Papers by Tong Bao

7 papers
EIT: Enhanced Interactive Transformer (2024.acl-long)

Copied to clipboard

Challenge: Existing multi-view learning models prioritize complementarity while ignoring consensus . EMHA allows for efficient modeling of global dependencies among tokens in parallel .
Approach: They propose an enhanced multi-head self-attention (EMHA) that prioritizes complementarity while ignoring consensus.
Outcome: The proposed method favors consensus among heads by introducing two models . it is superior on a wide range of language tasks with a modest increase in model size .
SurveyGen: Quality-Aware Scientific Survey Generation with Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Automated survey generation is a key task in scientific document processing due to lack of standardized evaluation datasets.
Approach: They propose a survey-based framework that integrates quality indicators into literature retrieval to assess higher-quality sources.
Outcome: The proposed framework enhances the standard Retrieval-Augmented Generation pipeline and enables human-guided writing.
MedKInstruct: A Multimodal Knowledge Graph Based Framework for Multi-Hop and Hard-Negative Instruction Data Synthesis in MedVQA (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for medical visual question answering focus on image–caption pairs, limiting the model’s ability to learn relevant medical knowledge during training.
Approach: They propose to synthesize instruction data from image–caption pairs and incorporate a multimodal medical knowledge graph to assist LVLMs in synthesizing knowledge-intensive instruction data.
Outcome: The proposed model outperforms existing methods on the public datasets Slake and VQA-RAD by 4.16% and 4.50%.
Asymmetric Conflict and Synergy in Post-training for LLM-based Multilingual Machine Translation (2025.findings-acl)

Copied to clipboard

Challenge: Existing work in LLM-based MMT typically mitigates the Curse of Multilinguality . asymmetric phenomenon in linguistic conflicts and synergy varies in different translation directions .
Approach: They propose a direction-aware training approach to address asymmetry in linguistic conflicts and synergy . they propose X-ALMA-13B-Pretrain with multilingual pre-training to achieve comparable performance .
Outcome: The proposed method achieves comparable performance to X-ALMA-13B-Pretrain (only SFT) with fewer pretraining tokens and 17B parameters.
Non-Autoregressive Translation by Learning Target Categorical Codes (2021.naacl-main)

Copied to clipboard

Challenge: Existing non-autoregressive text generation models still fall behind in translation quality . authors propose a model that learns implicitly categorical codes as latent variables .
Approach: They propose a non-autoregressive Transformer model that implicitly categorizes latent variables into decoding . they find it improves translation quality by introducing more informative decoder inputs .
Outcome: The proposed model achieves comparable or better performance in machine translation tasks than strong baselines.
PartialFormer: Modeling Part Instead of Whole for Machine Translation (2024.findings-acl)

Copied to clipboard

Challenge: Existing feed-forward neural networks have significant computational and parametric overhead.
Approach: They propose a parameter-efficient Transformer architecture that utilizes multiple smaller FFNs to reduce parameters and computation while maintaining essential hidden dimensions.
Outcome: The proposed architecture reduces computational and parameter overhead while maintaining essential hidden dimensions.
MLLM-I2W: Harnessing Multimodal Large Language Model for Zero-Shot Composed Image Retrieval (2025.coling-main)

Copied to clipboard

Challenge: Existing methods for combining image retrieval are supervised and zero-shot . however, the challenge of mapping pseudo-words to images within the joint image-text embedding space is still a challenge.
Approach: They propose a novel image-text mapping network which converts description-related image information into pseudo-word markers for precise ZS-CIR.
Outcome: The proposed model improves on COCO, CIRR, and Fashion-IQ benchmarks.

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