Shiyu Hu
9 papers · 2023–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (15) π£ Hot Topic Early Bird π Renaissance Researcher (5)
ποΈ
Keyword Collector
(50)
Top co-authors
Research topics
Artificial Intelligence
(6)
Computer Vision
(6)
Core AI Β· Artificial Intelligence
(6)
Analysis
(4)
Processing
(3)
Core AI Β· Computer Vision
(2)
Deep Learning
(1)
Interdisciplinary
(1)
Machine Learning
(1)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Cognitive Science
(1)
Domain-Specific
(1)
Learning Types
(1)
Methods
(1)
Keywords
multimodal learning
(3)
video understanding
(3)
vision-language tracking
(2)
vision-language model
(2)
reinforcement learning
(2)
object tracking
(2)
question answering
(1)
visual object tracking
(1)
reward modeling
(1)
visual reasoning
(1)
visual search
(1)
benchmark dataset
(1)
causal reasoning
(1)
cross-domain generalization
(1)
video reasoning
(1)
prompt tuning
(1)
semantic annotation
(1)
adaptive memory
(1)
spatio-temporal feature
(1)
temporal modeling
(1)
Papers
CausalStep: A Benchmark for Explicit Stepwise Causal Reasoning in Videos
AAAI 2026
Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning
ACL 2026
Select Less, Reason More: Prioritizing Evidence Purity for Video Reasoning
CVPR 2026
VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains
AAAI 2026
ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking
ICCV 2025
CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features
ICML 2025
Beyond Accuracy: Tracking more like Human via Visual Search
NeurIPS 2024
MemVLT: Vision-Language Tracking with Adaptive Memory-based Prompts
NeurIPS 2024
A Multi-modal Global Instance Tracking Benchmark (MGIT): Better Locating Target in Complex Spatio-temporal and Causal Relationship
NeurIPS 2023