Articulated 3D Scene Graphs for Open-World Mobile Manipulation
[Submitted on 18 Feb 2026 (v1), last revised 12 Oct 2026 (this version, v2)] View PDF HTML (experimental) Abstract:Semantic scene…
Author: admin
CAPTOR: a vision-language foundation model for Chest-Abdomen-Pelvis Oncologic CT
[Submitted on 9 Oct 2026] View PDF HTML (experimental) Abstract:Purpose : To develop and evaluate CAPTOR, a deep-learning vision-language foundation…
TrajCFG: Token-Wise Classifier-Free Guidance via Denoising Trajectory Feedback
[Submitted on 9 Oct 2026] View PDF HTML (experimental) Abstract:Classifier-free guidance (CFG) typically applies a shared scale to all latent…
Forecasting Without Full Identification: Reliability and Computational Cost in Clot-Growth Simulation
[Submitted on 8 Aug 2026 (v1), last revised 13 Oct 2026 (this version, v2)] View PDF HTML (experimental) Abstract:We forecast…
HIMMEL: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video Understanding
[Submitted on 4 May 2026 (v1), last revised 10 Oct 2026 (this version, v2)] Authors:Haopeng Jin, Wenlong Zhao, Tao Yu,…
Is the Future Predictable? Modeling Future Predictability for Reliable Temporal Reasoning
[Submitted on 8 Oct 2026] View PDF HTML (experimental) Abstract:Large language models (LLMs) remain unreliable when reasoning about the future.…
From Parameters to Behaviors: A Survey of Model Fusion for Large Language Models
[Submitted on 17 Sep 2026 (v1), last revised 10 Oct 2026 (this version, v2)] Authors:Shuo Cai, Yanggan Gu, Zihao Wang,…
Multimodal Co-Generation With Continuous Bitstream Diffusion
[Submitted on 9 Oct 2026] View PDF HTML (experimental) Abstract:We show that continuous bitstream diffusion (CoBit), originally developed for language…
GeoMotionGPT: Geometry-Aligned Motion Understanding with Large Language Models
[Submitted on 12 Jan 2026 (v1), last revised 12 Oct 2026 (this version, v5)] View PDF Abstract:Discrete motion tokenization has…
Latent World Action Model for GUI Agents
[Submitted on 9 Oct 2026] View PDF HTML (experimental) Abstract:Pixel-space world models have recently emerged as a promising approach for…