8 papers
Accelerating Disaggregated RL for Visual Generative LLMs with Diffusion-Based Parallelism and Trainer-Assisted Generation
Sijie Wang, Zhengyu Qing, Zhiqiang Tan +6
Reinforcement learning (RL) has become a dominant post-training paradigm, driving the emergence of high-performance RL systems such as veRL for autoregressive large language models…
SDG-Track: A Heterogeneous Observer-Follower Framework for High-Resolution UAV Tracking on Embedded Platforms
Jiawen Wen, Yu Hu, Suixuan Qiu +2
Real-time tracking of small unmanned aerial vehicles (UAVs) on edge devices faces a fundamental resolution-speed conflict. Downsampling high-resolution imagery to standard detector…
Sparsity-Aware Low-Rank Representation for Efficient Fine-Tuning of Large Language Models
Longteng Zhang, Sen Wu, Shuai Hou +7
Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in…
Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum
Zhuoning Guo, Mingxin Li, Yanzhao Zhang +3
The prevailing video retrieval paradigm is structurally misaligned, as narrow benchmarks incentivize correspondingly limited data and single-task training. Therefore, universal cap…
Dissecting the NVIDIA Hopper Architecture through Microbenchmarking and Multiple Level Analysis
Weile Luo, Ruibo Fan, Zeyu Li +4
This study presents a comprehensive multi-level analysis of the NVIDIA Hopper GPU architecture, focusing on its performance characteristics and novel features. We benchmark Hopper'…
City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning
Penglei Sun, Yaoxian Song, Xiangru Zhu +7
Scene understanding enables intelligent agents to interpret and comprehend their environment. While existing large vision-language models (LVLMs) for scene understanding have prima…