Kangheng Lin

According to our database1, Kangheng Lin authored at least 12 papers between 2025 and 2026.

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

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments.
CoRR, April, 2026

DM0: An Embodied-Native Vision-Language-Action Model towards Physical AI.
CoRR, February, 2026

STEP3-VL-10B Technical Report.
CoRR, January, 2026

VALU: A Benchmark for Video Anomaly Temporal Localization and Understanding at Multiple Semantic Levels.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025
NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale.
CoRR, August, 2025

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning.
CoRR, July, 2025

Unhackable Temporal Rewarding for Scalable Video MLLMs.
CoRR, February, 2025

PerPO: Perceptual Preference Optimization via Discriminative Rewarding.
CoRR, February, 2025

Do LVLMs Truly Understand Video Anomalies? Revealing Hallucination via Co-Occurrence Patterns.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Perception-R1: Pioneering Perception Policy with Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Perception in Reflection.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Unhackable Temporal Reward for Scalable Video MLLMs.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025


  Loading...