Papers by Tao Zeng

22 papers
Prior Knowledge and Memory Enriched Transformer for Sign Language Translation (2022.findings-acl)

Copied to clipboard

Challenge: Existing methods for sign language translation do not explore all of them . visual and textual understanding and additional prior knowledge learning are challenging .
Approach: They propose a method which integrates auxiliary information into vanilla transformer for SLT . they use visual-textual context information and additional auxiliary knowledge of a word .
Outcome: The proposed method improves the understanding of sign language videos with visual and textual understanding and additional prior knowledge learning.
Crossing Variational Autoencoders for Answer Retrieval (2020.acl-main)

Copied to clipboard

Challenge: Existing methods learned semantic representations with dual encoders or dual variational auto-encoders failed to capture the aligned semantics between question and answer.
Approach: They propose to use two variational auto-encoders to generate questions with aligned answers and generating answers with align questions.
Outcome: The proposed method outperforms the state-of-the-art answer retrieval method on SQuAD.
From Charts to Code: A Hierarchical Benchmark for Multimodal Models (2026.acl-long)

Copied to clipboard

Challenge: Chart2Code is a new benchmark for evaluating the natural language to chart code generation capabilities of large multimodal models.
Approach: They introduce Chart2Code, a new benchmark for evaluating the natural language to chart code generation capabilities of large multimodal models.
Outcome: The proposed benchmark is the first to scale task complexity while capturing diverse scenarios.
Rehearsal-free Continual Language Learning via Efficient Parameter Isolation (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for learning continual tasks do not cache history data, which makes the problem more challenging.
Approach: They propose a method that allocates a small portion of private parameters and learns them with a shared pre-trained model.
Outcome: The proposed method is comparable to existing methods and comparable to those using historical data.
Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models exhibit strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC) when instructions are revealed progressively in multi-turn settings, models get "Lost in Conversation"
Approach: They propose a framework that encourages models to generate correct answers and judge solvability in multi-turn conversations.
Outcome: The proposed framework improves models' ability to balance problem-solving with abstention . it reduces premature answering behaviors that cause lost-in-conversation (LiC)
ProductResearch: Training E-Commerce Deep Research Agents via Multi-Agent Synthetic Trajectory Distillation (2026.acl-industry)

Copied to clipboard

Challenge: Existing LLM-based agents lack the interaction depth and contextual breadth required for complex product research.
Approach: They propose a multi-agent framework that synthesizes high-fidelity tool-use trajectories for training robust e-commerce shopping agents.
Outcome: The proposed framework synthesizes high-fidelity, long-horizon tool-use trajectories for training robust e-commerce shopping agents.
OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding (2026.acl-long)

Copied to clipboard

Challenge: coding scaffolds that follow heterogeneous instructions remain under-examined in software engineering . coding models are capable software agents, but their ability to follow constraints remains under-explored .
Approach: They introduce OctoBench, which benchmarks scaffold-aware instruction following in agentic coding.
Outcome: The proposed benchmark aims to accelerate the development of more scaffold-aware agents.
Reinforcement Learning on Pre-Training Data (2026.acl-long)

Copied to clipboard

Challenge: Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings.
Approach: They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data.
Outcome: Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base.
ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation (2022.acl-long)

Copied to clipboard

Challenge: Residual networks are an Euler discretization of solutions to Ordinary Differential Equations (ODE).
Approach: They propose a residual block of layers in Transformer that can be described as a higher-order solution to ODE.
Outcome: The proposed architecture can gain large improvements over strong baselines at a slight cost in inference efficiency.
MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing low-bit quantization methods often exhibit severe performance degradation on complex reasoning tasks.
Approach: They propose a plug-and-play method that uses a key channel's intrinsic quantization difficulty and relevance to the query to identify and preserve critical key channels that need higher precision.
Outcome: Experiments on complex reasoning datasets show that the proposed method outperforms low-bit methods at a substantially reduced memory footprint.
Preserving Language Capabilities in Vision-Language Models via Representation Regulation (2026.findings-acl)

Copied to clipboard

Challenge: Vision-Language Models (VLMs) provide a unified framework to process both text-only and vision-language tasks.
Approach: They propose a method to reduce the distance between visual and textual representations by introducing a Representation Distribution Difference (RDD) loss.
Outcome: Empirical evidence shows that finetuning VLMs on vision-language data has degraded language capabilities.
What Matters in Training a GPT4-Style Language Model with Multimodal Inputs? (2024.naacl-long)

