Papers by Weiming Li

20 papers
MIBench: Evaluating Multimodal Large Language Models over Multiple Images (2024.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks and MLLMs focus on single-image input scenarios, leaving performance of ML models when handling multiple images underexplored.
Approach: They propose a benchmark to evaluate fine-grained abilities of multimodal large language models in multi-image scenarios.
Outcome: The proposed benchmark categorizes the multi-image abilities into three scenarios: MII, MKS and MIC.
NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging (2025.emnlp-main)

Copied to clipboard

Challenge: Early debugging efforts focused on code-level analysis, which often fails when addressing complex programming errors.
Approach: They propose a framework that employs natural language as an intermediate representation to improve code debugging by debuggating at a natural language level.
Outcome: The proposed framework outperforms traditional debugging methods and enables a broader modification space through direct refinement guided by execution feedback.
HiSA: Hierarchical State Abstraction for Scalable GUI Agents (2026.findings-acl)

Copied to clipboard

Challenge: Recent multimodal large language models (MLLMs) exploit insufficient state abstraction to automate workflows.
Approach: They propose a hierarchical state abstraction approach that actively restructures knowledge rather than passively retaining historical information.
Outcome: The proposed approach achieves a 40.58% success rate while reducing token consumption by 69.85% and monetary costs by 55.10% compared to the best-performing baseline.
ToM-Synth: Scaling Robust Theory of Mind in LLMs via 6,912 Structured Social Units (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods endowing LLMs with Theory of Mind fail to internalize the augmented ToM into the LLM.
Approach: They propose a factorial combinatorial synthesis framework that enables systematic synthesis of ToM data and uses it for RL fine-tuning.
Outcome: The proposed framework yields a training dataset of 27,648 instances.
Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are designed as specific task solvers with sophisticated prompt engineering, but are inherently incapacitating to address complex dynamic scenarios.
Approach: They propose an LLM-based agent with policy-level reflection and optimization that can learn from interactive experiences and progressively elevate its behavioral policy.
Outcome: The proposed agent outperforms vanilla LLM and specialized models in blackjack and Texas hold’em.
CompileAgent: Automated Real-World Repo-Level Compilation with Tool-Integrated LLM-based Agent System (2025.acl-long)

Copied to clipboard

Challenge: CompileAgent is the first LLM-based agent framework dedicated to repo-level compilation.
Approach: They propose a LLM-based agent framework dedicated to repo-level compilation.
Outcome: The proposed method significantly improves compilation success rate, ranging from 10% to 71%.
Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for video-text retrieval capture fine-grained semantic concepts . however, they lack the ability to capture finer-grain concepts such as objects and actions.
Approach: They propose a dual-encoder architecture for fast video-text retrieval that learns lexicon representations to capture fine-grained semantics.
Outcome: The proposed framework outperforms existing methods with 4.8% and 8.2% improvement on MSR-VTT and DiDeMo respectively.
Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for hallucination mitigation are based on external dependency and require external annotations or auxiliary models for preference data collection.
Approach: a new method is proposed to help model-generated hallucinations without external dependencies.
Outcome: a new method that self-injects hallucinations into a generated response improves halluuutations mitigation.
Unleashing the Power of LLMs in Court View Generation by Stimulating Internal Knowledge and Incorporating External Knowledge (2024.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have made remarkable strides in language generation, but they encounter difficulties in the knowledge-intensive legal domain.
Approach: They propose to decompose court views into different parts, stimulate internal knowledge, and incorporate external information to unleash the power of LLMs in the task.
Outcome: The proposed method generates more accurate and reliable court views on two real-world datasets LAIC2021 and CJO2022.
Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts (2026.acl-long)

