Papers by Haoli Bai

9 papers
Visually Guided Generative Text-Layout Pre-training for Document Intelligence (2024.naacl-long)

Copied to clipboard

Challenge: Prior work shows that pre-training techniques can boost the performance of visual document understanding (VDU) . Xu et al., 2020;; Gu e t al, 2021;; Appalaraju e al. 2022)
Approach: They propose a visually guided generative text-layout pre-training method that optimizes hierarchical language and layout modeling objectives to generate interleaved text and layout sequences.
Outcome: The proposed model can process word-intensive documents of any length and achieves competitive performance over baselines on VDU tasks.
Structured Pruning for Efficient Generative Pre-trained Language Models (2023.findings-acl)

Copied to clipboard

Challenge: Large-scale generative Pre-trained Language Models (PLMs) are limited in their deployment in real-world applications.
Approach: They propose to prune the feed-forward networks of generative pre-trained language models to smaller widths without designing extra operators.
Outcome: The proposed method achieves 1.51x/6.96x inference speedup on GPU/CPU with 67% size reduction.
IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact (2024.findings-acl)

Copied to clipboard

Challenge: Existing quantization methods are compromising performance of large language models (LLMs) despite their high computational intensity, LLMs are still demanding intensive computation.
Approach: They propose to generate the KV cache of pivot tokens losslessly from the full-precision model.
Outcome: The proposed method generates the KV cache of pivot tokens losslessly from the full-precision model with no extra inference overhead.
Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding (2023.acl-long)

Copied to clipboard

Challenge: Existing solutions for visual document understanding lack granularity of document textlines.
Approach: They propose a supervised pre-training program to leverage structural knowledge nested in document textlines to achieve fine-grained alignment between visual regions and texts.
Outcome: The proposed system performs better on various VDU tasks in English and Chinese.
BinaryBERT: Pushing the Limit of BERT Quantization (2021.acl-long)

Copied to clipboard

Challenge: Recent pre-trained language models have achieved remarkable performance improvement in various tasks, but the improvement generally comes at the cost of increasing model size and computation.
Approach: They propose a binary quantization technique which initializes binaryBERT by splitting from a ternary network.
Outcome: The proposed model achieves state-of-the-art performance on the GLUE and SQUAD benchmarks while being 24x smaller.
MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks focus on evaluating single-round interactions, neglecting other critical aspects.
Approach: They propose a benchmark to evaluate full-duplex speech language models in multi-round settings . they segment continuous full-dual dialogues into discrete turns for evaluation .
Outcome: The proposed benchmark compared full-duplex speech language models with full-dual speech models . the results show that the models perform better in multi-round settings than standard models compared to benchmarks .
Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats (2026.acl-long)

Copied to clipboard

Challenge: Microscaling Floating-Point (MXFP) is a low-precision format for large language models (LLMs).
Approach: They conduct systematic evaluations of PTQ under Microscaling Floating-Point (MXFP) . they find that MXFP8 consistently achieves near-lossless performance .
Outcome: The proposed method achieves near-lossless performance while MXFP4 introduces substantial accuracy degradation and remains challenging.
Efficient Inference for Large Language Models –Algorithm, Model, and System (2025.emnlp-tutorials)

Copied to clipboard

Challenge: Inference of LLMs incurs high computational costs, memory access overhead, and memory usage, leading to inefficiencies in terms of latency, throughput, power consumption, and storage.
Approach: This tutorial introduces the basics of efficient inference for LLMs and explains how to diagnose efficiency bottlenecks for a given workload on specific hardware.
Outcome: The tutorial introduces the basic concepts of modern LLMs, software and hardware.
Faster and Better LLMs via Latency-Aware Test-Time Scaling (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing research has overlooked the efficiency of TTS from a latency-sensitive perspective.
Approach: They propose two approaches to achieve latency-optimal TTS by branch-wise parallelism and sequence-wise parallelism.
Outcome: The proposed approach achieves latency-optimal TTS for large models . branch-wise parallelism and sequence-wise parallelism are key approaches .

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