5 papers
Test-Time Compositional Generalization in Diffusion Models via Concept Discovery
Zekun Wang, Anant Gupta, Tianyi Zhu +1
Compositional generalization requires models to produce novel configurations from familiar parts. In diffusion models, prior compositional generation methods typically assume that…
Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs
Hengwei Ye, Yuanting Guan, Yuxuan Ge +7
Multimodal Large Language Models (MLLMs) combine the linguistic strengths of LLMs with the ability to process multimodal data, enbaling them to address a broader range of visual ta…
AttAnchor: Guiding Cross-Modal Token Alignment in VLMs with Attention Anchors
Junyang Zhang, Tianyi Zhu, Thierry Tambe
A fundamental reason for the dominance of attention over RNNs and LSTMs in LLMs is its ability to capture long-range dependencies by modeling direct interactions between all tokens…
MOM: Memory-Efficient Offloaded Mini-Sequence Inference for Long Context Language Models
Junyang Zhang, Tianyi Zhu, Cheng Luo +1
Long-context language models exhibit impressive performance but remain challenging to deploy due to high GPU memory demands during inference. We propose Memory-efficient Offloaded…
MAG: Multi-Modal Aligned Autoregressive Co-Speech Gesture Generation without Vector Quantization
Binjie Liu, Lina Liu, Sanyi Zhang +5
This work focuses on full-body co-speech gesture generation. Existing methods typically employ an autoregressive model accompanied by vector-quantized tokens for gesture generation…