2025
AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence.
CoRR, February, 2025

HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading.
CoRR, February, 2025

No Preference Left Behind: Group Distributional Preference Optimization.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey.
CoRR, 2024

COMMA: A Communicative Multimodal Multi-Agent Benchmark.
CoRR, 2024

Towards a Unified View of Preference Learning for Large Language Models: A Survey.
CoRR, 2024

LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback.
CoRR, 2024

PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling.
CoRR, 2024

VeCAF: VLM-empowered Collaborative Active Finetuning with Training Objective Awareness.
CoRR, 2024

Mitigating Language-Level Performance Disparity in mPLMs via Teacher Language Selection and Cross-lingual Self-Distillation.
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade.
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness.
Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024

MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Large Language Models are not Fair Evaluators.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

Improving the Robustness of Distantly-Supervised Named Entity Recognition via Uncertainty-Aware Teacher Learning and Student-Student Collaborative Learning.
Proceedings of the Findings of the Association for Computational Linguistics, 2024

PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain.
Proceedings of the Findings of the Association for Computational Linguistics, 2024

Improving Event Definition Following For Zero-Shot Event Detection.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

2023
ML-Bench: Large Language Models Leverage Open-source Libraries for Machine Learning Tasks.
CoRR, 2023

Distantly-Supervised Named Entity Recognition with Uncertainty-aware Teacher Learning and Student-student Collaborative Learning.
CoRR, 2023

Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond.
CoRR, 2023

Human-in-the-Loop through Chain-of-Thought.
CoRR, 2023

DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade.
CoRR, 2023

DiffCap: Exploring Continuous Diffusion on Image Captioning.
CoRR, 2023

Compositional Task Representations for Large Language Models.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Empowering MultiModal Models' In-Context Learning Ability through Large Language Models.
Proceedings of the ACM Turing Award Celebration Conference - China 2023, 2023

SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recognition.
Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, 2023

2019
Using Feature Tree Model to Track High Speed Flying Soccer in Complicated Background.
Proceedings of the 14th IEEE International Conference on Intelligent Systems and Knowledge Engineering, 2019