collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Structural Sensitivity in Compressed Transformers: Relative Error Propagation and Layer Removal

Abhinaba Basu, Kumkum Basu, Koushik Deb

Compressing transformer weights makes large language models cheaper to deploy. But each layer's compression introduces an error. These errors accumulate as the signal passes throug…

cs.LG2026

HubRouter: A Pluggable Sub-Quadratic Routing Primitive for Hybrid Sequence Models

Abhinaba Basu

We introduce HubRouter, a pluggable module that replaces O(n^2) attention layers with O(nM) hub-mediated routing, where M << n is a small number of learned hub tokens. We demonstra…

cs.LG2026

When Does Content-Based Routing Work? Representation Requirements for Selective Attention in Hybrid Sequence Models

Abhinaba Basu

We identify a routing paradox in hybrid sequence models: content-based routing - deciding which tokens deserve expensive attention - requires pairwise computation, and this require…

cs.LG2026

The Coordinate System Problem in Persistent Structural Memory for Neural Architectures

Abhinaba Basu

We introduce the Dual-View Pheromone Pathway Network (DPPN), an architecture that routes sparse attention through a persistent pheromone field over latent slot transitions, and use…

cs.LG2026

Budget-Sensitive Discovery Scoring: A Formally Verified Framework for Evaluating AI-Guided Scientific Selection

Abhinaba Basu, Pavan Chakraborty

Scientific discovery increasingly relies on AI systems to select candidates for expensive experimental validation, yet no principled, budget-aware evaluation framework exists for c…

cs.LG2026

Cross-Domain Uncertainty Quantification for Selective Prediction: A Comprehensive Bound Ablation with Transfer-Informed Betting

Abhinaba Basu

We present a comprehensive ablation of nine finite-sample bound families for selective prediction with risk control, combining concentration inequalities (Hoeffding, Empirical Bern…