CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models
Paper • 2412.12932 • Published • 2
Hao Fei
scofield7419
AI & ML interests
Multimodal Learning, Large Language Model, Vision and Language, Natural Language Processing, Structural Modeling
Recent Activity
authored a paper 8 days ago
CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large
Vision-Language Models authored a paper 8 days ago
Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining authored a paper 8 days ago
Semantic Role Labeling: A Systematical SurveyOrganizations
authored 10
papers 8 days ago
Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining
Paper • 2412.10342 • Published
Semantic Role Labeling: A Systematical Survey
Paper • 2502.08660 • Published
Towards Multimodal Empathetic Response Generation: A Rich Text-Speech-Vision Avatar-based Benchmark
Paper • 2502.04976 • Published
Derm1M: A Million-scale Vision-Language Dataset Aligned with Clinical Ontology Knowledge for Dermatology
Paper • 2503.14911 • Published • 3
Unveiling the Cognitive Compass: Theory-of-Mind-Guided Multimodal Emotion Reasoning
Paper • 2602.00971 • Published
UniM: A Unified Any-to-Any Interleaved Multimodal Benchmark
Paper • 2603.05075 • Published • 1
SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models
Paper • 2604.12617 • Published • 6
Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment
Paper • 2604.19548 • Published • 16
Audio-Visual Intelligence in Large Foundation Models
Paper • 2605.04045 • Published • 33
submitted a
paper to Daily Papers 11 days ago
upvoted a paper 11 days ago
upvoted a paper 28 days ago
authored 7
papers 2 months ago
Towards Semantic Equivalence of Tokenization in Multimodal LLM
Paper • 2406.05127 • Published
So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection
Paper • 2505.18660 • Published • 2
Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models
Paper • 2505.24164 • Published
SMAP: Self-supervised Motion Adaptation for Physically Plausible Humanoid Whole-body Control
Paper • 2505.19463 • Published
MCM-DPO: Multifaceted Cross-Modal Direct Preference Optimization for Alt-text Generation
Paper • 2510.00647 • Published
DragNeXt: Rethinking Drag-Based Image Editing
Paper • 2506.07611 • Published • 1
A Reason-then-Describe Instruction Interpreter for Controllable Video Generation
Paper • 2511.20563 • Published • 1