Rajat Sen

Zero-shot in-context inference trained strictly on synthetic causal graphs can outperform fully tuned AutoML pipelines across diverse real-world tabular benchmarks.

Frozen tabular foundation models can dominate competitive ML benchmarks without parameter updates if an LLM agent is tasked strictly with evolving the semantic data pipeline around them.

Simple ensemble methods leveraging rich textual context can outperform state-of-the-art multimodal forecasting approaches on a new benchmark, TimesX, revealing hidden vulnerabilities in existing evaluations.