Papers by Xinyu Fu

6 papers
Reasoning Like Program Executors (2022.emnlp-main)

Copied to clipboard

Challenge: Existing language models are inadequate in reasoning, according to studies . a new reasoning pre-training paradigm is based on pretraining language models with programs .
Approach: They propose a reasoning pre-training paradigm that empowers language models to harvest reasoning knowledge possessed by program executors.
Outcome: The proposed reasoning pre-training paradigm can boost models' reasoning skills . it can be instantiated by different kinds of program executors and run on a single database .
SCoder: Progressive Self-Distillation for Bootstrapping Small-Scale Data Synthesizers to Empower Code LLMs (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing code large language models rely on large-scale instruction data distilled from proprietary LLMs for fine-tuning, which typically incurs high costs.
Approach: They propose an iterative self-distillation approach to bootstrap small-scale LLMs . they use large-scale instruction data distilled from proprietary LLM for fine-tuning .
Outcome: The proposed method reduces reliance on proprietary LLMs and minimizes costs.
MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to visual chain-of-thought are limited by external tools or fail to generate high-fidelity diagrams.
Approach: They propose a framework to enable large multimodal models with VCoT capabilities . they pre-train a model on a 15.2M-pair corpus and teach it how to leverage visual aids .
Outcome: The proposed framework unlocks complex, human-like visual reasoning in large language models . it pre-trains the model on a 15.2M-pair corpus and fine-tunes it on MathCanvas-Instruct .
Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment (P18-1)

Copied to clipboard

Challenge: Existing approaches to classify human affect and subjective information from multiple data sources are limited by the lack of high-level feature associations.
Approach: They propose a hierarchical multimodal architecture with attention and word-level fusion to classify utterance-level sentiment and emotion from text and audio data.
Outcome: The proposed model outperforms state-of-the-art approaches on published datasets and visualizes and interprets synchronized attention over modalities.
Hybrid Attention based Multimodal Network for Spoken Language Classification (C18-1)

Copied to clipboard

Challenge: Using linguistic content and vocal characteristics for multimodal deep learning is difficult for computers to interpret human meaning .
Approach: They propose a deep multimodal network with feature attention and modality attention to classify utterance-level speech data.
Outcome: The proposed system achieves state-of-the-art or competitive results on three published multimodal datasets.
NavA3: Understanding Any Instruction, Navigating Anywhere, Finding Anything (2026.acl-long)

Copied to clipboard

Challenge: Existing embodied navigation methods struggle with such tasks due to their limitations in comprehending high-level human instructions and localizing objects with an open vocabulary.
Approach: They propose a hierarchical framework for long-horizon navigation that integrates human instructions with 3D scene views.
Outcome: The proposed model achieves SOTA results and can complete long-horizon navigation tasks across different robot embodiments in real-world environments.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations