Papers by Siwei Wu

10 papers
LoopCoder: Scaling Code Intelligence via Looped Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large language models have mastered syntax-level code generation, but complex algorithmic reasoning remains a challenge.
Approach: They propose a recurrent inductive bias that aligns with the recursive nature of programming logic.
Outcome: The proposed model achieves comparable performance to standard dense models with more parameters.
DocMMIR: A Framework for Document Multi-modal Information Retrieval (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing multi-modal information retrieval models lack a comprehensive exploration of document-level retrieval . existing models suffer from the absence of cross-domain datasets at this granularity.
Approach: They propose a multi-modal document retrieval framework to unify diverse document formats and domains with a comprehensive retrieval scenario.
Outcome: The proposed framework improves document retrieval performance on a large multimodal dataset.
Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop Paths (2023.acl-long)

Copied to clipboard

Challenge: ATOMIC is a large-scale commonsense knowledge graph (CSKG) containing everyday if-then knowledge triplets, i.e., head event, relation, tail event.
Approach: They propose a CSKG completion method called Rel-CSKGC to predict the relation given the head event and tail event of a triplet and train a model based on existing triplets.
Outcome: The proposed method is based on existing triplets and can be used to complete the missing links in ATOMIC.
VCD: A Dataset for Visual Commonsense Discovery in Images (2025.findings-acl)

Copied to clipboard

Challenge: Visual commonsense data sets lack visual grounded representations of commonsensense . existing knowledge bases lack visual-based knowledge tied to actual visual scenes .
Approach: They present a large-scale visual commonsense dataset with over 100,000 images and 14 million object-commonsense pairs that integrates both Seen (directly observable) and Unseen (inferrable) commonsens.
Outcome: The proposed model integrates Seen (directly observable) and Unseen (inferrable) commonsense across Property, Action, and Space aspects.
Commonsense Knowledge Graph Completion Via Contrastive Pretraining and Node Clustering (2023.findings-acl)

Copied to clipboard

Challenge: Commonsense knowledge graphs are typically represented by short text, resulting in many different nodes representing the same concept.
Approach: They propose a framework based on Contrastive Pretraining and Node Clustering to solve these problems.
Outcome: The proposed framework outperforms state-of-the-art methods on two CSKG completion benchmarks.
COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)

Copied to clipboard

Challenge: Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation.
Approach: They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets.
Outcome: The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark.
SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval (2024.findings-acl)

Copied to clipboard

Challenge: Multi-modal information retrieval (MMIR) is a rapidly evolving field . current benchmarks for image-text pairings overlook the scientific domain .
Approach: They develop a scientific domain-specific MMIR benchmark to evaluate image-text pairings using open-access research paper corpora.
Outcome: The proposed benchmarks are based on 530K image-text pairs extracted from scientific documents with detailed captions.
SynthAgent: Adapting Web Agents with Synthetic Supervision (2026.acl-long)

Copied to clipboard

Challenge: Existing studies have focused on synthetic supervision but have encountered data quality issues.
Approach: They propose a fully synthetic supervision framework that aims at improving data quality via dual refinement of both tasks and trajectories.
Outcome: The proposed framework outperforms existing methods on standardized benchmarks and shows promising results on a standardized test.
MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models (2026.findings-eacl)

Copied to clipboard

Challenge: Current multimodal benchmarks focus on facts within individual images, but neglect associative relations among multiple images.
Approach: They propose a multi-image relational association task and a MMRA benchmark to evaluate LVLMs.
Outcome: The proposed benchmarks show that entity-level multi-image perception tasks pose greater challenges than image-level tasks.
LIME: Less Is More for MLLM Evaluation (2025.findings-acl)

Copied to clipboard

Challenge: Existing MLLM benchmarks and unified evaluation frameworks cannot accurately and efficiently reflect the ability of MLMLs.
Approach: They propose a semi-automated benchmark curated using a pipeline that filters out uninformative samples and eliminates answer leakage by focusing on tasks that require image-based understanding.
Outcome: The proposed benchmark reduces the number of samples by 76% and evaluation time by 77% while it can more effectively distinguish different models’ abilities.

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