8 papers
Position: Reasoning After Perception Means Reasoning Without Vision
Hongcheng Gao, Zihao Huang, Jingyi Tang +12
A common belief in multimodal research is that the perceptual weaknesses of vision--language models can be compensated by stronger language reasoning (e.g., chain-of-thought, in-co…
Predicting Mergeability of Parameter-Efficient Fine-Tuning Updates
Lin Tang, Wei Zhang, Jing Li +3
Low-rank adaptation (LoRA) makes it cheap to train many domain- and task-specific language model adapters, but whether two adapters can be merged is usually discovered only after b…
SonicBench: Dissecting the Physical Perception Bottleneck in Large Audio Language Models
Yirong Sun, Yanjun Chen, Xin Qiu +8
Large Audio Language Models (LALMs) excel at semantic and paralinguistic tasks, yet their ability to perceive the fundamental physical attributes of audio such as pitch, loudness,…
PhysVideoGenerator: Towards Physically Aware Video Generation via Latent Physics Guidance
Siddarth Nilol Kundur Satish, Devesh Jaiswal, Hongyu Chen +1
Current video generation models produce high-quality aesthetic videos but often struggle to learn representations of real-world physics dynamics, resulting in artifacts such as unn…
BRACE: A Benchmark for Robust Audio Caption Quality Evaluation
Tianyu Guo, Hongyu Chen, Hao Liang +5
Automatic audio captioning is essential for audio understanding, enabling applications such as accessibility and content indexing. However, evaluating the quality of audio captions…
UML-CoT: Structured Reasoning and Planning with Unified Modeling Language for Robotic Room Cleaning
Hongyu Chen, Guangrun Wang
Chain-of-Thought (CoT) prompting improves reasoning in large language models (LLMs), but its reliance on unstructured text limits interpretability and executability in embodied tas…