Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Chelsea FinnSuggested from co-authorship
- Zhenhui LiSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works162 from public data
- Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction1,284
A Deep Multi-View Spatial-Temporal Network (DMVST-Net) framework to model both spatial and temporal relations is proposed, which demonstrates effectiveness of the approach over state-of-the-art methods.
- Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction857
A novel Spatial-Temporal Dynamic Network (STDN) is proposed, in which a flow gating mechanism is introduced to learn the dynamic similarity between locations, and a periodically shifted attention mechanism is designed to handle long-term periodic temporal shifting.
- IntelliLight815
This paper proposes a more effective deep reinforcement learning model for traffic light control and tests the method on a large-scale real traffic dataset obtained from surveillance cameras.
- Analyzing and Mitigating Object Hallucination in Large Vision-Language Models381
This work proposes a simple yet powerful algorithm, LVLM Hallucination Revisor (LURE), to post-hoc rectify object hallucination in LVLMs by reconstructing less hallucinatory descriptions and consistently ranks at the top in both GPT and human evaluations.
- Surgical Fine-Tuning Improves Adaptation to Distribution Shifts316
Theoretically, it is proved that for two-layer neural networks in an idealized setting, first-layer tuning can outperform fine-tuning all layers, and it is shown that in such settings, selectively fine- tuning a subset of layers matches or outperforms commonly used fine- Tuning approaches.
- Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction276
This paper is the first to leverage information from multiple cities to increase the stability of transfer and designs a spatial-temporal network with a meta-learning paradigm designed to utilize the long-period data from other cities via transfer learning.
- Few-Shot Knowledge Graph Completion257
This work proposes a novel few-shot relation learning model (FSRL) that can effectively capture knowledge from heterogeneous graph structure, aggregate representations of few- shot references, and match similar entity pairs of reference set for every relation.
- Transferring Robustness for Graph Neural Network Against Poisoning Attacks203
This work proposes PA-GNN, which relies on a penalized aggregation mechanism that directly restrict the negative impact of adversarial edges by assigning them lower attention coefficients, and designs a meta-optimization algorithm that trains PA- GNN to penalize perturbations using clean graphs and their adversarial counterparts, and transfers such ability to improve the robustness of PA-gNN on the poisoned graph.
- MetaLight: Value-Based Meta-Reinforcement Learning for Traffic Signal Control202
This paper proposes a novel framework, named as MetaLight, to speed up the learning process in new scenarios by leveraging the knowledge learned from existing scenarios, which improves the-state-of-the-art reinforcement learning model FRAP in traffic signal control by optimizing its model structure and updating paradigm.
- Graph Few-Shot Learning via Knowledge Transfer196
This work innovatively proposes a graph few-shot learning (GFL) algorithm that incorporates prior knowledge learned from auxiliary graphs to improve classification accuracy on the target graph.
- Multimodal Representation Learning by Alternating Unimodal Adaptation155
MLA reframes the conventional joint multimodal learning process by transforming it into an al-ternating unimodal learning process, thereby minimizing interference between modalities and demonstrating the superiority of MLA over competing prior approaches.
- SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation145
This work proposes SAFREE, a novel, training-free approach for safe T2I and T2V, that does not alter the model's weights and incorporates a novel self-validating filtering mechanism that dynamically adjusts the denoising steps when applying the filtered embeddings.
- Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values143
A new framework øurs is proposed, which leverages memory network to explore global patterns given estimations from local perspectives, and introduces adversarial training to enhance the modeling of global temporal distribution.
- Modeling Spatial-Temporal Dynamics for Traffic Prediction.142
A novel Spatial-Temporal Dynamic Network (STDN) framework is proposed, which proposes a flow gating mechanism to learn the dynamic similarity between locations via traffic flow and extends the framework from region-based traffic prediction to traffic prediction for road intersections by using graph convolutional structure.
- Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer135
A model-agnostic few-shot learning framework for spatio-temporal graph called ST-GFSL is proposed, which proposes to generate non-shared parameters based on node-level meta knowledge to enhance feature extraction by transferring cross-city knowledge.
- Holistic Evaluation of Language Models127
Holistic Evaluation of Language Models (HELM) is presented to improve the transparency of language models and intends for HELM to be a living benchmark for the community, continuously updated with new scenarios, metrics, and models.
- How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs116
This work introduces a comprehensive safety evaluation suite, covering both out-of-distribution (OOD) generalization and adversarial robustness, and proposes a straightforward attack strategy for misleading VLLMs to produce visual-unrelated responses.
- 116
- 111
- 93
- Predicting Academic Performance for College Students81
A multi-task predictive framework based on a learning-to-rank algorithm for academic performance prediction that captures inter-semester correlation, inter-major correlation, and integrates student similarity to predict students’ academic performance is built.
- 65
- On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective60
A holistic framework for advancing trustworthiness in GenAI is established, paving the way for safer and more responsible integration of GenFMs into critical applications and releasing the toolkit for dynamic evaluation.
- Non-Stationary Model for Crime Rate Inference Using Modern Urban Data54
This paper uses large-scale Point-Of-Interest data and taxi flow data in the city of Chicago, IL in the USA to tackle crime rate inference at the neighborhood level, and employs the geographically weighted regression on top of negative binomial model (GWNBR).
- Joint Modeling of Dense and Incomplete Trajectories for Citywide Traffic Volume Inference46
This paper proposes a novel framework for the citywide traffic volume inference using both dense GPS trajectories and incomplete trajectories captured by camera surveillance systems and employs a high-fidelity traffic simulator and deep reinforcement learning to recover full vehicle movements from the incomplete trajectoryories.
- 29
- 24
- Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment20
FiSAO (Fine-Grained Self-Alignment Optimization), a novel self-alignment method that utilizes the model's own visual encoder as a fine-grained verifier to improve vision-language alignment without the need for additional data, is proposed.
- 20
- 18
- 17
- 17
- 17
- 16
- MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation15
- 14
- 14
- 13
- 13
- 11
- 11
- 9
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 6
- 6
- 6
- 5
- 4
- Improving Domain Generalization with Domain Relations4
This paper focuses on domain shifts, which occur when the model is applied to new domains that are different from the ones it was trained on, and proposes a new approach called D 3 G, which learns domain-specific models by leveraging the relations among different domains by leveraging the relations among different domains.
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- Reliable and Responsible Foundation Models: A Comprehensive Survey1
Critical issues, including bias and fairness, security and privacy, uncertainty, explainability, and distribution shift are explored, as well as methods like alignment and Artificial Intelligence-Generated Content (AIGC) detection.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.