9 papers
FysicsWorld: A Unified Full-Modality Benchmark for Any-to-Any Understanding, Generation, and Reasoning
Yue Jiang, Dingkang Yang, Minghao Han +6
Despite rapid progress in multimodal large language models (MLLMs) and emerging omni-modal architectures, current benchmarks remain limited in scope and integration, suffering from…
SatireDecoder: Visual Cascaded Decoupling for Enhancing Satirical Image Comprehension
Yue Jiang, Haiwei Xue, Minghao Han +5
Satire, a form of artistic expression combining humor with implicit critique, holds significant social value by illuminating societal issues. Despite its cultural and societal sign…
Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding
Keliang Liu, Zizhi Chen, Mingcheng Li +3
Document understanding is a long standing practical task. Vision Language Models (VLMs) have gradually become a primary approach in this domain, demonstrating effective performance…
FSRF: Factorization-guided Semantic Recovery for Incomplete Multimodal Sentiment Analysis
Ziyang Liu, Pengjunfei Chu, Shuming Dong +3
In recent years, Multimodal Sentiment Analysis (MSA) has become a research hotspot that aims to utilize multimodal data for human sentiment understanding. Previous MSA studies have…
COPO: Consistency-Aware Policy Optimization
Jinghang Han, Jiawei Chen, Hang Shao +7
Reinforcement learning has significantly enhanced the reasoning capabilities of Large Language Models (LLMs) in complex problem-solving tasks. Recently, the introduction of DeepSee…
PersonaAnimator: Personalized Motion Transfer from Unconstrained Videos
Ziyun Qian, Runyu Xiao, Shuyuan Tu +7
Recent advances in motion generation show remarkable progress. However, several limitations remain: (1) Existing pose-guided character motion transfer methods merely replicate moti…