Copied to clipboard

Challenge: Recent advances in GPT-4V have demonstrated remarkable multi-modal capabilities in processing image inputs and following open-ended instructions.
Approach: They propose a plug-and-play technique to enhance multi-modal LLMs . they propose 'lynx' to train multi-modal LLM models .
Outcome: The proposed training strategy improves understanding accuracy and instruction-following proficiency of multi-modal models.
Learning from LLM Agents: In-Context Generative Models for Text Casing in E-Commerce Ads (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing NER-based transformer models are expensive and lack contextual dependencies, making them less reliable when handling unseen or ad-specific terms, e.g., brand names.
Approach: They propose a two-stage approach to casing correction in e-commerce ad content that leverages Chain-of-Actions to enforce content policies while accurately handling ads-specific terms.
Outcome: The proposed model outperforms existing NER-based models and achieves near-LLM performance at a fraction of the cost.
ChatASU: Evoking LLM’s Reflexion to Truly Understand Aspect Sentiment in Dialogues (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies on interactive ASU ignore the coreference issue for opinion targets while this phenomenon is ubiquitous in interactive scenarios especially dialogues, limiting the ASU performance.
Approach: They propose a Chat-based Aspect Sentiment Understanding task that integrates various NLP tasks with the chat paradigm and propose 'trusted self-reflexion' approach with ChatGLM as backbone to address aspect coreference issue.
Outcome: The proposed task outperforms state-of-the-art baselines and shows that it is highly effective.
Bridging the Editing Gap in LLMs: FineEdit for Precise and Targeted Text Modifications (2025.findings-emnlp)

Copied to clipboard

Challenge: a recent study shows that large language models can perform precise text editing tasks.
Approach: InstrEditBench is a benchmark dataset that compares 30,000 structured editing tasks . experimental evaluations show FineEdit outperforms state-of-the-art models .
Outcome: The proposed model outperforms state-of-the-art models on single-turn edits and mistral-7B-OpenOrca on direct edits.
Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints (2022.naacl-main)

Copied to clipboard

Challenge: Existing approaches to lexically constrained neural machine translation suffer from high latency.
Approach: They propose a plug-in algorithm for non-autoregressive translation for this problem . they propose ACT to familiarize the model with the source-side context of constraints .
Outcome: The proposed model improves over the backbone constrained NAT model in constraint preservation and translation quality, especially for rare constraints.
Synonym Knowledge Enhanced Reader for Chinese Idiom Reading Comprehension (2020.coling-main)

Copied to clipboard

Challenge: Experimental results show that our model achieves state-of-the-art performance for Chinese idiom comprehension.
Approach: They propose a model that can mitigate the inconsistency between literal and literal meanings by incorporating the synonym knowledge enhanced reader into the model.
Outcome: The proposed model achieves state-of-the-art on a Chinese idiom reading comprehension dataset.
OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)

Copied to clipboard

Challenge: a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide.
Approach: They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions .
Outcome: The proposed agents are based on operating systems (OS) and operating systems frameworks.
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training (2021.findings-acl)

Copied to clipboard

Challenge: Symbolic music understanding is useful for many music applications, but lack of training data hinders representation learning.
Approach: They propose a pre-trained model for music understanding that uses symbolic music data to train music representations.
Outcome: The proposed model improves on four music understanding tasks.
GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) generate content that exhibits gender biases, raising ethical concerns.
Approach: They propose to use a dataset to identify gender biases in Large Language Models (LLMs) this dataset is a "chosen" and "rejected" LLM alignment is an effective approach to mitigate gender bias.
Outcome: The proposed dataset shows that it reduces gender bias and improves quality.
Extract and Attend: Improving Entity Translation in Neural Machine Translation (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to improve entity translation in Neural machine translation still suffer from inaccurate translation of entities due to the lack of entity training instances.
Approach: They propose an extract-and-tend approach to enhance entity translation in NMT by extracting entities from a dictionary and attending to them with a prefix.
Outcome: Experiments on En-Zh and En-Ru show that the proposed approach improves translation accuracy and translation quality.
KuiLeiXi: a Chinese Open-Ended Text Adventure Game (2021.acl-demo)

Copied to clipboard

Challenge: Recent advances in pre-trained language models have made it possible to generate human-like text.
Approach: They propose to integrate an open-ended text adventure game in Chinese, named KuiLeiXi, where players interact with the AI until the plot goals are reached.
Outcome: The proposed game lacks incentives and relies on players to explore on their own.

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