HuangLab Test

non-profit

AI & ML interests

None defined yet.

Recent Activity

Benjamin-eecs authored a paper 4 days ago

AutoEnvScaling: Automating the Data Flywheel with Terminal Agents

Benjamin-eecs authored a paper 8 days ago

Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries

Benjamin-eecs authored a paper 8 days ago

Learning Stateful Predictive Knowledge From Experience

View all activity

authored a paper 4 days ago

AutoEnvScaling: Automating the Data Flywheel with Terminal Agents

Paper • 2610.14163 • Published 10 days ago • 10

authored 2 papers 8 days ago

Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries

Paper • 2610.06269 • Published 14 days ago

Learning Stateful Predictive Knowledge From Experience

Paper • 2607.28638 • Published May 19 • 1

authored a paper 16 days ago

ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research

Paper • 2610.02202 • Published 18 days ago • 16

authored a paper about 2 months ago

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Paper • 2608.19197 • Published Aug 19 • 58

authored a paper 3 months ago

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published Jul 26 • 97

authored a paper 4 months ago

Agents' Last Exam

Paper • 2606.05405 • Published Jun 3 • 394

authored a paper 6 months ago

From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space

Paper • 2604.14142 • Published Apr 15 • 30

authored a paper 7 months ago

Reasoning over mathematical objects: on-policy reward modeling and test time aggregation

Paper • 2603.18886 • Published Mar 19 • 6

authored a paper 7 months ago

Agentic Critical Training

Paper • 2603.08706 • Published Mar 9 • 14

authored a paper 11 months ago

Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following

Paper • 2511.21662 • Published Nov 26, 2025 • 12

authored a paper 12 months ago

Scaling Agent Learning via Experience Synthesis

Paper • 2511.03773 • Published Nov 5, 2025 • 83

authored a paper 12 months ago

ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation

Paper • 2511.01163 • Published Nov 3, 2025 • 31

authored a paper 12 months ago

SPICE: Self-Play In Corpus Environments Improves Reasoning

Paper • 2510.24684 • Published Oct 28, 2025 • 18

authored 2 papers about 1 year ago

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

Paper • 2510.08697 • Published Oct 9, 2025 • 41

Agent Learning via Early Experience

Paper • 2510.08558 • Published Oct 9, 2025 • 259

authored 2 papers about 1 year ago

Agent Learning via Early Experience

Paper • 2510.08558 • Published Oct 9, 2025 • 259

LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training

Paper • 2509.23661 • Published Sep 28, 2025 • 53

authored 2 papers about 1 year ago

GEM: A Gym for Agentic LLMs

Paper • 2510.01051 • Published Oct 1, 2025 • 92

The Era of Real-World Human Interaction: RL from User Conversations

Paper • 2509.25137 • Published Sep 29, 2025 • 19