Compressing human text.
- Christian Steinruecken
I will present a new data compression algorithm that compresses human text more effectively than all current variants of PPM, CTW, DMC, LZ (Lempel-Ziv), LZMA, CSE and BWT. It uses a hierarchical non-parametric sequence model and online gradient optimisation.
-
-
Sebastian Nowozin
Partner Research Manager
-
-
Watch Next
-
Multimodal & Embodied Intelligence (S2)
- Rajiv Ratn Shah,
- Tanuja Ganu,
- Mercy Ranjit
-
Multimodal & Embodied Intelligence (S1), Panel on Multimodal AI: Progress, Pitfalls, Possibilities
- Madhava Krishna,
- Sriram Ganapathy,
- Somak Aditya
-
Session on Compute & Trust (Security)
- Krishna Pillutla,
- Danish Pruthi
-
Panel: Is Retrieval Relevant in the Age of Reasoning?
- Himanshu Tyagi,
- Ravishankar Krishnaswamy,
- Mrinal Kanti Das
-
Session on Reasoning
- Hongxiang Fan,
- Nagarajan Natarajan
-
Human-Centered AI: Design, Deployment & Healthcare
- Manik Gupta,
- Anirudha Joshi,
- Aaditeshwar Seth
-
-
-
-
Beyond Swahili: Designing Inclusive AI for Bantu Languages
- Alfred Malengo Kondoro
