5 papers
Textual Planning with Explicit Latent Transitions
Eliezer Shlomi, Ido Levy, Eilam Shapira +6
Planning with LLMs is bottlenecked by token-by-token generation and repeated full forward passes, making multi-step lookahead and rollout-based search expensive in latency and comp…
Donors and Recipients: On Asymmetric Transfer Across Tasks and Languages with Parameter-Efficient Fine-Tuning
Kajetan Dymkiewicz, Ivan Vulic, Helen Yannakoudakis +3
Large language models (LLMs) perform strongly across tasks and languages, yet how improvements in one task or language affect other tasks and languages remains poorly understood. W…
From Benchmarks to Business Impact: Deploying IBM Generalist Agent in Enterprise Production
Segev Shlomov, Alon Oved, Sami Marreed +9
Agents are rapidly advancing in automating digital work, but enterprises face a harder challenge: moving beyond prototypes to deployed systems that deliver measurable business valu…
TabSTAR: A Tabular Foundation Model for Tabular Data with Text Fields
Alan Arazi, Eilam Shapira, Roi Reichart
While deep learning has achieved remarkable success across many domains, it has historically underperformed on tabular learning tasks, which remain dominated by gradient boosting d…
Fairness under Competition
Ronen Gradwohl, Eilam Shapira, Moshe Tennenholtz
Algorithmic fairness has emerged as a central issue in ML, and it has become standard practice to adjust ML algorithms so that they will satisfy fairness requirements such as Equal…