8 papers
OpenForgeRL: Train Harness-native Agents in Any Environment
Xiao Yu, Baolin Peng, Ruize Xu +7
Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to external systems. While power…
HPD-Parsing: Hierarchical Parallel Document Parsing
Shu Wei, Jingjing Wu, Lingshu Zhang +10
Efficient teamwork typically combines global coordination with parallel execution, a principle not yet fully reflected in unified Vision-Language Model (VLM)-based document parsers…
Generating Risky Samples with Conformity Constraints via Diffusion Models
Han Yu, Hao Zou, Xingxuan Zhang +4
Although neural networks achieve promising performance in many tasks, they may still fail when encountering some examples and bring about risks to applications. To discover risky s…
Error Slice Discovery via Manifold Compactness
Han Yu, Hao Zou, Jiashuo Liu +4
Despite the great performance of deep learning models in many areas, they still make mistakes and underperform on certain subsets of data, i.e. error slices. Given a trained model,…
LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence
Xingxuan Zhang, Gang Ren, Han Yu +35
We argue that progress toward general intelligence requires complementary foundation models grounded in language, the physical world, and structured data. This report presents Limi…
Rethinking Reasoning with MDLMs: Early Exits, Post-hoc Reasoning, and Beyond
Zachary Horvitz, Raghav Singhal, Hao Zou +4
The reasoning paradigm, where language models reason before answering, has enabled breakthroughs on tasks such as mathematical problem-solving. While current tooling for reasoning…