6 papers
DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents
Zhuoran Yu, Le Thien Phuc Nguyen, Jaden Park +5
Multimodal Large Language Models (MLLMs) have achieved strong performance on structured visual understanding tasks such as chart and document question answering. However, existing…
Reasoning-Augmented Representations for Multimodal Retrieval
Jianrui Zhang, Anirudh Sundara Rajan, Brandon Han +3
Universal Multimodal Retrieval (UMR) seeks any-to-any search across text and vision, yet modern embedding models remain brittle when queries require latent reasoning (e.g., resolvi…
See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models
Le Thien Phuc Nguyen, Zhuoran Yu, Samuel Low Yu Hang +8
Multimodal large language models (MLLMs) are expected to jointly interpret vision, audio, and language, yet existing video benchmarks rarely assess fine-grained reasoning about hum…
Contamination Detection for VLMs using Multi-Modal Semantic Perturbation
Jaden Park, Mu Cai, Feng Yao +3
Recent advances in Vision-Language Models (VLMs) have achieved state-of-the-art performance on numerous benchmark tasks. However, the use of internet-scale, often proprietary, pret…
Revisiting Active Speaker Detection: An In-the-Wild Benchmark for Generalization and Robustness
Le Thien Phuc Nguyen, Zhuoran Yu, Khoa Quang Nhat Cao +8
We present UniTalk, a novel dataset emphasizing challenging scenarios to enhance model generalization for the task of active speaker detection (ASD). Previously established benchma…
CoAPT: Context Attribute words for Prompt Tuning
Gun Lee, Subin An, Sungyong Baik +1
We propose a novel prompt tuning method called CoAPT(Context Attribute words in Prompt Tuning) for few/zero-shot image classification. The core motivation is that attributes are de…