297 citations · 465 across the 9 of their papers we have counts for
9 papers
UniMoFlow: Grounding Instruction-Driven 3D Human Motion Editing in Generation
Yilei Hua, Beibei Jing, Ce Zheng +3
Instruction-driven editing of 3D human motion requires precise spatiotemporal localization, rich semantic grounding, and strict preservation of unmodified content. Existing methods…
CoFi-UCGen: Coarse-to-Fine Unsupervised Conditional Generation without Label Priors
Shengxi Li, Zhaokun Hu, Ce Zheng +3
Unsupervised conditional image generation (UCGen) aims to control generation without relying on manually annotated labels, yet remains challenging due to unstructured semantic repr…
SpecFed: Accelerating Federated LLM Inference with Speculative Decoding and Compressed Transmission
Ce Zheng, Xinghan Wang, Jiahong Ning +3
Federated inference enhances LLM performance in edge computing through weighted averaging of distributed model predictions. However, autoregressive LLM inference requires frequent…
MAVERIX: Multimodal Audio-Visual Evaluation and Recognition IndeX
Liuyue Xie, Avik Kuthiala, George Z. Wei +12
We introduce MAVERIX (Multimodal audiovisual Evaluation and Recognition IndeX), a unified benchmark to probe the video understanding in multimodal LLMs, encompassing video, audio,…
VISTA: A Visual and Textual Attention Dataset for Interpreting Multimodal Models
Harshit, Tolga Tasdizen
The recent developments in deep learning led to the integration of natural language processing (NLP) with computer vision, resulting in powerful integrated Vision and Language Mode…
INT-FlashAttention: Enabling Flash Attention for INT8 Quantization
Shimao Chen, Zirui Liu, Zhiying Wu +6
As the foundation of large language models (LLMs), self-attention module faces the challenge of quadratic time and memory complexity with respect to sequence length. FlashAttention…
PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning
Ke Zhang, DanDan Zhu, Qiuhan Xu +2
Training for multi-agent reinforcement learning(MARL) is a time-consuming process caused by distribution shift of each agent. One drawback is that strategy of each agent in MARL is…
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Gemini Team, Petko Georgiev, Ving Ian Lei +1132
In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over…
PaLM 2 Technical Report
Rohan Anil, Andrew M. Dai, Orhan Firat +125
We introduce PaLM 2, a new state-of-the-art language model that has better multilingual and reasoning capabilities and is more compute-efficient than its predecessor PaLM. PaLM 2 i…