7 papers
RoboShape: Information-Theoretic Point Cloud Representations for Privacy-Aware Robot Perception
Oguzhan Baser, Mirac Sozen, Kaan Kale +2
With the increased adoption of robotic agents operating in human environments by scanning and sharing 3D representations (e.g., for fleet learning, cloud-based planning, or collabo…
MultiTok: Variable-Length Tokenization for Efficient LLMs Adapted from LZW Compression
Noel Elias, Homa Esfahanizadeh, Kaan Kale +2
Large language models have drastically changed the prospects of AI by introducing technologies for more complex natural language processing. However, current methodologies to train…
WavShape: Information-Theoretic Speech Representation Learning for Fair and Privacy-Aware Audio Processing
Oguzhan Baser, Ahmet Ege Tanriverdi, Kaan Kale +2
Speech embeddings often retain sensitive attributes such as speaker identity, accent, or demographic information, posing risks in biased model training and privacy leakage. We prop…
PhonemeFake: Redefining Deepfake Realism with Language-Driven Segmental Manipulation and Adaptive Bilevel Detection
Oguzhan Baser, Ahmet Ege Tanriverdi, Sriram Vishwanath +1
Deepfake (DF) attacks pose a growing threat as generative models become increasingly advanced. However, our study reveals that existing DF datasets fail to deceive human perception…
Learnings from Scaling Visual Tokenizers for Reconstruction and Generation
Philippe Hansen-Estruch, David Yan, Ching-Yao Chung +7
Visual tokenization via auto-encoding empowers state-of-the-art image and video generative models by compressing pixels into a latent space. Although scaling Transformer-based gene…
OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset
Allen Roush, Yusuf Shabazz, Arvind Balaji +7
We introduce OpenDebateEvidence, a comprehensive dataset for argument mining and summarization sourced from the American Competitive Debate community. This dataset includes over 3.…