Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Suggested from co-authorship
- Jian Ping YinSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works64 from public data
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents623
UI-TARS is an end-to-end model that solely perceives the screenshots as input and performs human-like interactions and achieves SOTA performance in 10+ GUI agent benchmarks evaluating perception, grounding, and GUI task execution.
- Aligning Large Language Models with Human: A Survey515
This survey presents a comprehensive overview of these human-aligned LLMs, shedding light on several promising future research avenues in the field and serves as a valuable resource for anyone invested in understanding and advancing the alignment of LLMs to better suit human-oriented tasks and expectations.
- Improving Question Answering by Commonsense-Based Pre-training489
Results show that incorporating commonsense-based function improves the baseline on three question answering tasks that require commonsense reasoning and leverages useful evidence from an external commonsense knowledge base, which is missing in existing neural network models.
- ReTool: Reinforcement Learning for Strategic Tool Use in LLMs414
ReTool is proposed, which enhances long-form reasoning with tool-integrated learning, including dynamic interleaving of real-time code execution within natural language reasoning processes, and an automated RL paradigm that allows policy rollouts with multi-turn real-time code execution and teaches the model in learning when and how to invoke tools based on outcome feedback.
- Compare to The Knowledge: Graph Neural Fake News Detection with External Knowledge266
A novel end-to-end graph neural model called CompareNet is proposed, which compares the news to the knowledge base (KB) through entities for fake news detection and significantly outperforms state-of-the-art methods.
- LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation240
An empirical study to study the phenomena, mechanism, and mitigation of LLM hallucinations within more practical and complex development contexts in repository-level generation scenario and proposes an RAG-based mitigation method, which demonstrates consistent effectiveness in all studied LLMs.
- G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model233
G-LLaVA is developed, which demonstrates exceptional performance in solving geometric problems, significantly outperforming GPT-4-V on the MathVista benchmark with only 7B parameters.
- 225
- UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning201
UI-TARS-2 is presented, a native GUI-centered agent model that addresses challenges through a systematic training methodology: a data flywheel for scalable data generation, a stabilized multi-turn RL framework, a hybrid GUI environment that integrates file systems and terminals, and a unified sandbox platform for large-scale rollouts.
- 196
- Reasoning Over Semantic-Level Graph for Fact Checking191
This work proposes two mechanisms to exploit the structure of evidence while leveraging the advances of pre-trained models like BERT, GPT or XLNet, and is the state-of-the-art system in terms of both official evaluation metrics, namely claim verification accuracy and FEVER score.
- Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning153
This work introduces Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks, demonstrating excellent reasoning abilities in STEM and coding and generalization across diverse domains.
- WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach153
This work conducts a thorough examination of pretrained model based unsupervised sentence embeddings and concludes that an easy whitening-based vector normalization strategy with less than 10 lines of code consistently boosts the performance.
- Agents in software engineering: survey, landscape, and vision94
This paper presents a framework of LLM-based agents in SE which includes three key modules: perception, memory, and action and summarizes the current challenges in combining the two fields and proposes future opportunities in response to existing challenges.
- Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text94
The results show that the proposed logic-driven data augmentation algorithm achieves state-of-the-art performance on both datasets, and even surpasses human performance on the ReClor dataset.
- AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions85
This work proposes AutoKaggle, a powerful and user-centric framework that assists data scientists in completing daily data pipelines through a collaborative multi-agent system that implements an iterative development process that combines code execution, debugging, and comprehensive unit testing to ensure code correctness and logic consistency.
- Neural Deepfake Detection with Factual Structure of Text83
Results of experiments show that the proposed graph-based model for deepfake detection significantly improves strong base models built with RoBERTa and indicates that the model can distinguish the difference in the factual structure between machine-generated text and human-written text.
- From LSAT: The Progress and Challenges of Complex Reasoning69
This paper proposes a hybrid reasoning system to integrate these three tasks of the LSAT, including analytical reasoning, logical reasoning and reading comprehension, and sheds a light on the potential future directions, like unsupervised symbolic knowledge extraction, model interpretability, few-shot learning and comprehensive benchmark for complex reasoning.
- LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Network63
This work proposes LogicalFactChecker, a neural network approach capable of leveraging logical operations for fact checking, which achieves the state-of-the-art performance on TABFACT, a large-scale, benchmark dataset built for verifying a textual statement with semi-structured tables.
- Syntax-Enhanced Pre-trained Model56
It is demonstrated that infusing automatically produced syntax of text improves pre-trained models, and global syntactic distances among tokens bring larger performance gains compared to local head relations between contiguous tokens.
- When to Stop? Towards Efficient Code Generation in LLMs with Excess Token Prevention52
The key idea of CodeFast is to terminate the inference process in time when unnecessary excess tokens are detected, which can significantly improve the inference speed of various Code LLMs in code generation, without compromising the quality of generated code.
- PerLTQA: A Personal Long-Term Memory Dataset for Memory Classification, Retrieval, and Fusion in Question Answering52
A novel framework for memory integration in QA is proposed, consisting of three subtasks: Memory Classification, Memory Retrieval, and Memory Fusion, which provides a comprehensive paradigm for memory modeling, enabling consistent and personalized memory utilization.
- AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting50
AdaCtrl is proposed, a novel framework to support both difficulty-aware adaptive reasoning budget allocation and explicit user control over reasoning depth that dynamically adjusts its reasoning length based on self-assessed problem difficulty, while also allowing users to manually control the budget to prioritize either efficiency or effectiveness.
- UserAdapter: Few-Shot User Learning in Sentiment Analysis39
This work introduces a lightweight approach dubbed UserAdapter, which clamps hundred millions of parameters of the Transformer model and optimizes a tiny user-specific vector and offers an efficient way to produce a personalized Transformer model with less than 0.5% parameters added for each user.
