学者档案2020-2026ORCID 0000-0003-1476-0273
Liqiang Nie
Harbin Institute of Technology
104论文数
68末位作者
181合作者人数
1一作
0独著
一作与末位作者按论文署名顺序统计,部分顶会采用姓氏字母顺序署名。
近期论文104
- Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding第 6 位,共 6 位作者AAAI 2026 · 17 次引用
- ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval第 6 位,共 6 位作者CVPR 2026 · 16 次引用
- SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation第 7 位,共 7 位作者AAAI 2026 · 13 次引用
- TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval第 6 位,共 6 位作者ACL 2026 · 13 次引用
- Parallel Test-Time Scaling for Latent Reasoning Models第 5 位,共 6 位作者ACL 2026 · 10 次引用
- SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting第 6 位,共 6 位作者ICLR 2026 · 10 次引用
- TTOM: Test-Time Optimization and Memorization for Compositional Video Generation第 5 位,共 6 位作者ICLR 2026 · 6 次引用
- Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation第 6 位,共 6 位作者AAAI 2026 · 3 次引用
- TIME: Temporal-Sensitive Multi-Dimensional Instruction Tuning and Robust Benchmarking for Video-LLMs第 10 位,共 10 位作者AAAI 2026 · 1 次引用
- D2MoRA: Diversity-Regulated Asymmetric MoE-LoRA Decomposition for Efficient Multi-Task Adaptation第 7 位,共 7 位作者AAAI 2026
- Evolving Sparsity: Leveraging Token Importance Dynamics for Efficient LLM Decoding with Sparse Attention第 4 位,共 4 位作者ACL 2026
- StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video Retrieval第 6 位,共 6 位作者SIGIR 2026
- CogVLA: Cognition-Aligned Vision-Language-Action Models via Instruction-Driven Routing & Sparsification第 5 位,共 5 位作者NeurIPS 2025 · 87 次引用
- CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG第 5 位,共 5 位作者ACL 2025 · 15 次引用
- AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding第 6 位,共 6 位作者ACL Findings 2025 · 14 次引用
- Fair Deepfake Detectors Can Generalize第 5 位,共 6 位作者NeurIPS 2025 · 11 次引用
- GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching第 8 位,共 9 位作者AAAI 2025 · 10 次引用
- OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval第 6 位,共 6 位作者ACM MM 2025 · 10 次引用
- Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning第 4 位,共 4 位作者NeurIPS 2025 · 8 次引用
- Unified Transferability Metrics for Time Series Foundation Models第 6 位,共 6 位作者NeurIPS 2025 · 5 次引用
- Embodied Crowd Counting第 8 位,共 8 位作者NeurIPS 2025 · 3 次引用
- Rec: Towards Large Recommender Models with Reasoning第 7 位,共 7 位作者NeurIPS 2025 · 3 次引用
- Bi-Tuning with Collaborative Information for Controllable LLM-based Sequential Recommendation第 8 位,共 8 位作者ACL 2025 · 2 次引用
- FALCON: Resolving Visual Redundancy and Fragmentation in High-Resolution Multimodal Large Language Models via Visual Registers第 7 位,共 7 位作者ICCV 2025 · 2 次引用
- Less is More: Empowering GUI Agent with Context-Aware Simplification第 10 位,共 10 位作者ICCV 2025 · 2 次引用
- Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression第 5 位,共 5 位作者NeurIPS 2025 · 2 次引用
- Dually Self-Improved Counterfactual Data Augmentation Using Large Language Model第 5 位,共 5 位作者ACL 2025 · 1 次引用
- Enhancing HOI Detection with Contextual Cues from Large Vision-Language Models第 5 位,共 6 位作者ACM MM 2025 · 1 次引用
- HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models第 8 位,共 8 位作者ACL 2025 · 1 次引用
- Social Debiasing for Fair Multi-Modal LLMs第 7 位,共 7 位作者ICCV 2025 · 1 次引用
展示最近收录的 30 篇论文。
