Kaixin Ma
30 papers · 2017–2026 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
π Academic Marathon (8) π Conference Polyglot (9) π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (10)
πΊοΈ
Taxonomy Completionist
(46)
π
Conference Polyglot
(9)
π
Academic Marathon
(8)
π
Keyword Trendsetter Combo
(3)
π€
Dynamic Duo
(12)
π§¬
Topic Evolution
β
The Questioner
(3)
π
Century Club
(29)
ποΈ
Keyword Collector
(135)
β‘
Prolific Year
(6)
π₯
Unstoppable
(5)
Conferences
EMNLP (11)
ACL (6)
NAACL (4)
AAAI (2)
ICLR (2)
COLING (1)
EACL (1)
IJCNLP (1)
NIPS (1)
SEMEVAL (1)
Top co-authors
Keywords
question answering
(6)
language model
(4)
lateral thinking
(4)
commonsense reasoning
(4)
knowledge graph
(4)
web agent
(3)
attention mechanism
(3)
open-domain question answering
(3)
retrieval-augmented generation
(3)
zero-shot learning
(3)
knowledge identification
(2)
commonsense question answering
(2)
document grounding
(2)
large language model
(2)
goal-oriented dialogue
(2)
response generation
(2)
visual reasoning
(2)
vision language model
(2)
dialogue system
(2)
visual question answering
(1)
Papers
WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms
EACL 2026
WebEvolver: Enhancing Web Agent Self-Improvement with Co-evolving World Model
EMNLP 2025
COLUMBUS: Evaluating COgnitive Lateral Understanding Through Multiple-Choice reBUSes
AAAI 2025
DocBench: A Benchmark for Evaluating LLM-based Document Reading Systems
NAACL 2025
Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots
NAACL 2025
DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?
ICLR 2025
RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph
ICLR 2025
OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization
ACL 2025
Understanding and Enhancing Mamba-Transformer Hybrids for Memory Recall and Language Modeling
EMNLP 2025
Retrieval-augmented GUI Agents with Generative Guidelines
EMNLP 2025
DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes
EMNLP 2025
Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models
EMNLP 2024
WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
ACL 2024
MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning
NIPS 2024
Dense X Retrieval: What Retrieval Granularity Should We Use?
EMNLP 2024
SemEval-2024 Task 9: BRAINTEASER: A Novel Task Defying Common Sense
NAACL 2024
SemEval-2024 Task 9: BRAINTEASER: A Novel Task Defying Common Sense
SEMEVAL 2024
BRAINTEASER: Lateral Thinking Puzzles for Large Language Models
EMNLP 2023
Chain-of-Skills: A Configurable Model for Open-Domain Question Answering
ACL 2023
Open Domain Question Answering with A Unified Knowledge Interface
ACL 2022
Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge
EMNLP 2022
Coalescing Global and Local Information for Procedural Text Understanding
COLING 2022
Exploring Strategies for Generalizable Commonsense Reasoning with Pre-trained Models
EMNLP 2021
Building Goal-oriented Document-grounded Dialogue Systems
IJCNLP 2021
Knowledge-driven Data Construction for Zero-shot Evaluation in Commonsense Question Answering
AAAI 2021
Building Goal-oriented Document-grounded Dialogue Systems
ACL 2021
Bend but Donβt Break? Multi-Challenge Stress Test for QA Models
EMNLP 2019
Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering
EMNLP 2019
Challenging Reading Comprehension on Daily Conversation: Passage Completion on Multiparty Dialog
NAACL 2018
Text-based Speaker Identification on Multiparty Dialogues Using Multi-document Convolutional Neural Networks
ACL 2017