Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Chain-of-Thought Shows the Path to a Tree: Realizing Branching Complexity
Debanjan Dutta, Anish Chakrabarty, Swagatam Das
Chain of Thought (CoT) lifts the expressive ceiling of bounded-depth Transformers, with characterizations tying the number of CoT steps to circuit complexity classes. What remains…
cs.LG2025
On the Existence of Universal Simulators of Attention
Debanjan Dutta, Anish Chakrabarty, Faizanuddin Ansari +1
Previous work on the learnability of transformers \textemdash\ focused primarily on examining their ability to approximate specific algorithmic patterns through training \textemdas…
cs.LG2023
HyPE-GT: where Graph Transformers meet Hyperbolic Positional Encodings
Kushal Bose, Swagatam Das
Graph Transformers (GTs) facilitate the comprehension of complex relationships on graph-structured data by leveraging self-attention of the possible pairs of nodes. The structural…