract and inject healthcare knowledge into medical foundation models to enhance their ability to handle multiple tasks and modalities.
Outcome: The proposed method preserves privacy and enhances the model’s ability to handle complex medical tasks involving multiple modalities.
InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model (2025.findings-acl)

Copied to clipboard

Challenge: Despite the promising performance of Large Vision Language Models, they sometimes generate incorrect outputs.
Approach: They propose a multi-modal reward model that aligns LVLMs with human preferences.
Outcome: The proposed model achieves excellent results on the latest multi-modal reward model benchmark and shows competitive performance on text-only reward model.
S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to incentivize LLMs’ deep thinking abilities require large-scale data or significant training efforts.
Approach: They introduce an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference.
Outcome: The proposed framework outperforms models trained on long-CoT distilled data with 3.1k initialization samples and achieves an accuracy improvement of 51.0% to 81.6%.
Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have evolved from statistical sequence predictors to sophisticated autonomous agents capable of reasoning, planning, and sustaining multi-turn conversa-tions.
Approach: They propose a system that instantiates a "Sentient Agent" that simulates human-like emotional changes and inner thoughts to provide a more realistic evaluation of the model in multi-turn conversations.
Outcome: The proposed framework measures the agent's higher-order social cognition in multi-turn conversations.
Shadow-Activated Backdoor Attacks on Multimodal Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing backdoor attacks on Multimodal Large Language Models are less applicable to open-ended conversations with users.
Approach: They propose a shadow-activated backdoor attack scenario where attackers inject malicious content into the responses of MLLMs when the responses explicitly relate to the shadowed object.
Outcome: The proposed framework achieves the desired behaviors by constructing a poisoned dataset and implementing an attention-regularized tuning strategy.
LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Existing strategies for spatial localization are limited due to their limited capacity to perceive positional data.
Approach: They propose a location-based approach that leverages locational data to optimize interaction preferences.
Outcome: The proposed approach achieves SOTA results across offline benchmarks and real-world evaluations.
Implicit Discourse Relation Identification for Open-domain Dialogues (P19-1)

Copied to clipboard

Challenge: Discourse relation identification is a challenging problem in open-domain dialogue systems . previous work relies on formal text but this data is not suitable for informal dialogue .
Approach: They propose a method to automatically extract the implicit discourse relation argument pairs from dialogic turns and a pipeline to identify them.
Outcome: The proposed pipeline extracts argument pairs from dialogic turns and improves it by performing feature ablation and incorporating dialogue features.
Hierarchical Pretraining on Multimodal Electronic Health Records (2023.emnlp-main)

Copied to clipboard

Challenge: Existing pretraining models on EHR data are too specific, limiting their transferability.
Approach: They propose a general, unified pretraining framework for hierarchically multimodal EHR data that can be used to train models on a large dataset before fine-tuning it on 'upstream' tasks.
Outcome: The proposed model performs on eight downstream tasks spanning three levels and compares with baselines on 18 different tasks.
BIPEFT: Budget-Guided Iterative Search for Parameter Efficient Fine-Tuning of Large Pretrained Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for parameter-efficient fine-tuning are limited by computational and storage requirements.
Approach: They propose a budget-guided iterative search strategy to disentangle binary module and rank dimension search spaces and early selection strategies based on parameter budgets.
Outcome: The proposed method significantly improves search efficiency on public benchmarks.
Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder (2024.acl-long)

Copied to clipboard

Challenge: EEG-based language decoding is still in its nascent stages, despite promising applications in brain-computer interfaces.
Approach: They propose a novel EEG-text Masked Autoencoder that orchestrates compound self-supervised learning across and within EEG and text through a dedicated multi-stream encoder.
Outcome: The proposed model outperforms baseline framework in ROUGE-1 F1 and BLEU-4 scores and an LLM (specifically BART) to improve downstream tasks involving EEG and text.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations