From the 1 of 5 linked papers with an AI index.
5 papers
Chaos Is a LADDER: Domain Generalization Beyond Invariance via Reweighting
Yuhang Jiang, Fengchuan Zhang, Sanguo Zhang +1
The paper introduces LADDER, a method for domain generalization that learns separate causal and style representations, freezes them, and reweights source-specific classifiers at in…
A Circuit, Not The Circuit: Non-Unique Causal Localisation of the Mamba-2 State Sink
Yuhang Jiang, Bowen Zhang
Mechanistic interpretability routinely reads a probe and labels its top-activating units as the circuit executing the computation. We test the move in Mamba, on the state sink: the…
Task Structure Reverses Layerwise State Encoding in Sequence Models
Yuhang Jiang
Mechanistic studies of sequence models often treat layerwise state encodings as architectural traits: recurrent models concentrate readable state, attention-based models distribute…
PInVerify: An Offline Embodied Benchmark for Active Instance Verification
Yuhang Jiang
Embodied agents have made strong progress in navigating to target objects, but reaching the goal vicinity does not guarantee that the agent has found the correct instance: subtle a…
Can ChatGPT Overcome Behavioral Biases in the Financial Sector? Classify-and-Rethink: Multi-Step Zero-Shot Reasoning in the Gold Investment
Shuoling Liu, Gaoguo Jia, Yuhang Jiang +2
Large Language Models (LLMs) have achieved remarkable success recently, displaying exceptional capabilities in creating understandable and organized text. These LLMs have been util…