Chaofan Gan

Orcid: 0009-0001-5297-2202

According to our database1, Chaofan Gan authored at least 10 papers between 2024 and 2026.

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

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
From Priors to Perception: Grounding Video-LLMs in Physical Reality.
CoRR, May, 2026

MECD+: Unlocking Event-Level Causal Graph Discovery for Video Reasoning.
IEEE Trans. Pattern Anal. Mach. Intell., March, 2026

VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding.
CoRR, January, 2026

2025
Massive Activations are the Key to Local Detail Synthesis in Diffusion Transformers.
CoRR, October, 2025

Enhancing Video Large Language Models with Structured Multi-Video Collaborative Reasoning (early version).
CoRR, September, 2025

Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning.
CoRR, June, 2025

Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

MCA: 2D-3D Retrieval with Noisy Labels Via Multi-Level Adaptive Correction and Alignment.
Proceedings of the IEEE International Conference on Multimedia and Expo, ICME 2025 - Workshops, Nantes, France, June 30, 2025

2024
MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

DAC: 2D-3D Retrieval with Noisy Labels via Divide-and-Conquer Alignment and Correction.
Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024


  Loading...