collaborators

6 papers

cs.LG2026

Recursive Harness Self-Improvement

Hyunin Lee, Jinglue Xu, Jeffrey Seely +3

Under model--harness co-evolution, harnesses are not merely inference-time scaffolds but data-generating components whose execution traces can shape future foundation models. This…

cs.CV2026

Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning

Jiayi Lei, Yuandong Pu, Xingyu Han +8

Text-to-image (T2I) generation models have achieved remarkable progress in producing visually realistic images from natural language prompts. Yet it remains unclear whether their s…

cs.LG2026

How Good Can Linear Models Be for Time-Series Forecasting?

Lang Huang, Jinglue Xu, Luke Darlow

Time-series forecasting research has been moving steadily toward larger architectures, from specialized transformers to general-purpose foundation models, on the assumption that ca…

cs.LG2026

Sakana Fugu Technical Report

Yujin Tang, Edoardo Cetin, Jinglue Xu +11

The capabilities of frontier Large Language Models (LLMs) continue to advance, with different providers increasingly specializing in distinct domains. This raises a natural next ob…

cs.LG2026

Learning to Orchestrate Agents in Natural Language with the Conductor

Stefan Nielsen, Edoardo Cetin, Peter Schwendeman +3

Powerful large language models (LLMs) from different providers have been expensively trained and finetuned to specialize across varying domains. In this work, we introduce a new ki…

cs.LG2026

TRINITY: An Evolved LLM Coordinator

Jinglue Xu, Qi Sun, Peter Schwendeman +3

Combining diverse foundation models is promising, but weight-merging is limited by mismatched architectures and closed APIs. Trinity addresses this with a lightweight coordinator t…