Ximing Lu

ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge

Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

The Invisible Leash? Why RLVR May or May Not Escape Its Origin

DLER: Doing Length pEnalty Right — Incentivizing More Intelligence per Token via Reinforcement Learning

DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Tree-based Search

BroRL: Scaling Reinforcement Learning via Broadened Exploration

Long Grounded Thoughts: Distilling Compositional Visual Reasoning Chains at Scale

TinyEye: Sharpening Visual Reasoning of Tiny Models with Offline Policy Optimization

iGRPO: Self‑Feedback–Driven LLM Reasoning

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text

Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers

HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Interactive AI Agents

The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage

HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions

CertainlyUncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness