The 4th TTIC Student workshop will take place on February 21, 2020 on the 5th floor at TTIC. Talks will be in room 526. Posters and refreshments will be in the 5th floor common area. There will be 15/25-minute talks, plus 5 minutes for questions and turnover. There will be awards for the best poster and best talk.

Organizing Committee: Sudarshan Babu, Freda Shi, Karen Livescu, Madhur Tulsiani, Erica Cocom, Chrissy Novak
Talk Award Committee: Pritish Kamath, Sepideh Mahabadi, Sam Wiseman
Poster Award Committee: Arturs Backurs, Mrinmaya Sachan

Schedule

09:00-09:20	Breakfast Refreshments
09:20-09:30	Opening Remarks
09:30-10:30	Talk Session 1 (Chair: Sepideh Mahabadi)
09:30-10:00	Fernando Granha Jeronimo	Decoding Binary Codes
10:00-10:30	Jafar Jafarov	Asymmetric Correlation Clustering
10:30-11:15	Poster Session 1
	Tri Huynh	Multigrid Neural Memory
	Ruotian Luo	A Better Variant for Self Critical Sequence Training
	Kumar Kshitij Patel	Communication trade-offs for Local-SGD with large step size
	Pedro Savarese	Domain-Independent Dominance of Adaptive Methods
	Freda Shi	On the surprising effectiveness of few-shot constituency parsing
	Shubham Toshniwal	Memory Models for Coreference Resolution
	Takuma Yoneda	Pow-Wow: A Dataset and Study on Collaborative Communication in Pommerman
11:15-12:15	Keynote Talk: Hao Tang (TTIC PhD 2017)	Real-Time Speech Processing
12:15-13:15	Lunch
13:15-14:15	Talk Session 2 (Chair: Pritish Kamath)
13:15-13:35	Han Shao	Explore Smarter, Exploit More: Structure Adaptive Algorithms for Stochastic Bandits
13:35-13:55	Ruotian Luo	Pixel Consensus Voting for Panoptic Segmentation
13:55-14:15	Omar Montasser	Approximate is Good Enough: Probabilistic Variants of Dimensional and Margin Complexity
14:15-15:00	Poster Session 2 (Same Posters)
15:00-15:20	Coffee Break
15:20-16:20	Talk Session 3 (Chair: Sam Wiseman)
15:20-15:40	Jiading Fang	Self Supervised Dense Correspondence Learning
15:40-16:00	Davis Yoshida	Post-hoc Augmentation of Pre-trained Transformer Context Size
16:00-16:20	Shuning Jin	Discrete Latent Variable Representations for Low-Resource Text Classification
16:20-16:30	Break
16:30-16:40	Awards