Papers by Ziyue Liu

22 papers
VoxpopuliTTS: a large-scale multilingual TTS corpus for zero-shot speech generation (2025.coling-main)

Copied to clipboard

Challenge: Existing multilingual TTS datasets are limited in speech generation fields due to lack of quality data.
Approach: They propose to use 30,000 hours of high-quality speech data across 3 languages . they filter out low-quality text-text pairs and concatenate short transcripts .
Outcome: The proposed dataset comprises 30,000 hours of high-quality speech data, across 3 languages with multiple speakers and styles, suitable for various speech tasks such as TTS and ASR.
Model Composition for Multimodal Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing methods for creating versatile MLLMs rely on joint training with paired instruction data, which is resource-intensive and challenging to extend to new modalities.
Approach: They propose a new paradigm for multimodal large language models by reusing modality encoders and merging LLM parameters.
Outcome: The proposed model retains the modal understanding capabilities of each original model.
Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage (2026.findings-acl)

Copied to clipboard

Challenge: Prior work typically decomposes inference into prefill and decode stages, with the decode stage dominating total latency.
Approach: They propose an algorithm that detects threshold where information loss exceeds information gain during sparse decoding to reduce token consumption by up to 90% and a marginal accuracy degradation of less than 2%.
Outcome: The proposed algorithm reduces token consumption by 90% with a marginal accuracy degradation of less than 2% across reasoning-intensive benchmarks.
Enabling Stroke-Level Structural Analysis of Hieroglyphic Scripts without Language-Specific Priors (2026.findings-acl)

Copied to clipboard

Challenge: Existing structural analysis methods for hieroglyphic scripts are script-specific and labor-intensive.
Approach: They propose a hieroglyphic Stroke Analyzer framework that captures character-internal structures and semantics without handcrafted data.
Outcome: The proposed framework captures character-internal structures and semantics without priors . it can be used to generalize hieroglyphic scripts across languages .
ActiView: Evaluating Active Perception Ability for Multimodal Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for evaluating MLLMs have not addressed active perception . a novel benchmark is proposed to evaluate active perception in ML models .
Approach: They propose a benchmark to evaluate active perception in Multimodal Large Language Models . they restrict the perceptual field of a model and require it to actively zoom or shift it .
Outcome: The proposed benchmark focuses on a specialized form of Visual Question Answering (VQA) that eases and quantifies the evaluation yet challenging for existing MLLMs.
Graph-Structured Speculative Decoding (2024.findings-acl)

Copied to clipboard

Challenge: Speculative decoding is a promising technique to accelerate the inference of Large Language Models.
Approach: They propose a method that uses a token graph to record multiple sequence hypotheses within a single draft stage.
Outcome: The proposed method significantly accelerates the inference of Large Language Models (LLMs) it allows the LLM to choose from and select the longest sequence that meets its standards.
Make-A-Voice: Revisiting Voice Large Language Models as Scalable Multilingual and Multitask Learners (2024.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have been used for general-purpose interfaces across multiple tasks and languages.
Approach: They propose to use large language models as a general-purpose interface across multiple tasks and languages.
Outcome: The proposed model performs better on 200K hours of 6-language data for voice generation applications.
Perspective Transition of Large Language Models for Solving Subjective Tasks (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have revolutionized the field of natural language processing . performance of LLMs on subjective tasks is limited, authors say .
Approach: They propose a method that allows LLMs to select between direct, role, and third-person perspectives for best way to solve corresponding subjective problem.
Outcome: The proposed method outperforms widely used single fixed perspective based methods on 12 subjective tasks.
Browse and Concentrate: Comprehending Multimodal Content via Prior-LLM Context Fusion (2024.acl-long)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) lack understanding of multi-image and interleaved inputs due to the visual features encoded by frozen encoders before being fed into the LLM backbone.
Approach: They propose a two phase paradigm to enable in-depth multimodal context fusion prior to feeding the features into LLMs.
Outcome: The proposed paradigm boosts the performance on 7 multi-image scenarios, contributing to increments on average accuracy by 2.13% and 7.60% against strong MLLMs baselines with 3B and 11B LLMs, respectively.
QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are quantized to lower precision to reduce memory cost and latency in inference.
Approach: They propose a quantized zeroth-order framework for fine-tuning Large Language Models (LLMs) using low-precision forward passes.
Outcome: The proposed method achieves comparable results to first-order methods in FP8 and superior accuracy in INT8 and INT4 training.
FastDiff 2: Revisiting and Incorporating GANs and Diffusion Models in High-Fidelity Speech Synthesis (2023.findings-acl)

