161 citations · 164 across the 8 of their papers we have counts for
8 papers
LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies
Jialei Chen, Kai Wang, Kang Chen +9
Vision-Language-Action models (VLAs) leverage large-scale vision-language pretraining for semantic robot control, but often lack explicit foresight into how robot actions change th…
ReXMoE: Reusing Experts with Minimal Overhead in Mixture-of-Experts
Zheyue Tan, Zhiyuan Li, Tao Yuan +13
Mixture-of-Experts (MoE) architectures have emerged as a promising approach to scale Large Language Models (LLMs). MoE boosts the efficiency by activating a subset of experts per t…
Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving
Yuxuan Zhou, Xien Liu, Chenwei Yan +8
Large language models (LLMs) have demonstrated remarkable performance on various medical benchmarks, but their capabilities across different cognitive levels remain underexplored.…
Megrez-Omni Technical Report
Boxun Li, Yadong Li, Zhiyuan Li +12
In this work, we present the Megrez models, comprising a language model (Megrez-3B-Instruct) and a multimodal model (Megrez-3B-Omni). These models are designed to deliver fast infe…
LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K
Tao Yuan, Xuefei Ning, Dong Zhou +10
State-of-the-art large language models (LLMs) are now claiming remarkable supported context lengths of 256k or even more. In contrast, the average context lengths of mainstream ben…
Tracking Objects as Pixel-wise Distributions
Zelin Zhao, Ze Wu, Yueqing Zhuang +2
Multi-object tracking (MOT) requires detecting and associating objects through frames. Unlike tracking via detected bounding boxes or tracking objects as points, we propose trackin…
Learning Context-Aware Embedding for Person Search
Shihui Chen, Yueqing Zhuang, Boxun Li
Person Search is a relevant task that aims to jointly solve Person Detection and Person Re-identification(re-ID). Though most previous methods focus on learning robust individual f…
Efficient DETR: Improving End-to-End Object Detector with Dense Prior
Zhuyu Yao, Jiangbo Ai, Boxun Li +1
The recently proposed end-to-end transformer detectors, such as DETR and Deformable DETR, have a cascade structure of stacking 6 decoder layers to update object queries iteratively…