Lin Zhang

Temporal Precision Matters: Brain-Tuning Speech Language Models with Millisecond-Resolution Neural Signals ACL 2026 Why Do Emotions Change? Appraisal-Guided Reasoning for Emotion–Cause Triplet Extraction in Conversations ACL 2026 SEBSFormer: A Spectral-Enhanced Bi-Stream Transformer for Robust EEG Decoding AAAI 2026 SmartSplat: Feature-Smart Gaussians for Scalable Compression of Ultra-High-Resolution Images AAAI 2026 RealRep: Generalized SDR-to-HDR Conversion via Attribute-Disentangled Representation Learning AAAI 2026 Multi-Programming Language Sandbox for LLMs ACL 2025 Towards Audio-Visual Navigation in Noisy Environments: A Large-Scale Benchmark Dataset and an Architecture Considering Multiple Sound-Sources AAAI 2025 BigMac: A Communication-Efficient Mixture-of-Experts Model Structure for Fast Training and Inference AAAI 2025 Representing Sounds as Neural Amplitude Fields: A Benchmark of Coordinate-MLPs and a Fourier Kolmogorov-Arnold Framework AAAI 2025 Efficient and Accurate Prompt Optimization: the Benefit of Memory in Exemplar-Guided Reflection ACL 2025 M3HG: Multimodal, Multi-scale, and Multi-type Node Heterogeneous Graph for Emotion Cause Triplet Extraction in Conversations ACL 2025 Entrospect: Information-Theoretic Self-Reflection Elicits Better Response Refinement of Small Language Models ACL 2025 OSDFace: One-Step Diffusion Model for Face Restoration CVPR 2025 GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control CVPR 2025 DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models CVPR 2025 SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning ICCV 2025 Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning NAACL 2025 3DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection NIPS 2024 Spoof Diarization: "What Spoofed When" in Partially Spoofed Audio INTERSPEECH 2024 How Do Neural Spoofing Countermeasures Detect Partially Spoofed Audio? INTERSPEECH 2024 Audio-Synchronized Visual Animation ECCV 2024 Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation AAAI 2024 DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence? EMNLP 2024 D3GU: Multi-Target Active Domain Adaptation via Enhancing Domain Alignment WACV 2024 Eva: Practical Second-order Optimization with Kronecker-vectorized Approximation ICLR 2023 D2Match: Leveraging Deep Learning and Degeneracy for Subgraph Matching ICML 2023 Feature Expansion for Graph Neural Networks ICML 2023 A Diffusion Model for Event Skeleton Generation ACL 2023 Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks ICML 2023 MVP-Tuning: Multi-View Knowledge Retrieval with Prompt Tuning for Commonsense Reasoning ACL 2023 Self-Supervised Bidirectional Learning for Graph Matching AAAI 2023 MAP: Multimodal Uncertainty-Aware Vision-Language Pre-Training Model CVPR 2023 Range-Based Equal Error Rate for Spoof Localization INTERSPEECH 2023 Solving Math Word Problems via Cooperative Reasoning induced Language Models ACL 2023 LMR: A Large-Scale Multi-Reference Dataset for Reference-Based Super-Resolution ICCV 2023 Learning From Temporal Gradient for Semi-Supervised Action Recognition CVPR 2022 Fine-Tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning CVPR 2022 RRSR:Reciprocal Reference-Based Image Super-Resolution with Progressive Feature Alignment and Selection ECCV 2022 Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective EMNLP 2022 Data Augmentation Using McAdams-Coefficient-Based Speaker Anonymization for Fake Audio Detection INTERSPEECH 2022 SiD-WaveFlow: A Low-Resource Vocoder Independent of Prior Knowledge INTERSPEECH 2022 Spoofing-Aware Attention based ASV Back-end with Multiple Enrollment Utterances and a Sampling Strategy for the SASV Challenge 2022 INTERSPEECH 2022 Exact Shape Correspondence via 2D graph convolution NIPS 2022 PCBERT: Parent and Child BERT for Chinese Few-shot NER COLING 2022 Self-Augmented Unpaired Image Dehazing via Density and Depth Decomposition CVPR 2022 Federated Learning for Non-IID Data via Unified Feature Learning and Optimization Objective Alignment ICCV 2021 MT-ORL: Multi-Task Occlusion Relationship Learning ICCV 2021 An Initial Investigation for Detecting Partially Spoofed Audio INTERSPEECH 2021 Regional Resonance of the Lower Vocal Tract and its Contribution to Speaker Characteristics INTERSPEECH 2020 ARET: Aggregated Residual Extended Time-Delay Neural Networks for Speaker Verification INTERSPEECH 2020 An Efficient Approach to Informative Feature Extraction from Multimodal Data AAAI 2019