Papers by Zehan Wang

13 papers
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.
Masked Text-to-Audio Flow-Matching and Reward Feedback Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Experimental results show that Flow-matching generative models can scale training by increasing data, computational resources, and model size.
Approach: They propose a flow-matching transformer with masked generative modeling for scaling text-to-audio inference-time prediction.
Outcome: The proposed model scales inference-time computations by masking generation and re-predicting them through iterative decoding.
Pub-LawBench: Public-Oriented Benchmarking for LegalAI (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluation frameworks focus on legal professionals, not legal professionals.
Approach: They propose a public-oriented LegalAI benchmark grounded in legal functionalism and genre analysis to address this gap.
Outcome: The proposed model evaluates 17 large language models on Pub-LawBench using simple prompts and Chain-of-Thought under a vanilla inference setting.
Temporal Leakage in Search-Engine Date-Filtered Web Retrieval: A Retrospective Forecasting Case Study (2026.acl-short)

Copied to clipboard

Challenge: Search-engine date filters are widely used to enforce pre-cutoff retrieval in retrospective evaluations of search-augmented forecasters.
Approach: They propose stronger retrieval safeguards or evaluation on frozen, time-stamped web snapshots to prevent post-cutoff leakage.
Outcome: The proposed approach is unreliable across two major search engines, and the results are inflated.
T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback (2025.acl-long)

Copied to clipboard

Challenge: Text-to-audio (T2A) models still struggle to satisfy human preferences for prompt-following and acoustic quality when generating complex multi-event audio.
Approach: They propose to use AI feedback learning to enhance basic capabilities of text-to-audio models . they use a large audio preference dataset to evaluate the model's capabilities .
Outcome: The proposed model improves in simple and complex scenarios with AI feedback learning.
View-R1: Asymmetric Policy Optimization for Difficulty-Aware Multimodal Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) are powerful at integrating diverse data but struggle with complex reasoning.
Approach: They propose a method which separates responses into positive and negative groups to stabilize training and preserve knowledge.
Outcome: The proposed model View-R1 achieves a 10.55% improvement in reasoning and outperforms larger models while maintaining and improving performance on general tasks.
TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for talking head translation rely on cascading, resulting in delays and cascadic errors.
Approach: They propose a model for talking head translation, TransFace, which can translate audio-visual speech into audio-visual speech in other languages.
Outcome: The proposed model can translate audio-visual speech into audio-visual speech in other languages.
ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control (2025.acl-long)

Copied to clipboard

Challenge: Prior zero-shot TTS models only mimic the speaker’s voice without further control and adjustment capabilities while prior controllable TTS systems cannot perform speaker-specific voice generation.
Approach: They propose a style control module that captures codec representations corresponding to timbre, content, and style in a discrete decoupling codec space.
Outcome: The proposed system can fully clone the speaker's voice and perform speech-specific adjustment and control functions.
Knowledge Conflicts for LLMs: A Survey (2024.emnlp-main)

Copied to clipboard

Challenge: This survey examines knowledge conflicts for large language models (LLMs) this survey aims to shed light on strategies for improving the robustness of LLMs .
Approach: They focus on three categories of knowledge conflicts: context-memory, inter-context, and intra-membry conflict.
Outcome: The findings highlight the challenges faced by large language models when blending contextual and parametric knowledge.
Scene-robust Natural Language Video Localization via Learning Domain-invariant Representations (2023.findings-acl)

Copied to clipboard

Challenge: Recent studies have focused on improving performance with the assumption of independently identical data distribution while ignoring out-of-distribution data.
Approach: They propose a scene-robust NLVL problem and a generalizable framework to learn a robust model.
Outcome: The proposed model learns generalizable domain-invariant representations by alignment and decomposition.
3DRP-Net: 3D Relative Position-aware Network for 3D Visual Grounding (2023.emnlp-main)

Copied to clipboard

Challenge: 3D visual grounding aims to localize the desired objects in a 3D point cloud by a free-form language description.
Approach: They propose a relation-aware framework which captures relative spatial relationships between objects and enhances object attributes.
Outcome: The proposed framework outperforms state-of-the-art methods on three benchmarks . it captures relative spatial relationships between objects and enhances object attributes .
Data-Efficiently Learn Large Language Model for Universal 3D Scene Perception (2025.findings-naacl)

Copied to clipboard

Challenge: Existing methods for 3D scene understanding are limited to specific downstream tasks, hindering their practicality in real-world applications.
Approach: They propose a 3D visual perceptual ability and advanced reasoning capabilities for 3D scenes by aligning 3D representations into the feature space of advanced LLMs.
Outcome: The proposed system achieves a 82.2% relative score compared with state-of-the-art methods with limited data.
LONG2RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall (2024.findings-emnlp)

Copied to clipboard

Challenge: Retrieval-augmented generation (RAG) is a promising approach to address limitations of fixed knowledge in large language models.
Approach: They propose a benchmark and a metric to assess LLMs' ability to generate long-form responses that exploit retrieved information.
Outcome: The proposed benchmarks lack a comprehensive evaluation method to assess LLMs' ability to generate long-form responses that effectively exploits retrieved information.

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