Mengchen Qian
3 papers · 2026–2026 · 1 venue · 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.
Venues
Top co-authors
Research topics
Keywords
frame selection
(1)
curvature
(1)
multimodal large language model
(1)
hallucination detection
(1)
multi-agent architecture
(1)
large language model
(1)
temporal signal
(1)
neuro-symbolic framework
(1)
cross-modal comprehension
(1)
topology generation
(1)
accuracy
(1)
benchmark
(1)
generation
(1)
expert-level gpqa
(1)
knowledge-conditioned
(1)
region-specific selection
(1)
similarity curve
(1)
visual-token budget
(1)
Papers
OmniHallu: Unified Hallucination Detection for Cross-Modal Comprehension and Generation in Multimodal Large Language Models
EMNLP 2026
RIDGE: Region-Informed Derivative-Guided Evidence Selection for Long Video Understanding
EMNLP 2026
When Evidence Shapes Collaboration: Knowledge-Conditioned Topology Generation for Multi-Agent Systems
EMNLP 2026