Ke Wang

Activations as Features: Probing LLMs for Generalizable Essay Scoring Representations AAAI 2026 From Solver to Tutor: Evaluating the Pedagogical Intelligence of LLMs with KMP-Bench AAAI 2026 Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format Reasoning ACL 2026 GUI0: Self-Evolving Foundational GUI Agents in Super App Ecosystems ACL 2026 MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning ACL 2026 HDGS: Hierarchical Dynamic Gaussian Splatting for Urban Driving Scenes AAAI 2026 MOA: Multi-Objective Alignment for Role-Playing Agents ACL 2026 Semantic Document Derendering: SVG Reconstruction via Vision-Language Modeling AAAI 2026 Negative Entity Suppression for Zero-Shot Captioning with Synthetic Images AAAI 2026 EVM-QuestBench: An Execution-Grounded Benchmark for Natural-Language Transaction Code Generation ACL 2026 TabEmb: Joint Semantic-Structure Embedding for Table Annotation ACL 2026 Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts ACL 2026 Accelerating Adversarial Training on Under-Utilized GPU IJCAI 2025 Vision Transformers Beat WideResNets on Small Scale Datasets Adversarial Robustness AAAI 2025 Beyond Spatial Domain: Cross-domain Promoted Fourier Convolution Helps Single Image Dehazing AAAI 2025 Scaling and Taming Adversarial Training with Synthetic Data ICCV 2025 Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces ICML 2025 MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code ICLR 2025 DEPfold: RNA Secondary Structure Prediction as Dependency Parsing. ICLR 2025 NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection ICCV 2025 SAM Decoding: Speculative Decoding via Suffix Automaton ACL 2025 SDPO: Segment-Level Direct Preference Optimization for Social Agents ACL 2025 Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding CVPR 2025 EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning ACL 2025 MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning ACL 2025 Probability-Consistent Preference Optimization for Enhanced LLM Reasoning ACL 2025 RACQC: Advanced Retrieval-Augmented Generation for Chinese Query Correction EMNLP 2025 EquiBench: Benchmarking Large Language Models’ Reasoning about Program Semantics via Equivalence Checking EMNLP 2025 SATBench: Benchmarking LLMs’ Logical Reasoning via Automated Puzzle Generation from SAT Formulas EMNLP 2025 LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding EMNLP 2025 Alignment with Fill-In-the-Middle for Enhancing Code Generation EMNLP 2025 LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging ICLR 2025 MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs ACL 2024 OPUS: Occupancy Prediction Using a Sparse Set NIPS 2024 Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning NAACL 2024 Skin Malignancy Classification Using Patients’ Skin Images and Meta-data: Multimodal Fusion for Improving Fairness MIDL 2024 Review-Enhanced Hierarchical Contrastive Learning for Recommendation AAAI 2024 Learning from Failure: Improving Meeting Summarization without Good Samples AAAI 2024 Measuring the Inconsistency of Large Language Models in Preferential Ranking ACL 2024 Aligning Logits Generatively for Principled Black-Box Knowledge Distillation CVPR 2024 Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer CVPR 2024 StreamingFlow: Streaming Occupancy Forecasting with Asynchronous Multi-modal Data Streams via Neural Ordinary Differential Equation CVPR 2024 Towards Stable 3D Object Detection ECCV 2024 Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement EMNLP 2024 An Electoral Approach to Diversify LLM-based Multi-Agent Collective Decision-Making EMNLP 2024 AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories EMNLP 2024 FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents EMNLP 2024 Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset NIPS 2024 MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning ICLR 2024 Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification ICLR 2024 Localizing Task Information for Improved Model Merging and Compression ICML 2024 Pi-DUAL: Using privileged information to