Copied to clipboard

Challenge: Existing multimodal Mixture-of-Experts models accurately perceive image content yet fail in subsequent reasoning . Seeing but not thinking phenomenon is a puzzling phenomenon .
Approach: They propose a routing-guided intervention method that enhances domain expert activation.
Outcome: The proposed method achieves consistent improvements on visual reasoning tasks.
Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for vision-language pre-training lack high-level semantics and text is not sufficiently involved in masked modeling.
Approach: They propose a semantics-enhanced cross-modal MIM framework for vision-language representation learning that harvests high-level semantics from global image features via self-supervised agreement learning and transfers them to local patch encodings by sharing the encode space.
Outcome: The proposed model achieves state-of-the-art or competitive performance on multiple vision-language tasks.
Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation (2026.findings-acl)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) are increasingly being deployed as content moderators . however, they exploit the Human-AI capability gap and create adversarial environments . smuggling attacks exploit the human-AI gap and exploit the vulnerability .
Approach: They construct a benchmark to evaluate the vulnerability of MLLMs as content moderators . they identify three root causes: limited capabilities of vision encoders, robustness gap in OCR .
Outcome: The proposed model exploits the Human-AI capability gap and is vulnerable to smuggling attacks.
D-RAG: Differentiable Retrieval-Augmented Generation for Knowledge Graph Question Answering (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to Knowledge Graph Question Answering (KGQA) use Retrieval-Augmented Generation (RAG) but subgraph selection process is non-differentiable, preventing end-to-end training of the retriever and the generator.
Approach: They propose a Differentiable RAG approach that optimizes the retriever and the generator for KGQA.
Outcome: The proposed approach outperforms state-of-the-art approaches on WebQSP and CWQ.
LaMPE: Length-aware Multi-grained Positional Encoding for Adaptive Long-context Scaling Without Training (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) experience significant performance degradation when the input exceeds the pretraining context window due to the out-of-distribution (OOD) behavior of Rotary Position Embedding (RoPE).
Approach: They propose a training-free method that remaps out-of-distribution (OOD) positions into the in-distance range with fixed mapping strategies, ignoring the dynamic relationship between input length and effective context window.
Outcome: Experiments on three representative LLMs across five mainstream long-context benchmarks show that the proposed method achieves significant performance improvements compared to existing methods.
DiffusionNER: Boundary Diffusion for Named Entity Recognition (2023.acl-long)

Copied to clipboard

Challenge: Named Entity Recognition (NER) tasks are fundamental to many structured information extraction tasks.
Approach: They propose a named entity recognition task that uses a boundary-denoising diffusion process to denoise noisy spans.
Outcome: The proposed method achieves comparable or even better performance than previous state-of-the-art models on flat and nested datasets.
Enhancing LLM Language Adaption through Cross-lingual In-Context Pre-training (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for enhancing cross-lingual transfer are limited by parallel resources and lack linguistic and domain coverage.
Approach: They propose a cross-lingual in-context pre-training approach that leverages semantically related bilingual Wikipedia documents to enhance cross-linguistic transfer.
Outcome: The proposed approach improves multilingual performance on three models across six target languages.
Legal Judgment Prediction based on Knowledge-enhanced Multi-Task and Multi-Label Text Classification (2025.naacl-long)

Copied to clipboard

Challenge: Legal judgment prediction (LJP) is an essential task for legal AI, aiming at predicting judgments based on the facts of a case.
Approach: They propose a knowledge-enhanced approach that incorporates 'label-level knowledge' to enhance the representation of case facts for each task and 'task-level' knowledge to improve synergy.
Outcome: The proposed method is effective in comparison to state-of-the-art (SOTA) baselines.
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in reasoning models have demonstrated remarkable capabilities on mathematical and coding tasks, but their effectiveness in embodied domains remains largely unexplored.
Approach: They propose a reasoning model for interactive embodied tasks that synthesizes 9.3k coherent Observation-Thought-Action trajectories containing 64k ego-centric images and 90k diverse reasoning processes.
Outcome: The proposed model outperforms existing visual reasoning models by +9%, 24%, and +13% on long-horizon tasks.
Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries (2026.acl-long)

Copied to clipboard

Challenge: a goal of LLM alignment is to balance usefulness with harmlessness, but this conflictes when knowledge serves both legitimate and malicious purposes.
Approach: They propose a framework that combines safety-research contexts with adversarial interactions to exploit a vulnerability in Jargon queries.
Outcome: a framework outperforms existing methods in analyzing Jargon queries, a study shows . it achieves 93% of attacks across seven models, while remaining useful, the authors say .
AutoTaskEval: Towards Domain-Specific and Fine-Grained Evaluation for LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing automated approaches operate within fixed task schemas and often fail to autonomously discover new evaluation dimensions.
Approach: They propose an automated framework that constructs domain-specific benchmarks directly from unstructured corpora using Bloom’s Taxonomy.
Outcome: The proposed framework uncovers a broader and more fine-grained task space than expert-curated benchmarks while producing high-quality instances that preserve established model-level evaluation trends.

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