Papers by Xintong Wang

20 papers
Language over Labels: Contrastive Language Supervision Exceeds Purely Label-Supervised Classification Performance on Chest X-Rays (2022.aacl-srw)

Copied to clipboard

Challenge: Pretrained CLIP models lack domain-specific knowledge of text and images.
Approach: They adapt CLIP-based models to the chest radiography domain using contrastive language supervision and a detailed ablation study of the batch and dataset size.
Outcome: The proposed model outperforms supervised learning on labels on the MIMIC-CXR dataset while generalizing to the CheXpert and RSNA Pneumonia datasets.
POLAR: A Benchmark for Multilingual, Multicultural, and Multi-Event Online Polarization (2026.findings-acl)

Copied to clipboard

Challenge: polarization is a pervasive threat to democratic institutions, civil discourse, and social cohesion worldwide . most existing datasets focus on English or high-resource languages, reflecting a widespread trend across NLP tasks .
Approach: They propose a multilingual, multicultural, and multi-event dataset with over 110K instances in 22 languages drawn from diverse online platforms and real-world events.
Outcome: The proposed dataset analyzes polarization detection, type, and manifestation using a variety of annotation platforms adapted to each cultural context.
Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing fine-tuning and continual learning methods compress visual representations and emphasize task alignment over visual retention.
Approach: They propose a modality-decoupled gradient descent (MDGD) that regulates gradient updates to preserve effective rank of visual features and explicitly disentangles visual learning from task-specific alignment.
Outcome: The proposed model reduces visual forgetting and improves visual retention . it disentangles visual learning from task-specific alignment and preserves effective rank .
M2PA: A Multi-Memory Planning Agent for Open Worlds Inspired by Cognitive Theory (2025.findings-acl)

Copied to clipboard

Challenge: Open-world planning poses a challenge due to complex environments and task diversity . recent work shows that large language models (LLMs) lack the ability to connect to agents' experiences .
Approach: They propose an open-world multi-memory planning agent that combines large language models with human-like multi-mesh systems to leverage their strengths.
Outcome: The proposed agent outperforms state-of-the-art agents on 50 Minecraft tasks in zero-shot learning.
Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding (2024.findings-acl)

Copied to clipboard

Challenge: Recent research in large vision-language models has shown promising results, but the issue of hallucination remains.
Approach: They propose an instruction-based method to reduce hallucinations in large vision-language models . they use disturbance instructions to exacerbate hallucinosity in multimodal fusion modules .
Outcome: The proposed method reduces hallucinations in multimodal fusion modules by reducing alignment uncertainty and subtracting hallucines from the original distribution.
From Selection to Generation: A Survey of LLM-based Active Learning (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been used for selection and training of data for active learning.
Approach: They propose an intuitive taxonomy that categorizes LLM-based active learning techniques and discuss the transformative roles they can play in the active learning loop.
Outcome: The proposed model can generate entirely new data instances and provide more cost-effective annotations with fewer labeled data instances.
Towards Multi-Modal Text-Image Retrieval to improve Human Reading (2021.naacl-srw)

Copied to clipboard

Challenge: In primary school, children's books, as well as in modern language learning apps, multi-modal learning strategies like illustrations of terms and phrases are used to support reading comprehension.
Approach: They propose to use multi-modal transformers to train multi-dimensional models on text-image retrieval to support a user's reading comprehension of arbitrary text.
Outcome: The proposed model performs poorly because of the short and relatively simple textual data that the current models are trained with.
Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to training LLMs at ultra-low precisions suffer from convergence instability and substantial training costs.
Approach: They propose a progressive QAT framework with outlier channel splitting to address these issues . they use nested structure of integer quantization grids to enable a "train once, deploy any precision" paradigm .
Outcome: The proposed framework outperforms baselines on both Llama2/3 and W2A16, with an 11 speedup over BF16.
PiKGL: Leveraging Pruned Knowledge Graphs for Explainable Stance Detection (2026.tacl-1)

Copied to clipboard

Challenge: Experimental results demonstrate that a Pruned interpretable knowledge Graph Learning framework for explainable stance detection is state-of-the-art for social media stance prediction.
Approach: They propose a Pruned interpretable knowledge Graph Learning framework for explainable stance detection that incorporates commonsense knowledge and prunes redundant information to ensure precision and minimize noise.
Outcome: The proposed framework achieves state-of-the-art on three public datasets.
Chinese Toxic Language Mitigation via Sentiment Polarity Consistent Rewrites (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) can be effective at rewriting toxic content, but they often default to overly polite rewrites, distorting the emotional tone and communicative intent.
Approach: They evaluate 17 large language models with variant architectures to evaluate their ability to rewrite toxic content while preserving the speaker's original intent.
Outcome: The first Chinese detoxification dataset explicitly designed to preserve sentiment polarity is evaluated across five real-world scenarios.
Regularized Context Gates on Transformer for Machine Translation (2020.acl-main)

