20 papers
Constraint-Anchored Reasoning Traces
Zehua Cheng, Wei Dai, Jiahao Sun
Autoregressive multimodal large language models (MLLMs) suffer from error snowballing: a single incorrect inference early in a chainof-thought (CoT) trace corrupts all downstream r…
Equivariant Neural Belief Propagation
Zehua Cheng, Wei Dai, Jiahao Sun
Probabilistic inference over spatially embedded variables requires beliefs that respect symmetry, yet existing equivariant networks produce only scalars and vectors -- not…
In-Context Graphical Inference
Zehua Cheng, Wei Dai, Jiahao Sun
Marginal inference in discrete graphical models forces a choice between exactness and scalability: exact algorithms are intractable for high-treewidth graphs, while iterative appro…
Imbuing Large Language Models with Bidirectional Logic for Robust Chain Repair
Zehua Cheng, Wei Dai, Jiahao Sun +1
Autoregressive chain-of-thought (CoT) reasoning in large language models (LLMs) is fundamentally forward-directed: each step conditions only on prior tokens. This unidirectional in…
Invariant Gradient Alignment for Robust Reasoning Distillation
Zehua Cheng, Wei Dai, Jiahao Sun
Large language models (LLMs) suffer from shortcut learning: they systematically fail on out-of-distribution (OOD) inputs whose semantic surface differs from training data, even whe…
CasualSynth: Generating Structurally Sound Synthetic Data
Zehua Cheng, Wei Dai, Jiahao Sun +1
Large Language Models (LLMs) generate realistic synthetic data but offer no guarantee that their outputs respect the causal mechanisms governing the target domain. We introduce Cau…