9 papers
Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models
Yuansheng Gao, Jinman Zhao, Tong Zhang +5
Although Video Large Multimodal Models have achieved strong performance in video understanding, they still suffer from hallucination. Existing inference-time intervention methods u…
Synthetic Function Demonstrations Improve Generation in Low-Resource Programming Languages
Nick McKenna, Xinnuo Xu, Jack Williams +3
A key consideration when training an LLM is whether the target language is more or less resourced, for example English compared to Welsh, or Python compared to Excel. Typical train…
Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward
Tong Xiao, Xin Xu, Zhenya Huang +4
Enhancing the multimodal reasoning capabilities of Multimodal Large Language Models (MLLMs) is a challenging task that has attracted increasing attention in the community. Recently…
Better Think Thrice: Learning to Reason Causally with Double Counterfactual Consistency
Victoria Lin, Xinnuo Xu, Rachel Lawrence +4
Despite their strong performance on reasoning benchmarks, large language models (LLMs) have proven brittle when presented with counterfactual questions, suggesting weaknesses in th…
GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models
Jingxuan Wei, Caijun Jia, Xi Bai +7
The advent of Unified Multimodal Models (UMMs) signals a paradigm shift in artificial intelligence, moving from passive perception to active, cross-modal generation. Despite their…
HRIBench: Benchmarking Vision-Language Models for Real-Time Human Perception in Human-Robot Interaction
Zhonghao Shi, Enyu Zhao, Nathaniel Dennler +6
Real-time human perception is crucial for effective human-robot interaction (HRI). Large vision-language models (VLMs) offer promising generalizable perceptual capabilities but oft…