- Reverse-Engineered Reasoning for Open-Ended Generation38
This work introduces REverse-Engineered Reasoning (REER), a new paradigm that fundamentally shifts the approach of deep reasoning, and works ``backwards'' from known-good solutions to computationally discover the latent, step-by-step deep reasoning process that could have produced them.
- Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence37
Agent-World is presented, a self-evolving training arena for advancing general agent intelligence through scalable environments that consistently outperforms strong proprietary models and environment scaling baselines and reveals scaling trends in relation to environment diversity and self-evolution rounds, offering insights for building general agent intelligence.
- Acting Less is Reasoning More! Teaching Model to Act Efficiently36
This work proposes Optimal Tool Call-controlled Policy Optimization (OTC-PO), a simple yet effective RL-based framework that encourages models to produce accurate answers with minimal tool calls and is the first RL-based framework that explicitly optimizes tool-use efficiency in TIR 1.
- PerLTQA: A Personal Long-Term Memory Dataset for Memory Classification, Retrieval, and Synthesis in Question Answering35
This research introduces PerLTQA, an innovative QA dataset that combines semantic and episodic memories, including world knowledge, profiles, social relationships, events, and dialogues, and proposes a novel framework for memory integration and generation, consisting of three main components: Memory Classification, Memory Retrieval, and Memory Synthesis.
- Analytical Reasoning of Text31
This paper studies the challenge of analytical reasoning of text and collects a new dataset consisting of questions from the Law School Admission Test from 1991 to 2016, and presents an approach dubbed ARM, which outperforms pre-trained models significantly.
- 28
- You Augment Me: Exploring ChatGPT-based Data Augmentation for Semantic Code Search24
This work proposes a novel approach ChatDANCE, which utilizes high-quality and diverse augmented data generated by a large language model and leverages a filtering mechanism to eliminate low-quality augmentations and enables the backbone model (UniXcoder) to self-grow.
- GroundNLQ @ Ego4D Natural Language Queries Challenge 202324
A novel grounding model GroundNLQ is introduced, which employs a multi-modal multi-scale grounding module for effective video and text fusion and various temporal intervals, especially for long videos.
- Reasoning over Hybrid Chain for Table-and-Text Open Domain Question Answering24
This paper proposes a ChAin-centric Reasoning and Pre-training framework (CARP), which utilizes hybrid chain to model the explicit intermediate reasoning process across table and text for question answering and proposes a novel chain-centric pre-training method to enhance the pre-trained model in identifying the cross-modality reasoning process and alleviating the data sparsity problem.
- Data Management For Training Large Language Models: A Survey20
This survey provides a comprehensive overview of current research in data management within both the pretraining and supervised fine-tuning stages of LLMs, covering various noteworthy aspects of data management strategy design: data quantity, data quality, domain/task composition, etc.
- 19
- 18
- 18
- 16
- Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning16
A novel logic-driven data augmentation approach that enhances both generative large language models, such as GPT-3.5 and GPT-4, through prompt augmentation, and discriminative large language models through contrastive learning with logic-driven data augmentation.
- 14
- YODA: Teacher-Student Progressive Learning for Language Models12
YODA is introduced, a novel teacher-student progressive learning framework that emulates the teacher-student education process to improve the efficacy of model fine-tuning and finds that training with curriculum learning further improves learning robustness.
- 12
- Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA12
- Assessing and Enhancing the Robustness of Large Language Models with Task Structure Variations for Logical Reasoning10
It is shown that applying logic-driven data augmentation for fine-tuning and prompting can enhance generalisation in both discriminative and generative models, offering a path to improving their robustness for tasks involving logical reasoning.
- 10
- 8
- Leveraging Declarative Knowledge in Text and First-Order Logic for Fine-Grained Propaganda Detection7
Experiments show that the method achieves superior performance, demonstrating that injecting declarative knowledge expressed in both natural language and first-order logic can help the model to make more accurate predictions.
- 7
- 6
- 6
- An Efficient COarse-to-fiNE Alignment Framework @ Ego4D Natural Language Queries Challenge 20226
The model CONE dynamically slices the long video into candidate windows via a sliding window approach, an efficient window-centric COarse-to-fiNE alignment framework that learns the inter-window semantic variance through contrastive learning and speeds up inference by pre-filtering the candidate windows relevant to the NL query.
- 6
- Exploring Iterative Enhancement for Improving Learnersourced Multiple-Choice Question Explanations with Large Language Models5
ILearner-LLM is introduced, a framework that uses iterative enhancement with LLMs to improve generated explanations and produces explanations of higher quality that closely align with those written by students.
- Empowering Self-Learning of LLMs: Inner Knowledge Explicitation as a Catalyst4
A Self Knowledge Explicitation Learning (SKE-Learn) framework is introduced, which equips the LLMs with meta-skills to explicitly extract, verify and utilize inner knowledge for reasoning, which establishes a self-learning approach that ensures reliable selection of self-synthetic data.
- 4
- 4
- Modeling Semantic Composition with Syntactic Hypergraph for Video Question Answering4
This work proposes to build a syntactic dependency tree for each question with an off-the-shelf tool and use it to guide the extraction of meaningful word compositions, leading to a model named cross-modality-aware syntactic HCN, which outperforms all strong baselines.
- 2
- 1
- 1
- 1
- –
- CodeCritic: towards effective code quality evaluation with large language models–
The empirical results show that while GPT-4 outperforms other LLMs in code evaluation, its proprietary nature and cost limit its accessibility, and this paper presents CodeCritic, an open-source LLM fine-tuned on CodeCriticData, which achieves state-of-the-art results.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.