distinguish clean from noisy labels ICML 2024 Disambiguated Lexically Constrained Neural Machine Translation ACL 2023 Easy Guided Decoding in Providing Suggestions for Interactive Machine Translation ACL 2023 Improving Neural Machine Translation by Multi-Knowledge Integration with Prompting EMNLP 2023 PROSE: A Pronoun Omission Solution for Chinese-English Spoken Language Translation EMNLP 2023 M3Seg: A Maximum-Minimum Mutual Information Paradigm for Unsupervised Topic Segmentation in ASR Transcripts EMNLP 2023 CO-Net: Learning Multiple Point Cloud Tasks at Once with A Cohesive Network ICCV 2023 OFVL-MS: Once for Visual Localization across Multiple Indoor Scenes ICCV 2023 Poly-PC: A Polyhedral Network for Multiple Point Cloud Tasks at Once CVPR 2023 Semi-Supervised Parametric Real-World Image Harmonization CVPR 2023 Curricular Object Manipulation in LiDAR-Based Object Detection CVPR 2023 ResoNet: Noise-Trained Physics-Informed MRI Off-Resonance Correction NIPS 2023 ORCHID: A Chinese Debate Corpus for Target-Independent Stance Detection and Argumentative Dialogue Summarization EMNLP 2023 Disentangled Representation for Causal Mediation Analysis AAAI 2023 TSMind: Alibaba and Soochow University’s Submission to the WMT22 Translation Suggestion Task EMNLP 2022 Robust Learning against Relational Adversaries NIPS 2022 Incorporating Item Frequency for Differentially Private Set Union AAAI 2022 XYLayoutLM: Towards Layout-Aware Multimodal Networks for Visually-Rich Document Understanding CVPR 2022 Gated Mechanism Enhanced Multi-Task Learning for Dialog Routing COLING 2022 TransSum: Translating Aspect and Sentiment Embeddings for Self-Supervised Opinion Summarization ACL 2021 Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation NIPS 2021 Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation EMNLP 2021 Bridging the Domain Gap: Improve Informal Language Translation via Counterfactual Domain Adaptation AAAI 2021 TransSum: Translating Aspect and Sentiment Embeddings for Self-Supervised Opinion Summarization IJCNLP 2021 TermMind: Alibaba’s WMT21 Machine Translation Using Terminologies Task Submission EMNLP 2021 QEMind: Alibaba’s Submission to the WMT21 Quality Estimation Shared Task EMNLP 2021 Differentially Private Top-k Selection via Stability on Unknown Domain UAI 2020 Adversarial Text Generation via Sequence Contrast Discrimination EMNLP 2020 Computer Assisted Translation with Neural Quality Estimation and Automatic Post-Editing EMNLP 2020 Alibaba’s Submission for the WMT 2020 APE Shared Task: Improving Automatic Post-Editing with Pre-trained Conditional Cross-Lingual BERT EMNLP 2020 SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference ICLR 2020 HOPPITY: LEARNING GRAPH TRANSFORMATIONS TO DETECT AND FIX BUGS IN PROGRAMS ICLR 2020 Automatic Emergency Diagnosis with Knowledge-Based Tree Decoding IJCAI 2020 Differentially Private Survival Function Estimation MLHC 2020 Providing SLOs for Resource-Harvesting VMs in Cloud Platforms OSDI 2020 Differentially Private Small Dataset Release Using Random Projections UAI 2020 Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation NIPS 2019 Exact Gaussian Processes on a Million Data Points NIPS 2019 Discrete Binary Coding based Label Distribution Learning IJCAI 2019 Cost-Sensitive Learning to Rank AAAI 2019 Empirical Evaluation of Speaker Adaptation on DNN Based Acoustic Model INTERSPEECH 2018 Binary Coding based Label Distribution Learning IJCAI 2018 Dynamic Neural Program Embeddings for Program Repair ICLR 2018 Investigating Generative Adversarial Networks Based Speech Dereverberation for Robust Speech Recognition INTERSPEECH 2018 SentiGAN: Generating Sentimental Texts via Mixture Adversarial Networks IJCAI 2018 Dimensionally Guided Synthesis of Mathematical Word Problems IJCAI 2016 Minimal Solvers for 3D Geometry From Satellite Imagery ICCV 2015 Automated Geometry Theorem Proving for Human-Readable Proofs IJCAI 2015 Automatic Generation of Raven’s Progressive Matrices IJCAI 2015 Stereo under Sequential Optimal Sampling: A Statistical Analysis Framework for Search Space Reduction CVPR 2014