3 papers
cs.LG2026
Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal Models
Abinav Rao, Sujan Rachuri
Unified multimodal models share a language model backbone for both understanding and generating images. Can DPO align both capabilities simultaneously? We present the first systema…
cs.CL2026
Correct Chains, Wrong Answers: Dissociating Reasoning from Output in LLM Logic
Abinav Rao, Sujan Rachuri, Nikhil Vemuri
LLMs can execute every step of chain-of-thought reasoning correctly and still produce wrong final answers. We introduce the Novel Operator Test, a benchmark that separates operator…
cs.LG2026
Graph Hopfield Networks: Energy-Based Node Classification with Associative Memory
Abinav Rao, Alex Wa, Rishi Athavale
We introduce Graph Hopfield Networks, whose energy function couples associative memory retrieval with graph Laplacian smoothing for node classification. Gradient descent on this jo…