collaborators

16 papers

cs.CR2026

The Usefulness Gap in Proof-of-Useful-Work: An Empirical Study of Pearl's cuPOW Protocol

Abhinaba Basu

Pearl, a Layer-1 blockchain with high-profile AI industry endorsements, markets its Proof-of-Useful-Work (PoUW) protocol as simultaneously securing the network and performing AI in…

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.CL2026

Transactional Attention: Semantic Sponsorship for KV-Cache Retention

Abhinaba Basu

At K=16 tokens (0.4% of a 4K context), every existing KV-cache compression method achieves 0% on credential retrieval. The failure mode is dormant tokens: credentials, API keys, an…

cs.CL2026

Measuring and curing reasoning rigidity: from decorative chain-of-thought to genuine faithfulness

Abhinaba Basu, Pavan Chakraborty

Language models increasingly show their work by writing step-by-step reasoning before answering. But are these steps genuinely used, or is the answer rigid - fixed before reasoning…