Papers by Bin Fu

7 papers
BeSimulator: A Large Language Model Powered Text-based Behavior Simulator (2025.emnlp-main)

Copied to clipboard

Challenge: Existing robot simulators focus on physical process modeling and realistic rendering, resulting in high computational costs and limited adaptability.
Approach: They propose a modular and novel LLM-powered framework to analyze and validate robot behaviors in text-based environments.
Outcome: The proposed framework can generalize across scenarios and achieve long-horizon complex simulation.
LARA: Linguistic-Adaptive Retrieval-Augmentation for Multi-Turn Intent Classification (2024.emnlp-industry)

Copied to clipboard

Challenge: Multi-turn intent classification is challenging due to the complexity and evolving nature of conversational contexts . lack of data on multi-turn datasets makes it difficult to collect multi-turned datasets a challenge .
Approach: They propose a framework for multi-turn intent classification that integrates a retrieval-augmented mechanism with a fine-tuned smaller model.
Outcome: The proposed framework improves accuracy on multi-turn intent classification tasks across six languages.
Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods (2026.acl-long)

Copied to clipboard

Challenge: Recent efforts to accelerate inference in Multimodal Large Language Models have focused on visual token compression.
Approach: They propose a framework that leverages downsampling as a discriminator to denoise existing benchmarks.
Outcome: The proposed evaluation framework leverages downsampling as a discriminator to denoise existing benchmarks.
Enhancing Unsupervised Sentence Embeddings via Knowledge-Driven Data Augmentation and Gaussian-Decayed Contrastive Learning (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for data augmentation neglect fine-grained knowledge, such as entities and quantities, leading to insufficient diversity and high data noise.
Approach: They propose a pipeline-based data augmentation method via LLMs and introduce the Gaussian-decayed gradient-assisted Contrastive Sentence Embedding (GCSE) model to enhance unsupervised sentence embeddings.
Outcome: The proposed method achieves state-of-the-art performance in semantic textual similarity tasks using fewer data samples and smaller LLMs.
Improving Low-Resource Sequence Labeling with Knowledge Fusion and Contextual Label Explanations (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to sequence labeling are limited due to the scarcity of domain-specific data and semantic distribution biases in domain-based contexts.
Approach: They propose a framework that integrates an LLM-based knowledge enhancement workflow with a span-based Knowledge Fusion for Rich and Efficient Extraction model.
Outcome: The proposed model achieves state-of-the-art performance on multiple domain-specific sequence labeling datasets and is highly efficient.
Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data (2024.findings-acl)

Copied to clipboard

Challenge: OpenAI's GPT-4 has demonstrated remarkable multimodal capabilities, but specific mechanics of GPT4 remain unknown.
Approach: They propose a data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning.
Outcome: The proposed method improves on ten commonly assessed models and provides greater flexibility compared to existing methods.
Text Editing as Imitation Game (2022.findings-emnlp)

Copied to clipboard

Challenge: Text editing is an important domain of processing tasks to edit the text in a localized fashion, such as text simplification.
Approach: They propose a nonautoregressive decoder for state-to-action demonstrations that parallels the decoding while retaining the dependencies between tokens.
Outcome: The proposed model outperforms the autoregressive baselines on a suite of Arithmetic Equation benchmarks in terms of performance, efficiency, and robustness.

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