6 papers
Careful Judge: Safe and Efficient Human-AI Collaborative Decision Making
Chenyu Zhang, Rachel Luo, Boyi Li +3
In human-AI collaborative decision making, human review can prevent unsafe AI decisions, but each human judgment is costly. Treating human intervention after AI abstention as a one…
VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning
Zewei Zhou, Rachel Luo, Yulong Cao +10
Self-improving policies continually expose new failure patterns, changing what their judges must be able to verify. However, current fixed judges constrain both optimization feedba…
Coverage Aware Active Evaluation for Failure Discovery with Paired Systems
Anjali Parashar, Rachel Luo, Apoorva Sharma +6
Autonomous systems can fail in rare and heterogeneous ways, making real-world failure discovery difficult under limited testing budgets. Although cheaper proxies such as simulators…
X4Val: Learning Neural Surrogates for Variance-Reduced Policy Evaluation
Rachel Luo, Michael Watson, Apoorva Sharma +6
Rigorous evaluation of learning-based robotic systems is an essential prerequisite for deployment. However, real-world test data is expensive to gather; moreover, in a typical iter…
TGIF: Text-Guided Layer Fusion Mitigates Hallucination in Multimodal LLMs
Chenchen Lin, Sanbao Su, Rachel Luo +4
Multimodal large language models (MLLMs) typically rely on a single late-layer feature from a frozen vision encoder, leaving the encoder's rich hierarchy of visual cues under-utili…
Sim2Val: Leveraging Correlation Across Test Platforms for Variance-Reduced Metric Estimation
Rachel Luo, Heng Yang, Michael Watson +4
Learning-based robotic systems demand rigorous validation to assure reliable performance, but extensive real-world testing is often prohibitively expensive, and if conducted may st…