Tao Feng

Orcid: 0000-0001-5571-8018

Affiliations:
  • Tsinghua University, Department of Computer Science and Technology, Knowledge Engineering Group, KEG, China
  • Sichuan University, College of Computer Science, Chengdu, China (PhD 2023)
  • Alibaba Group


According to our database1, Tao Feng authored at least 38 papers between 2021 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models.
CoRR, May, 2026

RotMoLE: Enhancing Mixture of Low-Rank Experts through Rotational Gating Mechanism.
CoRR, May, 2026

A Faster Path to Continual Learning.
CoRR, April, 2026

Zoom to Essence: Trainless GUI Grounding by Inferring upon Interface Elements.
CoRR, March, 2026

Why Does RL Generalize Better Than SFT? A Data-Centric Perspective on VLM Post-Training.
CoRR, February, 2026

OmniRAG-Agent: Agentic Omnimodal Reasoning for Low-Resource Long Audio-Video Question Answering.
CoRR, February, 2026

Continual GUI Agents.
CoRR, January, 2026

CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving.
CoRR, January, 2026

Adapt Before Continual Learning.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

Branch, or Layer? Zeroth-Order Optimization for Continual Learning of Vision-Language Models.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
C-Flat++: Towards a More Efficient and Powerful Framework for Continual Learning.
CoRR, August, 2025

Lumos-1: On Autoregressive Video Generation from a Unified Model Perspective.
CoRR, July, 2025

MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems.
CoRR, March, 2025

Generative Artificial Intelligence in Robotic Manipulation: A Survey.
CoRR, March, 2025

Parameter-Efficient Fine-Tuning for Foundation Models.
CoRR, January, 2025

Class-Incremental Player Detection With Refined Response-Based Knowledge Distillation.
IEEE Trans. Instrum. Meas., 2025

Visible light human activity recognition driven by generative language model.
Inf. Fusion, 2025

Behavior-Pred: A semantic-enhanced trajectory pre-training framework for motion forecasting.
Inf. Fusion, 2025

Multi-label feature selection with feature reconstruction and label correlations.
Expert Syst. Appl., 2025

A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

SAMora: Enhancing SAM through Hierarchical Self-Supervised Pre-Training for Medical Images.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

2024
UniGrad-FS: Unified Gradient Projection With Flatter Sharpness for Continual Learning.
IEEE Trans. Ind. Informatics, December, 2024

Hospital readmission prediction with hybrid-sampling and self-paced balance learning.
Concurr. Comput. Pract. Exp., August, 2024

Learning to cluster person via graph convolution networks for video-based person re-identification.
Concurr. Comput. Pract. Exp., August, 2024

Revisiting class-incremental object detection: An efficient approach via intrinsic characteristics alignment and task decoupling.
Expert Syst. Appl., 2024

BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systems.
CoRR, 2024

Make Continual Learning Stronger via C-Flat.
CoRR, 2024

Make Continual Learning Stronger via C-Flat.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Revisiting Neural Networks for Continual Learning: An Architectural Perspective.
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024

InstructVideo: Instructing Video Diffusion Models with Human Feedback.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
Refined Response Distillation for Class-Incremental Player Detection.
CoRR, 2023

RLIPv2: Fast Scaling of Relational Language-Image Pre-training.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022
Progressive Learning without Forgetting.
CoRR, 2022

RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
Towards Mask-robust Face Recognition.
Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2021


  Loading...