Copied to clipboard

Challenge: Context gates are effective to control the contributions from the source and target contexts in the recurrent neural network (RNN) based neural machine translation.
Approach: They propose a method to identify source and target contexts and introduce a gate mechanism to control the contributions from source and targets in the advanced Transformer architecture.
Outcome: The proposed model achieves an averaged gain of 1.0 BLEU score over a strong transformer baseline.
QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training–Inference Mismatch (2026.findings-acl)

Copied to clipboard

Challenge: Recent work has shown that reinforcement learning with simple rule-based reward functions (RLVR) can induce emergent reasoning behaviors and yield gains in challenging domains such as math problem solving.
Approach: They propose a rollout-alignment-quantization-aware RL which aligns training-side forward with the quantized rollout to minimize mismatch.
Outcome: The proposed approach outperforms quantized-rollout training by +5.5 on Qwen3-30B-A3B MoE for math problems while maintaining low-bit throughput.
Multilingual and Explainable Text Detoxification with Parallel Corpora (2025.coling-main)

Copied to clipboard

Challenge: Existing approaches to manage toxic speech on social platforms are limited . however, there is a need for more proactive moderation of abusive speech.
Approach: They extend parallel text detoxification corpus to new languages to test the approach . they propose a method that combines toxic and non-toxic sentences into a more neutral form .
Outcome: The proposed method integrates the descriptive features of toxic and non-toxic sentences into a more neutral or non- toxic form.
CoMMIT: Coordinated Multimodal Instruction Tuning (2025.emnlp-main)

Copied to clipboard

Challenge: et al., 2024) show that multimodal instruction tuning is more effective than baselines.
Approach: They propose a multimodal balance coefficient that enables quantitative measurement of the balance of learning . they propose auxiliary regularization on the gradient to promote updating with larger step sizes .
Outcome: The proposed method is more effective than baselines in MLLM instruction tuning.
MelTrim: Coarse-to-Fine Data Pruning for Speech Classification (2026.findings-acl)

Copied to clipboard

Challenge: Unlike image or text classification, speech classification tasks are particularly challenging due to the difficulty in capturing the acoustic, semantic, and contextual representations.
Approach: They propose a dataset pruning method that coarsely filters redundant samples using DBSCAN clustering on Mel-Frequency Cepstral Coefficients (MFCC) features.
Outcome: The proposed method achieves 49.5% improvement in WA on the MEAD dataset and 41.9% reduction in EER on speaker identification tasks.
GUI Agents: A Survey (2025.findings-acl)

Copied to clipboard

Challenge: Large Foundation Models (LFMs) have transformed the landscape of AI research and day-to-day life.
Approach: They propose a framework that delineates GUI agents' perception, reasoning, planning, and acting capabilities.
Outcome: The proposed framework delineates their perception, reasoning, planning, and acting capabilities.
Metagent-P: A Neuro-Symbolic Planning Agent with Metacognition for Open Worlds (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) show promising potential through their world knowledge and language processing capabilities in open-world planning.
Approach: They propose a framework that integrates the world knowledge of large language models, symbolic reasoning capabilities of cognitive architectures, and metacognition to improve experience utilization.
Outcome: The proposed framework outperforms current state-of-the-art methods in Minecraft and reduces the average replanning counts by 34% and exceeds the human success rate by 18.96%.
SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes (2026.acl-long)

Copied to clipboard

Challenge: Existing preference-based approaches fail to address this challenge by exploiting language priors to bypass visual grounding.
Approach: They propose a framework that leverages scene graphs as structured visual information to perform controllable structural interventions.
Outcome: The proposed framework improves answer accuracy and reasoning faithfulness across seven visual reasoning benchmarks.
CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) achieve excellent performance through pretraining on extensive data.
Approach: They propose an efficient selective layer intervention based on parameter-efficient fine-tuning methods to select the optimal steering layer to modulate LLM semantics.
Outcome: The proposed approach is based on a model-agnostic framework and is safe to deploy.
MOTIF: Contextualized Images for Complex Words to Improve Human Reading (2022.lrec-1)

Copied to clipboard

Challenge: Existing studies have shown that multimodal information is crucial for concept formation, accordingly for language acquisition.
Approach: They collect a multimodal dataset enriched with complex word annotations and validated image match.
Outcome: The proposed dataset contains 1125 comprehension texts retrieved from Wikipedia Simple Corpus .

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