collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2026

Spectral Conditioning of Attention Improves Transformer Performance

Hemanth Saratchandran, Simon Lucey

We present a theoretical analysis of the Jacobian of an attention block within a transformer, showing that it is governed by the query, key, and value projections that define the a…

cs.LG2026

The Inlet Rank Collapse in Implicit Neural Representations: Diagnosis and Unified Remedy

Jianqiao Zheng, Hemanth Saratchandran, Simon Lucey

Implicit Neural Representations (INRs) have revolutionized continuous signal modeling, yet they struggle to recover fine-grained details within finite training budgets. While empir…

cs.LG2025

From Tables to Signals: Revealing Spectral Adaptivity in TabPFN

Jianqiao Zheng, Cameron Gordon, Yiping Ji +2

Task-agnostic tabular foundation models such as TabPFN have achieved impressive performance on tabular learning tasks, yet the origins of their inductive biases remain poorly under…

cs.LG2025

Cutting the Skip: Training Residual-Free Transformers

Yiping Ji, James Martens, Jianqiao Zheng +5

Transformers have achieved remarkable success across a wide range of applications, a feat often attributed to their scalability. Yet training them without skip (residual) connectio…

cs.LG2025

Stable Forgetting: Bounded Parameter-Efficient Unlearning in Foundation Models

Arpit Garg, Hemanth Saratchandran, Ravi Garg +1

Machine unlearning in foundation models (e.g., language and vision transformers) is essential for privacy and safety; however, existing approaches are unstable and unreliable. A wi…

cs.LG2025

Leaner Transformers: More Heads, Less Depth

Hemanth Saratchandran, Damien Teney, Simon Lucey

Transformers have reshaped machine learning by utilizing attention mechanisms to capture complex patterns in large datasets, leading to significant improvements in performance. Thi…