← Search

Tengyue Wang

2 accepted papers

2026

Beyond Fixed Biases: Decoding the Role of Reasoning Uncertainty in MLLM Modality Conflicts

ICML 2026poster

Multimodal Large Language Models (MLLMs) must resolve conflicts when modalities provide contradictory information, a process we term "modality following". We propose a framework that deconstructs this behavior into case-specific relative reasoning uncertainty and a model's stable inherent preference…

Cited by 0SourceScholar
2026

Beyond Isolation: A Unified Benchmark for General-Purpose Navigation

RSS 2026poster

The pursuit of general-purpose embodied agents is currently hindered by fragmented evaluation protocols that isolate navigation skills and fixate on specific robot morphologies. This disconnect fails to reflect real-world scenarios where agents must orchestrate diverse behaviors across varying physi…

Cited by 0SourceScholar