Profiles2020-2026ORCID 0000-0003-1476-0273
Liqiang Nie
Harbin Institute of Technology
104Papers
68Last author
181Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers104
- Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video UnderstandingAuthor 6 of 6AAAI 2026 · 17 citations
- ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image RetrievalAuthor 6 of 6CVPR 2026 · 16 citations
- SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic ManipulationAuthor 7 of 7AAAI 2026 · 13 citations
- TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image RetrievalAuthor 6 of 6ACL 2026 · 13 citations
- Parallel Test-Time Scaling for Latent Reasoning ModelsAuthor 5 of 6ACL 2026 · 10 citations
- SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space SplittingAuthor 6 of 6ICLR 2026 · 10 citations
- TTOM: Test-Time Optimization and Memorization for Compositional Video GenerationAuthor 5 of 6ICLR 2026 · 6 citations
- Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action AnticipationAuthor 6 of 6AAAI 2026 · 3 citations
- TIME: Temporal-Sensitive Multi-Dimensional Instruction Tuning and Robust Benchmarking for Video-LLMsAuthor 10 of 10AAAI 2026 · 1 citation
- D2MoRA: Diversity-Regulated Asymmetric MoE-LoRA Decomposition for Efficient Multi-Task AdaptationAuthor 7 of 7AAAI 2026
- Evolving Sparsity: Leveraging Token Importance Dynamics for Efficient LLM Decoding with Sparse AttentionAuthor 4 of 4ACL 2026
- StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video RetrievalAuthor 6 of 6SIGIR 2026
- CogVLA: Cognition-Aligned Vision-Language-Action Models via Instruction-Driven Routing & SparsificationAuthor 5 of 5NeurIPS 2025 · 87 citations
- CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAGAuthor 5 of 5ACL 2025 · 15 citations
- AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language UnderstandingAuthor 6 of 6ACL Findings 2025 · 14 citations
- Fair Deepfake Detectors Can GeneralizeAuthor 5 of 6NeurIPS 2025 · 11 citations
- GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle DispatchingAuthor 8 of 9AAAI 2025 · 10 citations
- OFFSET: Segmentation-based Focus Shift Revision for Composed Image RetrievalAuthor 6 of 6ACM MM 2025 · 10 citations
- Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual LearningAuthor 4 of 4NeurIPS 2025 · 8 citations
- Unified Transferability Metrics for Time Series Foundation ModelsAuthor 6 of 6NeurIPS 2025 · 5 citations
- Embodied Crowd CountingAuthor 8 of 8NeurIPS 2025 · 3 citations
- Rec: Towards Large Recommender Models with ReasoningAuthor 7 of 7NeurIPS 2025 · 3 citations
- Bi-Tuning with Collaborative Information for Controllable LLM-based Sequential RecommendationAuthor 8 of 8ACL 2025 · 2 citations
- FALCON: Resolving Visual Redundancy and Fragmentation in High-Resolution Multimodal Large Language Models via Visual RegistersAuthor 7 of 7ICCV 2025 · 2 citations
- Less is More: Empowering GUI Agent with Context-Aware SimplificationAuthor 10 of 10ICCV 2025 · 2 citations
- Trained Mamba Emulates Online Gradient Descent in In-Context Linear RegressionAuthor 5 of 5NeurIPS 2025 · 2 citations
- Dually Self-Improved Counterfactual Data Augmentation Using Large Language ModelAuthor 5 of 5ACL 2025 · 1 citation
- Enhancing HOI Detection with Contextual Cues from Large Vision-Language ModelsAuthor 5 of 6ACM MM 2025 · 1 citation
- HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language ModelsAuthor 8 of 8ACL 2025 · 1 citation
- Social Debiasing for Fair Multi-Modal LLMsAuthor 7 of 7ICCV 2025 · 1 citation
Showing the 30 most recent indexed papers.
