Xi Wang

JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification ACL 2026 Hallucination as a Computational Boundary: A Hierarchy of Inevitability and the Oracle Escape AAAI 2026 TokenPowerBench: Benchmarking the Power Consumption of LLM Inference AAAI 2026 Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs’ Hallucinations ACL 2026 Towards Robust Edge Model Adaptation via Elastic Architecture Search AAAI 2026 Autonomous Vehicle Path Planning by Searching with Differentiable Simulation AAAI 2026 TrendFact: A Benchmark Towards Hotspot Perception in Automatic Fact-Checking ACL 2026 ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesis ACL 2026 FIXME: Towards End-to-End Benchmarking of LLM-Aided Design Verification AAAI 2026 Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories ACL 2026 RABot: Reinforcement-Guided Graph Augmentation for Imbalanced and Noisy Social Bot Detection AAAI 2026 ChipMind: Retrieval-Augmented Reasoning for Long-Context Circuit Design Specifications AAAI 2026 GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQL ACL 2026 Decomposing Prompts, Composing Actions: A Multi-Granularity Prompting Approach for Incremental Action Learning AAAI 2026 KBLaM: Knowledge Base augmented Language Model ICLR 2025 Leveraging Driver Field-of-View for Multimodal Ego-Trajectory Prediction ICLR 2025 How to set AdamW’s weight decay as you scale model and dataset size ICML 2025 OMS: One More Step Noise Searching to Enhance Membership Inference Attacks for Diffusion Models IJCAI 2025 Exploration-Driven Generative Interactive Environments CVPR 2025 MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation NAACL 2025 Adaptive Retrieval-Augmented Generation for Conversational Systems NAACL 2025 Bio2Vol: Adapting 2D Biomedical Foundation Models for Volumetric Medical Image Segmentation MICCAI 2025 Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience EMNLP 2025 Analyzing values about gendered language reform in LLMs’ revisions EMNLP 2025 AKiRa: Augmentation Kit on Rays for Optical Video Generation CVPR 2025 GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control CVPR 2025 Understanding Museum Exhibits using Vision-Language Reasoning ICCV 2025 Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description ICCV 2025 Di[M]O: Distilling Masked Diffusion Models into One-step Generator ICCV 2025 DCTMamba: Advancing JPEG Image Restoration Through Long-Sequence Modeling and Adaptive Frequency Strategy AAAI 2025 SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering AAAI 2025 LineArt: A Knowledge-guided Training-free High-quality Appearance Transfer for Design Drawing with Diffusion Model CVPR 2025 PALM: Predicting Actions through Language Models ECCV 2024 SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation NIPS 2024 Transparent and Scrutable Recommendations Using Natural Language User Profiles ACL 2024 Coarse-to-Fine Latent Diffusion Model for Glaucoma Forecast on Sequential Fundus Images MICCAI 2024 Noise Level Adaptive Diffusion Model for Robust Reconstruction of Accelerated MRI MICCAI 2024 Joint control variate for faster black-box variational inference AISTATS 2024 Extragradient Type Methods for Riemannian Variational Inequality Problems AISTATS 2024 Characteristic AI Agents via Large Language Models COLING 2024 Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation CVPR 2024 Long-Tail Class Incremental Learning via Independent Sub-prototype Construction CVPR 2024 What Do You See in Vehicle? Comprehensive Vision Solution for In-Vehicle Gaze Estimation CVPR 2024 WANDR: Intention-guided Human Motion Generation CVPR 2024 Clarifying the Path to User Satisfaction: An Investigation into Clarification Usefulness EACL 2024 E.T. the Exceptional Trajectory: Text-to-camera-trajectory generation with character awareness ECCV 2024 Real Appearance Modeling for More General Deepfake Detection ECCV 2024 Source-Free Domain-Invariant Performance Prediction ECCV 2024 NeRFail: Neural Radiance Fields-Based Multiview Adversarial Attack AAAI 2024 Bayesian Low-rank Adaptation for Large Language Models ICLR 2024 Convolutional Persistence as a Remedy to Neural Model Analysis AISTATS 2023 SpatialFormer: Semantic and Target Aware Attentions for Few-Shot Learning AAAI 2023 Task2KB: A Public Task-Oriented Knowledge Base AAAI 2023 A Survey on Asking Clarification Questions Datasets in Conversational Systems ACL 2023 JAWS: Just a Wild Shot for Cinematic Transfer in Neural Radiance Fields CVPR 2023 GazeNeRF: 3D-Aware Gaze Redirection With Neural Radiance Fields CVPR 2023 Improving Conversational Recommendation Systems via Bias Analysis and Language-Model-Enhanced Data Augmentation EMNLP 2023 Particle-based Variational Inference with Preconditioned Functional Gradient Flow ICLR 2023 Robustness to corruption in pre-trained Bayesian neural networks ICLR 2023 Large-Scale Automatic Audiobook Creation INTERSPEECH 2023 ContextSpeech: Expressive and Efficient Text-to-Speech for Paragraph Reading INTERSPEECH 2023 Online Optimization over Riemannian Manifolds JMLR 2023 SMASH: Improving SMAll Language Models’ Few-SHot Ability with Prompt-Based Distillation EMNLP 2022 Self-supervised Context-aware Style Representation for Expressive Speech Synthesis INTERSPEECH 2022 SoftSpeech: Unsupervised Duration Model in FastSpeech 2 INTERSPEECH 2022 Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation NIPS 2022 Distributed Online Convex Optimization with Compressed Communication NIPS 2022 Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning CVPR 2022 JPEG Artifacts Removal via Contrastive Representation Learning ECCV 2022 MetaASSIST: Robust Dialogue State Tracking with Meta Learning EMNLP 2022 QuadrupletBERT: An Efficient Model For Embedding-Based Large-Scale Retrieval NAACL 2021 Self-Supervised 3D Hand Pose Estimation From Monocular RGB via Contrastive Learning ICCV 2021 Learning Dual Priors for JPEG Compression Artifacts Removal ICCV 2021 Improving Embedding-based Large-scale Retrieval via Label Enhancement EMNLP 2021 No-regret Online Learning over Riemannian Manifolds NIPS 2021 Specification and verification in the field: Applying formal methods to BPF just-in-time compilers in the Linux kernel OSDI 2020 An Efficient Subband Linear Prediction for LPCNet-Based Neural Synthesis INTERSPEECH 2020 Relaxed Multivariate Bernoulli Distribution and Its Applications to Deep Generative Models UAI 2020 Thunderbolt: Throughput-Optimized, Quality-of-Service-Aware Power Capping at Scale OSDI 2020 Automated Verification of Customizable Middlebox Properties with Gravel NSDI 2020 Forward-Backward Decoding for Regularizing End-to-End TTS INTERSPEECH 2019 Nickel: A Framework for Design and Verification of Information Flow Control Systems OSDI 2018 A New Glottal Neural Vocoder for Speech Synthesis INTERSPEECH 2018 Large-Scale Domain Adaptation via Teacher-Student Learning INTERSPEECH 2017 Push-Button Verification of File Systems via Crash Refinement OSDI 2016 Identifying Information Disclosure in Web Applications with Retroactive Auditing OSDI 2014 Jitk: A Trustworthy In-Kernel Interpreter Infrastructure OSDI 2014 Improving Integer Security for Systems with KINT OSDI 2012