most citedHuman Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs

2 citations · 2 across the 10 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2026

IRIS: An Intelligent Vision-Language System for Ocular Surface Diseases via Topic Tree and Scene-Driven VQA Generation

Hao Wei, Wenjin Qi, Dasen Dai +2

While Large Vision-Language Models (VLMs) demonstrate remarkable generic capabilities, their clinical reasoning in specialized domains like ocular surface diseases (OSDs) is severe…

cs.CV2026

ReMAP-PET: Beyond Visual Understanding -- Learning Region-Guided Metabolic Alignment Semantics from Brain PET

Dasen Dai, Yanteng Zhang, Shuoqi Li +6

Positron Emission Tomography (PET) reveals brain metabolism and is clinically central to neurodegenerative disease assessment, yet existing 3D brain foundation models treat PET as…

cs.CV2026

OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents

Shuang Chen, Kaituo Feng, Hangting Chen +7

Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence verification, and multi-step…

cs.CV20262 cited

Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs

Jen-Tse Huang, Dasen Dai, Jen-Yuan Huang +7

Humans develop perception through a bottom-up hierarchy: from basic primitives and Gestalt principles to high-level semantics. In contrast, current Multimodal Large Language Models…

cs.CV2026

Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis

Shuang Chen, Quanxin Shou, Hangting Chen +16

Unified multimodal models provide a natural and promising architecture for understanding diverse and complex real-world knowledge while generating high-quality images. However, the…

cs.CV2026

VidDoS: Universal Denial-of-Service Attack on Video-based Large Language Models

Duoxun Tang, Dasen Dai, Jiyao Wang +3

Video-LLMs are increasingly deployed in safety-critical applications but are vulnerable to Energy-Latency Attacks (ELAs) that exhaust computational resources. Current image-centric…