collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

Where Computation Lives Inside TabPFN: Causal Localisation of Attention Head Function

Atharva Gupta, Dhruv Kumar, Murari Mandal +1

We present the first causal mechanistic analysis of a tabular foundation model, investigating how TabPFN 2.5's feature wise attention heads distribute computation across layers. Us…

cs.LG2026

Mix, Don't Pick: Why Synthetic Corpus Composition Matters for Time Series Foundation Model Pretraining

Aaryan Nagpal, Debdeep Sanyal, Murari Mandal +2

Choosing the wrong synthetic generator for time-series foundation model pretraining is costly: under identical training budgets, the best and worst generators produce up to a $2\ti…

cs.LG2026

REGEN: Reference-Guided Synthetic Multivariate Time Series Generation for Forecasting

Moulik Gupta, Dhruv Kumar, Murari Mandal +1

Training robust multivariate time series forecasting models requires large, diverse corpora, yet many real-world domains provide only a handful of observed sequences. Existing gene…

cs.LG2026

Latent Phase-Shift Rollback: Inference-Time Error Correction via Residual Stream Monitoring and KV-Cache Steering

Manan Gupta, Dhruv Kumar

Large language models frequently commit unrecoverable reasoning errors mid-generation: once a wrong step is taken, subsequent tokens compound the mistake rather than correct it. We…

cs.LG2025

time2time: Causal Intervention in Hidden States to Simulate Rare Events in Time Series Foundation Models

Debdeep Sanyal, Aaryan Nagpal, Dhruv Kumar +2

While transformer-based foundation models excel at forecasting routine patterns, two questions remain: do they internalize semantic concepts such as market regimes, or merely fit c…