22 papers
Environment-free Synthetic Data Generation for API-Calling Agents
Seanie Lee, Sanjoy Chowdhury, Chao Jiang +5
Training API-calling large language model (LLM) agents demands massive amounts of high-quality trajectories. However, collecting such data at scale typically requires fully impleme…
RayRoPE: Projective Ray Positional Encoding for Multi-view Attention
Yu Wu, Minsik Jeon, Jen-Hao Rick Chang +2
We study positional encodings for multi-view transformers that process tokens from a set of posed input images, and seek a mechanism that encodes patches uniquely, allows SE(3)-inv…
TrajTok: Learning Trajectory Tokens enables better Video Understanding
Chenhao Zheng, Jieyu Zhang, Jianing Zhang +6
Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video efficiency and scalability. While…
Velox: Learning Representations of 4D Geometry and Appearance
Anagh Malik, Dorian Chan, Xiaoming Zhao +3
We introduce a framework for learning latent representations of 4D objects which are descriptive, faithfully capturing object geometry and appearance; compressive, aiding in downst…
VSAS-Bench: Real-Time Evaluation of Visual Streaming Assistant Models
Pavan Kumar Anasosalu Vasu, Cem Koc, Fartash Faghri +6
Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core mechanism for real-time vis…
Pretraining with hierarchical memories: separating long-tail and common knowledge
Hadi Pouransari, David Grangier, C Thomas +2
The impressive performance gains of modern language models currently rely on scaling parameters: larger models store more world knowledge and reason better. Yet compressing all wor…