1. 3DCodeEdit: Benchmarking Instruction-Guided 3D Program Editing
In submission
All Research
Publications, submissions, and collaborations. Explore by research direction.
* Equal contribution.
In Submission
2. Planning while Listening and Speaking for Real-Time Competitive Debate
In submission
3. How Should Planning Agents ReSHAPE Their Search Space?
BiAlign@NeurIPS'26
4. Reading the Tea Leaves, Again: Can Large Language Models Predict Language Model Training Runs?
In submission
5. Knowing When to Stop: The Evidence–Action Gap in Coding Agents
In submission
6. Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation
In submission
7. Adaptive-GEPA: Make Your Harness Fit Heterogeneous Requests
In submission
8. Pivot-ICL: Adaptive Exemplar Selection for In-Context Learning
In submission
9. The Ramon Llull's Thinking Machine for Automated Ideation
LM4Sci@COLM'25
10. RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems
In submission
Peer-reviewed Publications
1. Improving Attributed Long-form Question Answering with Intent Awareness
ICLR'26
2. Revela: Dense Retriever Learning via Language Modeling
ICLR'26 · Oral; FrontierIR at AAAI'26 · Best Paper Award
3. Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters
ICLR'26
4. Improving Large Language Model Planning with Action Sequence Similarity
ICLR'25
5. MoR: Better Handling Diverse Queries with a Mixture of Sparse, Dense, and Human Retrievers
EMNLP'25 [Code]
6. cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree
Findings of EMNLP'25 [Code]
7. SPHERE: An Evaluation Card for Human-AI Systems
Findings of ACL'25 [Project]
8. Dense X Retrieval: What Retrieval Granularity Should We Use?
EMNLP'24
9. MixGR: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity
EMNLP'24
10. Beyond Relevance: Evaluate and Improve Retrievers on Perspective Awareness
COLM'24
11. "Merge Conflicts!" Exploring the Impacts of External Distractors to Parametric Knowledge Graphs
COLM'24
12. Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models
Findings of ACL'24
13. GeoHard: Towards Measuring Class-wise Hardness through Modelling Class Semantics
Findings of ACL'24
14. Thrust: Adaptively Propels Large Language Models with External Knowledge
NeurIPS'23
15. Video State-changing Object Segmentation
ICCV'23
16. Towards Reference-free Text Simplification Evaluation with a BERT Siamese Network Architecture
Findings of ACL'23
17. On Measuring the Intrinsic Few-Shot Hardness of Datasets
EMNLP'22
18. Weakly Supervised Text Classification using Supervision Signals from a Language Model
Findings of NAACL'22 [Details]
19. PCR4ALL: A Comprehensive Evaluation Benchmark for Pronoun Coreference Resolution
20. Leveraging Topic Relatedness for Argument Persuasion
Findings of ACL'21 [Details]
21. Probing Toxic Content in Large Pre-Trained Language Models
ACL'21 [Details]
22. The Effects of Fear of Missing Out on Social Media Posting Preferences
European Journal of Marketing, 2021
23. WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge
ACL'20 [PDF] [Code & data] [Details]
Workshop Papers
1. HiMemFormer: Hierarchical Memory-Aware Transformer for Multi-Agent Action Anticipation
VLM@NeurIPS'24
2. A Brief Survey and Comparative Study of Recent Development of Pronoun Coreference Resolution in English
CRAC@EMNLP'21 [PDF] [Code & data] [Details]
3. Learning Contextual Causality Between Daily Events from Time-consecutive Images
CIV@CVPR'21 [Details]
Large-scale Collaborations
1. DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
ICML'26 · Spotlight [OpenReview]
2. Efficient Test-Time Adaptation through Human-AI Interaction
TTCL@NeurIPS'26 [OpenReview]
3. Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (BIG-bench)
TMLR'23 [OpenReview]
Academic Events
- Winter, 2027 General chair, FrontierIR, the Second Workshop on New Frontiers in Information Retrieval at AAAI 2027.
- Fall, 2026 Invited panelist, Global Embodied Ecosystem Night at IROS 2026.
- Summer, 2026 Invited talk at Google DeepMind: Continual Learning for Coding Agents.
- Summer, 2025 Invited talk at UW H2 Group: Improving Large Language Model Planning with Action Sequence Similarity.
- Summer, 2024 Invited talk at Samaya AI: Towards Building Retrieval Systems in Complex Realistic Scenarios.
- Summer, 2022 Invited talk at the ICML Commonsense Tutorial: On Task Difficulty of Few-shot Learning.
- Spring, 2022 Invited talk at NUS, Department of Marketing: NLP as a Tool for Scientific Discovery.
Service
- General chair, FrontierIR, the Second Workshop on New Frontiers in Information Retrieval at AAAI 2027.
- Area chair for ACL and EMNLP (2024–present), and NAACL (2025–present).
- Reviewer for NeurIPS (2024–present), ICLR (2025–present), ICML (2025–present), and COLM (2024–present); previously for ACL, EMNLP, NAACL, EACL, AACL, AAAI, and ECCV.