2 citations · 3 across the 18 of their papers we have counts for
13 papers · 1 filter
RealtimeWAM: How Fast Can I Run My World Action Model?
Huanan Liu, Ye Li, Kangye Ji +8
World Action Models (WAMs) combine visual dynamics modeling with action generation, but their high inference latency limits responsive robot control. Recent efforts accelerate infe…
ChunkTrust: Adapting Execution Horizons for Robot Policies with Action-Expert Evidence
Fanding Huang, Jingyan Jiang, Shifeng Bao +13
Robot foundation policies predict action chunks, but how many actions to execute before replanning depends on the current task phase. We introduce ChunkTrust, which treats the exec…
CurvSpec: Adaptive Multi-Curvature Learning for Partial Relevant Video Retrieval
Zhen Liu, Letian Li, Jinpeng Wang +4
Partially Relevant Video Retrieval (PRVR) seeks to retrieve untrim-med videos containing a moment that matches a text query, without temporal annotations. The relevant moment may l…
FutureDuet: Decoupling Observation Access from Future Supervision in World Action Models
Jie Wu, Yuzhi Huang, Junqi Liu +5
World Action Models (WAMs) augment robot action generation with future visual supervision. Existing WAMs commonly fuse main and wrist observations into one visual stream and train…
GeniWorld: A Generalizable Interactive World Model for Robotic Manipulation via Visual Actions
Chenghao Gu, Hanyang Yu, Jingbo Zhang +7
Generalist robot policies exhibit strong capabilities, but their robustness in complex and unseen environments remains limited. Scaling robot learning and evaluation in diverse rea…
Respect Your Zero-Shot Uncertainty: Conservative Calibration for Test-Time-Adapted Vision-Language Models
Jingyan Jiang, Yaru Sun, Xiao Chen +5
Test-time adaptation (TTA) can improve the recognition accuracy of vision-language models under distribution shift, but often degrades calibration, making predictive confidence unr…
TAU-Bench: From Anomaly Instance Tracking to Fine-Grained Video Anomaly Understanding
Kepeng Yang, Dongxuan Liu, Rongxin Gao +8
Humans understand anomalous events through a coherent perceptual process in which they identify the focal instance, follow its behavior as the event unfolds, and interpret why it v…
ChainVLA: Chaining Vision-Language-Action Queries through a Unified Execution State for Long-Horizon Manipulation
Yuzhi Huang, Weijue Bu, Ziyi Xiong +4
Humans perform long-horizon manipulation by retaining knowledge of what earlier actions have established while continuously adapting the motion underway. By contrast, action-chunke…
DynTrace: Tracking Dynamic Object Evidence for 4D Spatio-Temporal Reasoning in MLLMs
Rongxin Gao, Yuzhi Huang, Dongxuan Liu +8
4D spatio-temporal reasoning, jointly modeling 3D spatial structure and temporal evolution, is essential for understanding dynamic worlds and enabling embodied interaction. While c…
What Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective
Jiazhen Huang, Xiao Chen, Zhiming Liu +3
Vision-Language Models (VLMs) such as CLIP have become a standard backbone for open-vocabulary recognition, yet their zero-shot predictions remain vulnerable to distribution shifts…
MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching
Shuzhao Xie, Junchen Ge, Weixiang Zhang +10
3D Gaussian Splatting (3DGS) achieves high-quality novel view synthesis with real-time rendering, but its storage cost remains prohibitive for practical deployment. Existing post-t…
Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D World
Yuzhi Huang, Kairun Wen, Rongxin Gao +14
Humans inhabit a physical 4D world where geometric structure and semantic content evolve over time, constituting a dynamic 4D reality (spatial with temporal dimension). While curre…
RoboStream: Weaving Spatio-Temporal Reasoning with Memory in Vision-Language Models for Robotics
Yuzhi Huang, Jie Wu, Weijue Bu +9
Enabling reliable long-horizon robotic manipulation is a crucial step toward open-world embodied intelligence. However, VLM-based planners treat each step as an isolated observatio…