Bang Liu

What to Ask Next? Probing the Imaginative Reasoning of LLMs with TurtleSoup Puzzles AAAI 2026 LLMs for Bayesian Optimization in Scientific Domains: Are We There Yet? EMNLP 2025 R3Mem: Bridging Memory Retention and Retrieval via Reversible Compression ACL 2025 Data Interpreter: An LLM Agent for Data Science ACL 2025 OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning ICLR 2025 FACT: Examining the Effectiveness of Iterative Context Rewriting for Multi-fact Retrieval NAACL 2025 Improving Context Fidelity via Native Retrieval-Augmented Reasoning EMNLP 2025 VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text ICLR 2025 Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection ICLR 2025 MatExpert: Decomposing Materials Discovery By Mimicking Human Experts ICLR 2025 INDOORWORLD : Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environment EMNLP 2025 AFlow: Automating Agentic Workflow Generation ICLR 2025 OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following ACL 2024 Talk Funny! A Large-Scale Humor Response Dataset with Chain-of-Humor Interpretation AAAI 2024 FAC2E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition EMNLP 2024 Enhancing Healthcare LLM Trust with Atypical Presentations Recalibration EMNLP 2024 HoneyComb: A Flexible LLM-Based Agent System for Materials Science EMNLP 2024 Enhancing Agent Learning through World Dynamics Modeling EMNLP 2024 CausalNET: Unveiling Causal Structures on Event Sequences by Topology-Informed Causal Attention IJCAI 2024 GOAt: Explaining Graph Neural Networks via Graph Output Attribution ICLR 2024 Resonance RoPE: Improving Context Length Generalization of Large Language Models ACL 2024 Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games ACL 2024 EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time ICML 2024 CadVLM: Bridging Language and Vision in the Generation of Parametric CAD Sketches ECCV 2024 MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization EMNLP 2023 Identify Event Causality with Knowledge and Analogy AAAI 2023 Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models ACL 2023 MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modeling ACL 2023 Search-Oriented Conversational Query Editing ACL 2023 SkillQG: Learning to Generate Question for Reading Comprehension Assessment ACL 2023 ICA-Proto: Iterative Cross Alignment Prototypical Network for Incremental Few-Shot Relation Classification EACL 2023 Efficient Classification of Long Documents via State-Space Models EMNLP 2023 HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science EMNLP 2023 DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization ICCV 2023 Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning EMNLP 2022 MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-Based Visual Question Answering CVPR 2022 Feeding What You Need by Understanding What You Learned ACL 2022 R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning ICLR 2022 QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance EMNLP 2022 Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting IJCNLP 2021 Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction IJCNLP 2021 Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog Management NAACL 2021 Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval ACL 2021 Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction ACL 2021 S$^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks NIPS 2021 Refining BERT Embeddings for Document Hashing via Mutual Information Maximization EMNLP 2021 Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting ACL 2021 Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval IJCNLP 2021 Matching Article Pairs with Graphical Decomposition and Convolutions ACL 2019