BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:What’s not an Autoregressive LLM? - Prof. Lingpeng Kong\, HKU
DTSTART:20250220T110000Z
DTEND:20250220T120000Z
UID:TALK226255@talks.cam.ac.uk
CONTACT:Shun Shao
DESCRIPTION:Abstract:\n\nThis talk explores alternatives to autoregressive
  Large Language Models (LLMs)\, with a particular focus on discrete diffus
 ion models. The presentation covers recent advances in non-autoregressive 
 approaches to text generation\, reasoning\, and planning tasks. Key develo
 pments discussed include Reparameterized Discrete Diffusion Models (RDMs)\
 , which show promising results in machine translation and error correction
 \, and applications of discrete diffusion to complex reasoning tasks like 
 countdown games\, Sudoku\, and chess. The talk also examines sequence-to-s
 equence text diffusion models\, as well as the novel Diffusion of Thoughts
  (DoTs) framework for chain-of-thought reasoning. These non-autoregressive
  approaches demonstrate competitive performance while offering potential a
 dvantages in terms of parallel processing and flexible generation patterns
  compared to traditional autoregressive models.\n\n\n\nA short CV:\n\nhttp
 s://ikekonglp.github.io/lingpenk_cv.pdf\n\n\n\nBio:\n\nLingpeng Kong is an
  assistant professor in the Department of Computer Science\, the Universit
 y of Hong Kong. From 2017-2020\, he was a (senior) research scientist at G
 oogle DeepMind. He received his Ph.D. in Artificial Intelligence from the 
 School of Computer Science\, Carnegie Mellon University. His work lies at 
 the intersection of natural language processing (NLP) and machine learning
  (ML)\, with a focus on representation learning\, structured prediction\, 
 and generative models. He has served as the (senior) area chairs for top N
 LP and ML conferences such as ICLR\, NeurIPS\, ICML\, EMNLP\, and NAACL. H
 e has also served as an action editor for Transactions on Machine Learning
  Research (TMLR) and ACL rolling review (ARR). His research was recognized
  with outstanding paper awards from ACL and EACL.\n\nA photo for the event
  web page:\nhttps://ikekonglp.github.io/me_new.jpeg
LOCATION:https://cam-ac-uk.zoom.us/j/97599459216?pwd=QTRsOWZCOXRTREVnbTJBd
 XVpOXFvdz09
END:VEVENT
END:VCALENDAR