Papers by Yunxin Li

14 papers
Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment (2024.acl-long)

Copied to clipboard

Challenge: Recent Large Multimodal Models (LMMs) focus on visual knowledge-dimension alignment, but ignore visual knowledge.
Approach: They propose a cognitive visual-language mapper that integrates visual-linguistic knowledge alignment with a fine-grained knowledge Adapter.
Outcome: The proposed model significantly improves LMMs on knowledge-based visual question answering (VQA) it also improves the performance of other models, including GPT-4V and Gemini-Pro.
Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs (2026.acl-long)

Copied to clipboard

Challenge: despite significant progress, full-duplex SLMs are constrained by severe modality interference, authors say . modality interferes with acoustic and semantic modeling, making them unintelligent and unnatural . authors propose a hierarchical parameter separation strategy that decouples conflicting modalities in deep layers .
Approach: They propose a hierarchical parameter separation strategy that decouples conflicting modalities in deep layers while preserving cross-modality coherence via a dedicated semantic alignment channel.
Outcome: The proposed method significantly advances the state of the art on full-duplex benchmarks . it decouples conflicting modalities in deep layers while preserving cross-modality coherence .
A Multimodal In-Context Tuning Approach for E-Commerce Product Description Generation (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for generating product descriptions from images are inaccurate and generic . e-commerce product descriptions are important for content marketing and increasing engagement .
Approach: They propose a new setting for generating product descriptions from images, augmented by marketing keywords.
Outcome: The proposed approach improves the accuracy and diversity of product descriptions by up to 3.3% on Rouge-L and 9.4% on D-5.
Benchmarking LLM’s Capability in Reasoning over Conflicting Web References (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) integrated with retrieval-augmented generation (RAG) are a dominant framework for building intelligent assistants.
Approach: They propose a benchmark to evaluate LLMs' reasoning capability over real-world conflicting documents retrieved from the web.
Outcome: The proposed benchmark evaluates LLMs' reasoning capability over real-world conflicting documents retrieved from the web.
U-CORE: A Unified Deep Cluster-wise Contrastive Framework for Open Relation Extraction (2023.tacl-1)

Copied to clipboard

Challenge: Existing methods for Relation Extraction (RE) are limited due to the overlap between predefined and undefined relations.
Approach: They propose a unified framework for both Zero-shot and Unsupervised Relation Extraction tasks by leveraging techniques from Contrastive Learning and Clustering.
Outcome: The proposed framework improves on three well-known datasets showing an average improvement of 7.35% ARI on Zero-shot ORE tasks and 15.24% ARI for Unsupervised ORE.
SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget (2024.acl-long)

Copied to clipboard

Challenge: Mixture of experts (MoE) is a popular technique to improve capacity of Large Language Models (LLMs) but memory-constrained devices are a major concern in edge AI training and serving.
Approach: They propose a framework for efficient serving of MoE-based large language models with tunable memory budgets.
Outcome: Experiments show that SwapMoE can reduce memory consumption while maintaining reasonable accuracy.
UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity Mixture-of-Experts (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation.
Approach: They propose a unified speech and music generation model built upon a novel framework . they propose specialized MoE architectures and curated training strategies to tackle data imbalances .
Outcome: The proposed model achieves state-of-the-art performance on major speech and music generation benchmarks.
WindowsWorld: A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application Environments (2026.findings-acl)

Copied to clipboard

Challenge: Existing GUI agents perform poorly on multi-application tasks, stalling at early sub-goals.
Approach: They propose to assess GUI Agents on complex multi-step tasks that mirror real-world professions.
Outcome: The proposed benchmark contains 181 tasks with an average of 5.0 sub-goals across 17 common desktop applications, of which 78% are inherently multi-application.
Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement (2025.acl-long)

Copied to clipboard

Challenge: Existing high-quality human-annotated SFT data is a bottleneck for Large Language Models (LLMs).
Approach: They propose a two-stage synthetic data generation framework that incorporates World Knowledge Trees and Self-Reflection Refinement to produce high-quality SFT data at scale.
Outcome: The proposed model fine-tuned on 20K condor-generated samples achieves superior performance compared to instruct model trained with RLHF.
A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for conditional inference on joint textual and visual clues lack multimodal context reasoning capability.
Approach: They propose a multi-modal context reasoning approach that embeds textual semantics and objective image information into the pretrained language model to perform context reasoning.
Outcome: The proposed approach improves on two data sets and shows 4.8% gain on the PMR.
An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are a powerful tool for test-time scaling, but they are often used under time constraints.
Approach: They propose to use LLMs to make models think before answering questions . they also use self-correction and best-of-N decoding to encourage deeper thinking .
Outcome: The proposed models are able to achieve higher inference accuracy with extra inference computation under time constraints.
VideoVista-CulturalLingo: 360° Horizons-Bridging Cultures, Languages, and Domains in Video Comprehension (2025.acl-long)

Copied to clipboard

Challenge: Existing video evaluation benchmarks focus on a single language, typically English, and feature videos rooted in Western cultural contexts.
Approach: They propose a video evaluation benchmark designed to bridge cultural, linguistic, and domain divide in video comprehension.
Outcome: The proposed video evaluation benchmark bridges cultural, linguistic, and domain divides . existing benchmarks only feature videos from YouTube, Shutterstock, or established video datasets based on cultural diversity .
A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex Text (2023.acl-long)

Copied to clipboard

Challenge: Pretrained Vision-Language Models (VLMs) have achieved remarkable performance in image retrieval from text, but their performance drops drastically when confronted with linguistically complex texts.
Approach: They propose an end-to-end Neural Divide-and-Conquer Reasoning framework for linguistically complex texts that they struggle to comprehend.
Outcome: The proposed framework significantly improves performance in complex image-text reasoning problem.
Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise Supervision (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for integrating textual graphs with LLMs are limited by symbolic inference and high annotation costs.
Approach: They propose a textual graph reasoning framework that integrates textual diagrams with large language models.
Outcome: The proposed approach achieves 15.6% accuracy and 17.2% in F1 score on three common datasets.

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