5 papers
Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations
Bryce Grant, Peng Wang
Existing interpretability tools do not test whether a representation keeps the same content when only the phrasing changes. We treat each paraphrase pair as a local witness that tw…
Sequential Planning via Anchored Robotic Keypoints
Bryce Grant, Aryeh Rothenberg, Logan Senning +3
Changes in a robot's observations do not automatically imply changes in the task it is solving, but language-conditioned manipulation systems often fail to separate the two. If an…
TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization
Bryce Grant, Aryeh Rothenberg, Atri Banerjee +1
Localizing objects and parts from natural language in 3D space is essential for robotics, AR, and embodied AI, yet existing methods face a trade-off between the accuracy and geomet…
VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latents
Feng Wang, Yichun Shi, Ceyuan Yang +4
This work presents VTok, a unified video tokenization framework that can be used for both generation and understanding tasks. Unlike the leading vision-language systems that tokeni…
Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane
Haoyu Liu, Sucheng Ren, Tingyu Zhu +5
Rotary Position Embedding (RoPE) is the de facto positional encoding in large language models due to its ability to encode relative positions and support length extrapolation. When…