10 papers
Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models
Senqiao Yang, Chengyao Wang, Yuxin Chen +13
Scaling robot data is crucial for building generalist Vision-Language-Action (VLA) models, yet robot trajectories are harder to scale than web-scale image-text data because embodie…
GKDT: General Keypoint Detection Transformer
Changsheng Lu, Yuxin Chen, Haokun Gui +5
With the emergence of various pre-trained vision and language models, computer vision is shifting from narrow-domain to open-domain recognition. The construction of a more powerful…
Semantic Generative Tuning for Unified Multimodal Models
Songsong Yu, Yuxin Chen, Ying Shan +1
Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture. However, prevailing training paradigms independently…
Reasoning Can Be Restored by Correcting a Few Decision Tokens
Changshuo Shen, Leheng Sheng, Yuxin Chen +2
Large reasoning models (LRMs) substantially outperform their base LLM counterparts on challenging reasoning benchmarks, yet it remains poorly understood where base models go wrong…
CLAW: Composable Language-Annotated Whole-body Motion Generation
Jianuo Cao, Yuxin Chen, Masayoshi Tomizuka
Training language-conditioned whole-body controllers for humanoid robots demands large-scale motion-language datasets. Existing approaches based on motion capture are costly and li…
LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling
Yuxin Chen, Chumeng Liang, Hangke Sui +4
Continuous diffusion has been the foundation of high-fidelity, controllable, and few-step generation of many data modalities such as images. However, in language modeling, prior co…
StarVLA-: Reducing Complexity in Vision-Language-Action Systems
Jinhui Ye, Ning Gao, Senqiao Yang +7
Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for building general-purpose robotic agents. However, the VLA landscape remains highly fragmented…
OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video
Junfu Pu, Yuxin Chen, Teng Wang +1
Current multimodal large language models (MLLMs) have demonstrated remarkable capabilities in short-form video understanding, yet translating long-form cinematic videos into detail…
VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models
Zixuan Wang, Yuxin Chen, Yuqi Liu +6
Vision-Language-Action (VLA) models typically map visual observations and linguistic instructions directly to control signals. This "black-box" mapping forces a single forward pass…
Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models
Shengchao Zhou, Yuxin Chen, Yuying Ge +4
Vision-language models (VLM) excel at general understanding yet remain weak at dynamic spatial reasoning (DSR), i.e., reasoning about the evolvement of object geometry and relation…