Copied to clipboard

Challenge: Experimental results show that Generative adversarial networks sacrifice sample diversity for quality and speed, while diffusion models exhibit outperformed sample quality and diversity at a high computational cost.
Approach: They propose to combine GANs and diffusion probabilistic models to achieve better sample quality and diversity.
Outcome: The proposed models outperform GANs and diffusion models in speech synthesis . the proposed models enjoy an efficient 4-step sampling process and exhibit better sample diversity .
Linguistically-Informed Evaluation of LLMs on Acceptability Judgments in a Forced-Choice Paradigm (2026.acl-srw)

Copied to clipboard

Challenge: Recent studies have reported close alignment with human judgments and systematic divergences driven by response biases and inconsistencies.
Approach: They evaluate large language models' ability to perform acceptability judgments in a forced-choice paradigm.
Outcome: The proposed models approximate human judgments but lack performance on morphosyntactic phenomena and prompt formulations.
IFlyLegal: A Chinese Legal System for Consultation, Law Searching, and Document Analysis (D19-3)

Copied to clipboard

Challenge: Legal Tech is a system that performs legal consulting, multi-way law searching, and legal document analysis using deep contextual representations and various attention mechanisms.
Approach: They propose a Chinese legal system that performs legal consulting, multi-way law searching, and legal document analysis using deep contextual representations and various attention mechanisms.
Outcome: The proposed system performs legal consulting, multi-way law searching, and legal document analysis by exploiting techniques such as deep contextual representations and various attention mechanisms.
CODIS: Benchmarking Context-dependent Visual Comprehension for Multimodal Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Multimodal large language models have demonstrated promising results in a variety of tasks that combine vision and language.
Approach: They propose a benchmark to assess the ability of models to use contextual information in free-form text to enhance visual comprehension.
Outcome: The proposed model fails to extract and utilize contextual information to improve understanding of images.
AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension (2024.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for audio-centric interaction have impeded advancements in this field . AIR-Bench evaluates LALMs' ability to understand audio signals and interact with humans .
Approach: They propose a benchmark to evaluate the ability of large audio-language models to understand audio signals . they use 19 tasks with approximately 19k single-choice questions to examine single-task ability .
Outcome: The proposed framework evaluates the ability of large audio-language models to understand audio signals and interact with humans in the textual format.
MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing multimodal benchmarks overlook linguistic and visual ambiguities, authors say . ambiguity resolution between modalities is lacking in multimodal large language models .
Approach: They propose a benchmark to evaluate multimodal ambiguity resolution across multilingual and cross-modal scenarios.
Outcome: a new benchmark evaluates multimodal ambiguity resolution across multilingual and cross-modal scenarios . the benchmark shows that MLLMs can resolve ambiguities in image-text alignment . however, existing benchmarks often overlook linguistic and visual ambiguties .
MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for MLLMs struggle with fine-grained temporal reasoning . despite advances in video understanding, current methods struggle with time-sensitive tasks .
Approach: They propose a time-stamp-aware multi-segment grounding method that enhances temporal understanding by introducing timestamps.
Outcome: The proposed method outperforms existing methods on time-sensitive tasks and generalizes well across diverse temporal understanding scenarios.
SHARP: Steering Hallucination in LVLMs via Representation Engineering (2025.emnlp-main)

Copied to clipboard

Challenge: Large Vision-Language Models (LVLMs) generate responses that are plausible but incorrect or unsupported—commonly referred to as hallucinations.
Approach: They propose a representation-level intervention framework that modulates hallucination-related features during inference by probing their encoded features.
Outcome: The proposed framework reduces hallucinations while maintaining the performance and generalization capabilities of Large Vision-Language Models (LVLMs).
Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions (2023.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) demonstrate impressive reasoning ability and the maintenance of world knowledge in natural language tasks.
Approach: They propose a framework that enables LLMs to ask relevant questions to uncover more details in the image, along with filters for refining the generated information.
Outcome: The proposed framework boosts the performance of baseline methods by 2.15% on OK-VQA and achieves consistent improvements across different LLMs.
CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-Training (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for expressive text-to-speech only implicitly learn prosody with masked token reconstruction tasks.
Approach: They propose a cross-modal contrastive pre-training framework that learns from prosody variance of the same text token under different contexts.
Outcome: The proposed framework can learn from prosody variance of a text token under different contexts.
DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms (2025.findings-emnlp)

Copied to clipboard

Challenge: Dongba pictographic is the only pictograph script still in use in the world.
Approach: DongbaMIE is the first dataset focusing on multimodal information extraction of Dongbe pictographs.
Outcome: The dataset contains 23,530 sentence-level and 2,539 paragraph-level high-quality text-image pairs.
CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation (2025.emnlp-main)

Copied to clipboard

Challenge: Large foundation models have become huge, but they consume computational resources in pretraining.
Approach: They propose to replace full-size layers with compute-efficient auto-encoders that enforce low-rank activations throughout training.
Outcome: The proposed method reduces the computing cost by 2pmbtimes and improves training throughput by 1.86pmtime.

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