Papers by Eric Xia
Linear Relational Decoding of Morphology in Language Models (2025.naacl-srw)
Copied to clipboard
| Challenge: | Recent work has shown that affine transformations on subject representations can faithfully approximate model outputs for certain subject-object relations. |
| Approach: | They propose to use affine transformations to adapt the Bigger Analogy Test Set to test faithfulness of morphological relations. |
| Outcome: | The proposed method achieves 90% faithfulness on morphological relations, with similar findings across languages and models. |
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Speculative decoding (SD) has proven to be effective for autoregressive generation in large language models (LLMs), however its application to vision-language models (VLMs) remains relatively unexplored. |
| Approach: | They propose a Speculative Decoding framework for vision-language models that integrates a neural architecture search framework and target-aware supernet training to identify optimal interaction strategies. |
| Outcome: | DREAM-S achieves 3.85 speedup compared to baselines on well-established vision-language models. |