10 papers
What Makes an Efficient VLA? Navigating Action-Head Design, Scaling, and Latency
Luoyang Sun, Guoyang Xia, Fengfa Li +9
Vision-Language-Action (VLA) models combine a pretrained vision encoder, a language backbone, and an action head, but their relative contribution has not been established under con…
VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment
Guoyang Xia, Fengfa Li, Hongjin Ji +4
Vision-language-action models (VLAs) have recently advanced robotic manipulation, yet the effects of different robot-data pre-training paradigms remain difficult to compare because…
MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models
Yuncheng Yang, Feiyang Ye, Shixian Luo +7
Vision-Language Models (VLMs) have achieved success using homogeneous Transformers to process multimedia data. Recent studies show that heterogeneous structures interleaving effici…
Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling
Yilong Chen, Yanxi Xie, Zitian Gao +10
Large token-indexed lookup tables provide a compute-decoupled scaling path, but their practical gains are often limited by poor parameter efficiency and rapid memory growth. We att…
Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs
Luoyang Sun, Jiwen Jiang, Yifeng Ding +9
Vision-Language-Action Models (VLAs) have emerged as a key paradigm of Physical AI and are increasingly deployed in autonomous vehicles, robots, and smart spaces. In these resource…
MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources
Baorui Ma, Jiahui Yang, Donglin Di +5
Scaling has powered recent advances in vision foundation models, yet extending this paradigm to metric depth estimation remains challenging due to heterogeneous sensor noise, camer…
AFD-SLU: Adaptive Feature Distillation for Spoken Language Understanding
Yan Xie, Yibo Cui, Liang Xie +1
Spoken Language Understanding (SLU) is a core component of conversational systems, enabling machines to interpret user utterances. Despite its importance, developing effective SLU…
Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning
Yang Zhou, Sunzhu Li, Shunyu Liu +11
Recent advances in Large Language Models (LLMs) have underscored the potential of Reinforcement Learning (RL) to facilitate the emergence of reasoning capabilities. Despite the enc…
QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation
Jiahui Yang, Yongjia Ma, Donglin Di +6
Existing text-to-image models often rely on parameter fine-tuning techniques such as Low-Rank Adaptation (LoRA) to customize visual attributes. However, when combining multiple LoR…
Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking
Yilong Chen, Junyuan Shang, Zhenyu Zhang +7
Large language models (LLMs) face inherent performance bottlenecks under parameter constraints, particularly in processing critical tokens that demand complex reasoning. Empirical…