Hao Cheng

CollabLLM: From Passive Responders to Active Collaborators ICML 2025 Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts ACL 2025 ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning ICLR 2025 Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass ICLR 2025 Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities NAACL 2025 SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents ICLR 2025 DocLens: Multi-aspect Fine-grained Evaluation for Medical Text Generation ACL 2024 Fast-ELECTRA for Efficient Pre-training ICLR 2024 LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents ECCV 2024 Language Models as Inductive Reasoners EACL 2024 MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts ICLR 2024 OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Tracking NAACL 2024 ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks NAACL 2024 Augmenting Language Models with Long-Term Memory NeurIPS 2023 Chain-of-Skills: A Configurable Model for Open-Domain Question Answering ACL 2023 Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models NeurIPS 2023 Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning ICLR 2023 Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding EMNLP 2023 Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering ACL 2023 Understand and Modularize Generator Optimization in ELECTRA-style Pretraining ICML 2023 Visually-Augmented Language Modeling ICLR 2023 Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention IJCAI 2022 Knowledge-Rich Self-Supervision for Biomedical Entity Linking EMNLP 2022 Open Domain Question Answering with A Unified Knowledge Interface ACL 2022 Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge EMNLP 2022 Unsupervised Learning of Hierarchical Conversation Structure EMNLP 2022 Dialogue State Tracking with a Language Model using Schema-Driven Prompting EMNLP 2021 Posterior Differential Regularization with f-divergence for Improving Model Robustness NAACL 2021 Targeted Adversarial Training for Natural Language Understanding NAACL 2021 UnitedQA: A Hybrid Approach for Open Domain Question Answering ACL 2021 The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding ACL 2020 A Dynamic Speaker Model for Conversational Interactions NAACL 2019 Sounding Board: A User-Centric and Content-Driven Social Chatbot NAACL 2018 A Factored Neural Network Model for Characterizing Online Discussions in Vector Space EMNLP 2017 Bi-directional Attention with Agreement for Dependency Parsing EMNLP 2016 Scalable and Sound Low-Rank Tensor Learning AISTATS 2016 Language Models for Image Captioning: The Quirks and What Works ACL 2015 Open-Domain Name Error Detection using a Multi-Task RNN EMNLP 2015 Characterizing the Representer Theorem ICML 2013 Convex Two-Layer Modeling NeurIPS 2013