Tongtian Yue
7 papers · 2024–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π Conference Polyglot (3) π Renaissance Researcher (5) π Cross-Pollinator (14) πΊοΈ Taxonomy Completionist (19)
π§
Keyword Pioneer
β‘
Prolific Year
(5)
Conferences
CVPR (3)
EMNLP (2)
ICLR (2)
Top co-authors
Keywords
video language model
(2)
video understanding
(2)
object detection
(1)
motion estimation
(1)
temporal reasoning
(1)
question answering
(1)
multimodal learning
(1)
multi-modal learning
(1)
visual grounding
(1)
fine-grained recognition
(1)
low-rank adaptation
(1)
vision-language model
(1)
multimodal large language model
(1)
positional encoding
(1)
position encoding
(1)
long video understanding
(1)
mask generation
(1)
visual token compression
(1)
parameter-efficient adaptation
(1)
rotary position embedding
(1)
Papers
VRoPE: Rotary Position Embedding for Video Large Language Models
EMNLP 2025
Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs
ICLR 2025
Ada-K Routing: Boosting the Efficiency of MoE-based LLMs
ICLR 2025
Efficient Motion-Aware Video MLLM
CVPR 2025
ViPE: Visual Perception in Parameter Space for Efficient Video-Language Understanding
EMNLP 2025
SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models
CVPR 2024
Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression Segmentation
CVPR 2024