Zilong Zheng

MMUIE: Massive Multi-Domain Universal Information Extraction for Long Documents EACL 2026 v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound ACL 2026 Look Both Ways and No Sink: Converting LLMs into Text Encoders without Training ACL 2025 ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection ACL 2025 Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective ACL 2025 In-Context Editing: Learning Knowledge from Self-Induced Distributions ICLR 2025 Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs EMNLP 2025 Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks EMNLP 2025 OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts CVPR 2025 DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints AAAI 2025 MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge ICLR 2025 Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs ICLR 2025 VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges ICCV 2025 Adaptive Preference Optimization with Uncertainty-aware Utility Anchor EMNLP 2025 MCU: An Evaluation Framework for Open-Ended Game Agents ICML 2025 How to Synthesize Text Data without Model Collapse? ICML 2025 TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation ICML 2025 Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge EMNLP 2024 Mars: Situated Inductive Reasoning in an Open-World Environment NIPS 2024 An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding NIPS 2024 Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels ACL 2024 LooGLE: Can Long-Context Language Models Understand Long Contexts? ACL 2024 MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark ACL 2024 Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling ACL 2024 LangSuit·E: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments ACL 2024 Towards More Realistic Chinese Spell Checking with New Benchmark and Specialized Expert Model COLING 2024 Varying Sentence Representations via Condition-Specified Routers EMNLP 2024 MindAgent: Emergent Gaming Interaction NAACL 2024 Rethinking Dictionaries and Glyphs for Chinese Language Pre-training ACL 2023 Diplomat: A Dialogue Dataset for Situated PragMATic Reasoning NIPS 2023 Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models EMNLP 2023 ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab NIPS 2023 VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions ACL 2023 SQA3D: Situated Question Answering in 3D Scenes ICLR 2023 Modeling Instance Interactions for Joint Information Extraction with Neural High-Order Conditional Random Field ACL 2023 Unsupervised Vision-Language Parsing: Seamlessly Bridging Visual Scene Graphs With Language Structures via Dependency Relationships CVPR 2022 Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling ICLR 2022 Energy-Based Generative Cooperative Saliency Prediction AAAI 2022 SHARP: Search-Based Adversarial Attack for Structured Prediction NAACL 2022 Patchwise Generative ConvNet: Training Energy-Based Models From a Single Natural Image for Internal Learning CVPR 2021 GRICE: A Grammar-based Dataset for Recovering Implicature and Conversational rEasoning ACL 2021 Learning Triadic Belief Dynamics in Nonverbal Communication From Videos CVPR 2021 Learning Energy-Based Model with Variational Auto-Encoder as Amortized Sampler AAAI 2021 Learning Cycle-Consistent Cooperative Networks via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation AAAI 2021 Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification CVPR 2021 GRICE: A Grammar-based Dataset for Recovering Implicature and Conversational rEasoning IJCNLP 2021 Motion-Based Generator Model: Unsupervised Disentanglement of Appearance, Trackable and Intrackable Motions in Dynamic Patterns AAAI 2020 Reasoning Visual Dialogs With Structural and Partial Observations CVPR 2019 Learning Dynamic Generator Model by Alternating Back-Propagation through Time AAAI 2019 Learning Descriptor Networks for 3D Shape Synthesis and Analysis CVPR 2018