5 papers
Parameter-free Adaptive Sparse Attention via Compression-Based Content Selection
Debarshi Kundu, Swaroop Ghosh, Vasant Honavar
Data-adaptive sparse attention masks substantially outperform fixed patterns (e.g., BigBird and Longformer) and can even exceed dense attention on long sequences. Existing adaptive…
Projection-Free Transformers via Gaussian Kernel Attention
Debarshi Kundu, Archisman Ghosh, Swaroop Ghosh +1
Self-attention in Transformers is typically implemented as , where , , and are learned linear projections of the input…
Capturing Quantum Snapshots from a Single Copy via Mid-Circuit Measurement and Dynamic Circuit
Debarshi Kundu, Avimita Chatterjee, Archisman Ghosh +1
We propose Quantum Snapshot with Dynamic Circuit (QSDC), a hardware-agnostic, learning-driven framework for capturing quantum snapshots: non-destructive estimates of quantum states…
Guess, SWAP, Repeat : Capturing Quantum Snapshots in Classical Memory
Debarshi Kundu, Avimita Chatterjee, Swaroop Ghosh
We introduce a novel technique that enables observation of quantum states without direct measurement, preserving them for reuse. Our method allows multiple quantum states to be obs…
SciFaultyQA: Benchmarking LLMs on Faulty Science Question Detection with a GAN-Inspired Approach to Synthetic Dataset Generation
Debarshi Kundu
Consider the problem: ``If one man and one woman can produce one child in one year, how many children will be produced by one woman and three men in 0.5 years?" Current large langu…