Skip to yearly menu bar Skip to main content


(7 events)   Timezone:  
Show all
The 2026 schedule is still incomplete
Toggle Poster Visibility
Oral
Thu Apr 23 11:15 AM -- 11:25 AM (PDT) None
High-dimensional Analysis of Synthetic Data Selection
In Oral Session 2B
Parham Rezaei · Filip Kovačević · Francesco Locatello · Marco Mondelli
[ OpenReview] 
Oral
Thu Apr 23 11:27 AM -- 11:37 AM (PDT) None
How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability
In Oral Session 2B
Shawn Im · Changdae Oh · Zhen Fang · Yixuan Li
[ OpenReview] 
Oral
Thu Apr 23 11:39 AM -- 11:49 AM (PDT) None
Sequences of Logits Reveal the Low Rank Structure of Language Models
In Oral Session 2B
Noah Golowich · Allen Liu · Abhishek Shetty
[ OpenReview] 
Oral
Thu Apr 23 11:51 AM -- 12:01 PM (PDT) None
Intrinsic Entropy of Context Length Scaling in LLMs
In Oral Session 2B
Jingzhe Shi · Qinwei (Martin) Ma · Hongyi Liu · Hang Zhao · Jenq-Neng Hwang · Lei Li
[ Slides]  [ OpenReview] 
Oral
Thu Apr 23 12:03 PM -- 12:13 PM (PDT) None
From Markov to Laplace: How Mamba In-Context Learns Markov Chains
In Oral Session 2B
Marco Bondaschi · Ashok Makkuva · Nived Rajaraman · Xiuying Wei · Razvan Pascanu · Caglar Gulcehre · Michael Gastpar
[ OpenReview] 
Oral
Thu Apr 23 12:15 PM -- 12:25 PM (PDT) None
The Coverage Principle: How Pre-Training Enables Post-Training
In Oral Session 2B
Fan Chen · Audrey Huang · Noah Golowich · Sadhika Malladi · Adam Block · Jordan Ash · Akshay Krishnamurthy · Dylan Foster
[ OpenReview] 
Oral
Thu Apr 23 12:27 PM -- 12:37 PM (PDT) None
Quantitative Bounds for Length Generalization in Transformers
In Oral Session 2B
Zachary Izzo · Eshaan Nichani · Jason Lee
[ OpenReview]