Cong Wang

Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression ACL 2026 AEA: Adaptive Expert Allocation Improves Sentence Embeddings from Mixture-of-Experts LLM ACL 2026 See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs ACL 2026 Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism ACL 2026 Beyond Single-Point Perturbation: A Hierarchical, Manifold-Aware Approach to Diffusion Attacks AAAI 2026 Investigating More Explainable and Partition-Free Compositionality Estimation for LLMs: A Rule-Generation Perspective ACL 2026 Focusing Condition: Inference-Time Self-Contrastive Steering Elicits Better Conditional Text Embeddings in LLMs ACL 2026 RegionMarker: A Region-Triggered Semantic Watermarking Framework for Embedding-as-a-Service Copyright Protection AAAI 2026 HQ-SVC: Towards High-Quality Zero-Shot Singing Voice Conversion in Low-Resource Scenarios AAAI 2026 RFF-TTA: Physical Information-Aware Prototype for Temporally Varying RF Fingerprinting Online Test-Time-Adaptation AAAI 2026 UniFit: Towards Universal Virtual Try-on with MLLM-Guided Semantic Alignment AAAI 2026 IMAGGarment+: Efficient Attribute-Wise Diffusion for Garment Generation AAAI 2026 CHOIR: Harmonizing Structured Persona Diversity for Robust Collaborative LLM Reasoning ACL 2026 MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing CVPR 2025 Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models AAAI 2025 IMAGDressing-v1: Customizable Virtual Dressing AAAI 2025 Intra and Inter Parser-Prompted Transformers for Effective Image Restoration AAAI 2025 Fed-DFA: Federated Distillation for Heterogeneous Model Fusion Through the Adversarial Lens AAAI 2025 CALM: Curiosity-Driven Auditing for Large Language Models AAAI 2025 Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering ACL 2025 Multi-Prompting Decoder Helps Better Language Understanding ACL 2025 Review-Instruct: A Review-Driven Multi-Turn Conversations Generation Method for Large Language Models ACL 2025 LMEraser: Large Model Unlearning via Adaptive Prompt Tuning AISTATS 2025 Can't Slow Me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devices CVPR 2025 RoDEval: A Robust Word Sense Disambiguation Evaluation Framework for Large Language Models EMNLP 2025 A Survey on LLMs for Story Generation EMNLP 2025 SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time Editing ICCV 2025 D3: Training-Free AI-Generated Video Detection Using Second-Order Features ICCV 2025 Revisiting Adversarial Patch Defenses on Object Detectors: Unified Evaluation, Large-Scale Dataset, and New Insights ICCV 2025 Fine-Grained 3D Gaussian Head Avatars Modeling from Static Captures via Joint Reconstruction and Registration ICCV 2025 Ensembling Diffusion Models via Adaptive Feature Aggregation ICLR 2025 Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model ICML 2025 Optimal Graph Learning and Nuclear Norm Maximization for Deep Cross-Domain Robust Label Propagation IJCAI 2024 Multi-Attention Based Visual-Semantic Interaction for Few-Shot Learning IJCAI 2024 Constrained Intrinsic Motivation for Reinforcement Learning IJCAI 2024 Value at Adversarial Risk: A Graph Defense Strategy against Cost-Aware Attacks AAAI 2024 SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency AAAI 2024 Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models ICLR 2024 AP-Adapter: Improving Generalization of Automatic Prompts on Unseen Text-to-Image Diffusion Models NIPS 2024 Sharpness-Aware Model-Agnostic Long-Tailed Domain Generalization AAAI 2024 Batch Singular Value Polarization and Weighted Semantic Augmentation for Universal Domain Adaptation ICML 2024 Correlation Matching Transformation Transformers for UHD Image Restoration AAAI 2024 Demonstrating Adaptive Mobile Manipulation in Retail Environments RSS 2024 Enhancing Modal Fusion by Alignment and Label Matching for Multimodal Emotion Recognition INTERSPEECH 2024 Explore Internal and External Similarity for Single Image Deraining with Graph Neural Networks IJCAI 2024 LoLep: Single-View View Synthesis with Locally-Learned Planes and Self-Attention Occlusion Inference ICCV 2023 Bayes-MIL: A New Probabilistic Perspective on Attention-based Multiple Instance Learning for Whole Slide Images ICLR 2023 PromptRestorer: A Prompting Image Restoration Method with Degradation Perception NIPS 2023 Boomerang: Metadata-Private Messaging under Hardware Trust NSDI 2023 Honeycomb: Secure and Efficient GPU Executions via Static Validation OSDI 2023 Aggregating Multiple Heuristic Signals as Supervision for Unsupervised Automated Essay Scoring ACL 2023 Adaptive Gating in Mixture-of-Experts based Language Models EMNLP 2023 Controlling Class Layout for Deep Ordinal Classification via Constrained Proxies Learning AAAI 2023 Weakly Supervised 3D Segmentation via Receptive-Driven Pseudo Label Consistency and Structural Consistency AAAI 2023 Convolutional Embedding Makes Hierarchical Vision Transformer Stronger ECCV 2022 Optimal Transport for Label-Efficient Visible-Infrared Person Re-identification ECCV 2022 Online-Updated High-Order Collaborative Networks for Single Image Deraining AAAI 2022 Amplifying Membership Exposure via Data Poisoning NIPS 2022 Task-Level Self-Supervision for Cross-Domain Few-Shot Learning AAAI 2022 TransBoost: A Boosting-Tree Kernel Transfer Learning Algorithm for Improving Financial Inclusion AAAI 2022 CARTL: Cooperative Adversarially-Robust Transfer Learning ICML 2021 You See What I Want You To See: Exploring Targeted Black-Box Transferability Attack for Hash-Based Image Retrieval Systems CVPR 2021 Evade Deep Image Retrieval by Stashing Private Images in the Hash Space CVPR 2020 Explore Truthful Incentives for Tasks with Heterogenous Levels of Difficulty in the Sharing Economy IJCAI 2019 GELU-Net: A Globally Encrypted, Locally Unencrypted Deep Neural Network for Privacy-Preserved Learning IJCAI 2018