Papers by Liqiang Niu
REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-training (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models have achieved great success on Machine Reading Comprehension (MRC) however, the poor support in evidence extraction hinders them from further advancing MRC. |
| Approach: | They propose a REtrieval-based pre-training approach that strengthens evidence extraction during pre-training by inherited downstream MRC tasks. |
| Outcome: | The proposed approach strengthens evidence extraction during pre-training, which is further inherited by downstream tasks. |
LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing LMM-based embedding models exhibit a high degree of overlap in similarity distribution between positive and negative pairs, making it challenging to distinguish hard negative pairs effectively. |
| Approach: | They propose a framework that improves the embedding model's representation learning for negative pairs based on their discriminative difficulty. |
| Outcome: | The proposed framework improves the embedding model's representation learning for negative pairs based on their discriminative difficulty. |
AVG-LLaVA: An Efficient Large Multimodal Model with Adaptive Visual Granularity (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing large multimodal models typically divide high-resolution images into multiple local images and a global image, leading to a large number of visual tokens. |
| Approach: | They propose an LMM that can adaptively select the appropriate visual granularity based on the input image and instruction. |
| Outcome: | The proposed model significantly reduces visual tokens and speeds up inference on 11 benchmarks. |
TIU-Bench: A Benchmark for Evaluating Large Multimodal Models on Text-rich Image Understanding (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing text-rich image understanding benchmarks lack scale and fragmented scenarios . a new full-image structured output format is proposed to enable fine-grained evaluation of perception and reasoning capabilities. |
| Approach: | They propose a large-scale, multilingual benchmark that includes over 100,000 annotations and 22,000 question-answer pairs. |
| Outcome: | The proposed framework provides a comprehensive platform for developing and evaluating next-generation multimodal AI systems. |
UMTIT: Unifying Recognition, Translation, and Generation for Multimodal Text Image Translation (2024.lrec-main)
Copied to clipboard
| Challenge: | Current Image machine translation (IMT) relies on a cascaded system that combines Optical Character Recognition (OCR) and a complex process of rendering the translated text back onto the source image. |
| Approach: | They propose a multimodal image-text translation model that generates consistent target images . they use two image-to-text conversion steps to convert images to text to recognize source text . |
| Outcome: | The proposed model outperforms existing methods and surpasses state-of-the-art methods in text recognition tasks. |
ArrowGEV: Grounding Events in Video via Learning the Arrow of Time (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches for grounding events in videos are limited by their time-sensitive nature . arrow of time in physics characterizes intrinsic directionality of temporal processes . |
| Approach: | They propose a framework that explicitly models temporal directionality in events to improve event grounding and temporal understanding in VLMs. |
| Outcome: | The proposed framework improves event grounding and directionality understanding in VLMs. |
Translatotron-V(ison): An End-to-End Model for In-Image Machine Translation (2024.findings-acl)
Copied to clipboard
| Challenge: | In-image machine translation (IIMT) aims to translate an image containing texts in source language into an image with translations in target language. |
| Approach: | They propose an end-to-end IIMT model with four modules that translate images . they propose a two-stage training framework to assist the model in learning alignment across languages . |
| Outcome: | The proposed model outperforms cascaded models with only 70.9% of parameters and is highly accurate. |