1 citations · 1 across the 12 of their papers we have counts for
14 papers
Outperforming 1000 Euclidean Layers With Hyperbolic Goal-Conditioned RL
Timo Klein, Thomas Lang, Andrii Shkabrii +3
Scaling self-supervised contrastive reinforcement learning (CRL) to 1000-layer Euclidean neural networks has enabled state-of-the-art goal-reaching performance, yet wall-clock time…
AC-VLA: Robust Out-of-Distribution Action Execution via Compositional Learning
Xiaojiang Peng, Kai Peng, Jie Lu +3
Vision-Language-Action (VLA) models excel at end-to-end robotic manipulation but struggle with out-of-distribution (OOD) generalization when familiar sub-tasks are recombined in un…
OmniOPSD: Rationale-Privileged On-Policy Self-Distillation for Affective Computing
Zebang Cheng, Shuimu Chen, Boxue Yang +7
Reinforcement learning for multimodal large language models (MLLMs) is often hindered by severe reward sparsity in complex reasoning tasks. This challenge is particularly pronounce…
Unleashing More Actions via Action Compositional Training for VLA Models
Kai Peng, Jie Lu, Xiaojiang Peng
Vision-Language-Action models excel at robotic manipulation, driven by the scale and diversity of demonstration data. However, standard training paradigms often cause VLA models to…
Adaptive Action Chunking at Inference-time for Vision-Language-Action Models
Yuanchang Liang, Xiaobo Wang, Kai Wang +5
In Vision-Language-Action (VLA) models, action chunking (i.e., executing a sequence of actions without intermediate replanning) is a key technique to improve robotic manipulation a…
On incremental and semi-global exponential stability of gradient flows satisfying generalized Łojasiewicz inequalities
Andreas Oliveira, Arthur C. B. de Oliveira, Mario Sznaier +1
The Łojasiewicz inequality characterizes objective-value convergence along gradient flows and, in special cases, yields exponential decay of the cost. However, such results do not…
ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows
Penghao Wang, Yuhao Zhou, Mengxuan Wu +12
As large language models (LLMs) advance, the ultimate vision for their role in science is emerging: we could build an AI collaborator to effectively assist human beings throughout…
EA-ViT: Efficient Adaptation for Elastic Vision Transformer
Chen Zhu, Wangbo Zhao, Huiwen Zhang +9
Vision Transformers (ViTs) have emerged as a foundational model in computer vision, excelling in generalization and adaptation to downstream tasks. However, deploying ViTs to suppo…
Dynamic Vision Mamba
Mengxuan Wu, Zekai Li, Zhiyuan Liang +9
Mamba-based vision models have gained extensive attention as a result of being computationally more efficient than attention-based models. However, spatial redundancy still exists…
MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification
Zhaopan Xu, Pengfei Zhou, Jiaxin Ai +6
Reasoning is an essential capacity for large language models (LLMs) to address complex tasks, where the identification of process errors is vital for improving this ability. Recent…
PEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language Models
Zhaopan Xu, Pengfei Zhou, Weidong Tang +7
Multimodal large language models (MLLMs) have achieved remarkable success in vision-language tasks, but their reliance on vast, internet-sourced data raises significant privacy and…
Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training
Mingjia Shi, Yuhao Zhou, Ruiji Yu +8
Vision Mamba has shown close to state of the art performance on computer vision tasks, drawing much interest in increasing it's efficiency. A promising approach is token reduction…
Dataset Growth
Ziheng Qin, Zhaopan Xu, Yukun Zhou +10
Deep learning benefits from the growing abundance of available data. Meanwhile, efficiently dealing with the growing data scale has become a challenge. Data publicly available are…
A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
Kai Wang, Mingjia Shi, Yukun Zhou +6
Training diffusion models is always a computation-intensive task. In this paper, we introduce a novel speed-up method for diffusion model training, called, which is based on a clos…