Lexsi Labs

About Us

Research Papers - Lexsi Labs

Contact Us - Lexsi Labs

AGI Talks: A night with AI researchers (India AI Impact Summit) · Luma

[2411.12643] DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models

[2502.03014] xai_evals : A Framework for Evaluating Post-Hoc Local Explanation Methods

[2507.08330] Interpretability-Aware Pruning for Efficient Medical Image Analysis

[2509.08592] Interpretability as Alignment: Making Internal Understanding a Design Principle

TabTune Library

Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning

Orion-Bix: Bi-Axial Attention for Tabular In-Context Learning

Exploring Fine-Tuning for Tabular Foundation Models

Beyond KL Divergence: Policy Optimization with Flexible Bregman Divergences for LLM Reasoning

Beyond Uniform Credit: Causal Credit Assignment for Policy Optimization

AlignTune Library

C-ΔΘ: Circuit-Restricted Weight Arithmetic for Selective Refusal