Author name cluster

Yinghui Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

15 papers

2 author rows

AAAI Conference 2026 Conference Paper

DAPointMamba: Domain Adaptive Point Mamba for Point Cloud Completion

Yinghui Li
Qianyu Zhou
Di Shao
Hao Yang
Ye Zhu
Richard Dazeley
Xuequan Lu

Domain adaptive point cloud completion (DA PCC) aims to narrow the geometric and semantic discrepancies between the labeled source and unlabeled target domains. Existing methods either suffer from limited receptive fields or quadratic complexity due to using CNNs or vision Transformers. In this paper, we present the first work that studies the adaptability of state space models (SSMs) in DA PCC and find that directly applying SSMs to DA PCC will encounter several challenges: directly serializing 3D point clouds into 1D sequences often disrupts the spatial topology and local geometric features of the target domain. Besides, the overlook of designs in the learning domain-agnostic representations hinders the adaptation performance. To address these issues, we propose a novel framework, DAPointMamba for DA PCC, that exhibits strong adaptability across domains and has the advantages of global receptive fields and efficient linear complexity. It has three novel modules. In particular, Cross-Domain Patch-Level Scanning introduces patch-level geometric correspondences, enabling effective local alignment. Cross-Domain Spatial SSM Alignment further strengthens spatial consistency by modulating patch features based on cross-domain similarity, effectively mitigating fine-grained structural discrepancies. Cross-Domain Channel SSM Alignment actively addresses global semantic gaps by interleaving and aligning feature channels. Extensive experiments on both synthetic and real-world benchmarks demonstrate that our DAPointMamba outperforms state-of-the-art methods with less computational complexity and inference latency.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees

Yangning Li
Shaoshen Chen
Yinghui Li
Yankai Chen
Hai-Tao Zheng
Hui Wang
Wenhao Jiang
Philip S Yu

The quadratic complexity of self-attention limits Large Language Models (LLMs) in processing long contexts, a capability vital for many advanced applications. Context compression aims to mitigate this computational barrier while preserving essential semantic information. However, existing methods often falter: explicit methods can sacrifice local detail, while implicit ones may exhibit positional biases, struggle with information degradation, or fail to capture long-range semantic dependencies. We introduce AdmTree, a novel framework for adaptive, hierarchical context compression designed with a core focus on maintaining high semantic fidelity while keep efficiency. AdmTree dynamically segments input based on information density, employing gist tokens to summarize variable-length segments as leaves in a semantic binary tree. This structure, combined with a lightweight aggregation mechanism and a frozen backbone LLM (minimizing new trainable parameters), enables efficient hierarchical abstraction of the context. By effectively preserving fine-grained details alongside global semantic coherence, mitigating position bias, and adapting dynamically to content, AdmTree comprehensively preserves the semantic information of lengthy context.

PDF Details

NeurIPS Conference 2025 Conference Paper

Atomic Thinking of LLMs: Decoupling and Exploring Mathematical Reasoning Abilities

Jiayi Kuang
Haojing Huang
Yinghui Li
Xinnian Liang
Zhikun Xu
Yangning Li
Xiaoyu Tan
Chao Qu

Large Language Models (LLMs) have demonstrated outstanding performance in mathematical reasoning capabilities. However, we argue that current large-scale reasoning models primarily rely on scaling up training datasets with diverse mathematical problems and long thinking chains, which raises questions about whether LLMs genuinely acquire mathematical concepts and reasoning principles or merely remember the training data. In contrast, humans tend to break down complex problems into multiple fundamental atomic capabilities. Inspired by this, we propose a new paradigm for evaluating mathematical atomic capabilities. Our work categorizes atomic abilities into two dimensions: (1) field-specific abilities across four major mathematical fields, algebra, geometry, analysis, and topology, and (2) logical abilities at different levels, including conceptual understanding, forward multi-step reasoning with formal math language, and counterexample-driven backward reasoning. We propose corresponding training and evaluation datasets for each atomic capability unit, and conduct extensive experiments about how different atomic capabilities influence others, to explore the strategies to elicit the required specific atomic capability. Evaluation and experimental results on advanced models show many interesting discoveries and inspirations about the different performances of models on various atomic capabilities and the interactions between atomic capabilities. Our findings highlight the importance of decoupling mathematical intelligence into atomic components, providing new insights into model cognition and guiding the development of training strategies toward a more efficient, transferable, and cognitively grounded paradigm of "atomic thinking".

PDF Details

ICLR Conference 2025 Conference Paper

Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

Yangning Li
Yinghui Li
Xinyu Wang 0013
Yong Jiang 0005
Zhen Zhang
Xinran Zheng
Hui Wang 0030
Hai-Tao Zheng 0002

Multimodal Retrieval Augmented Generation (mRAG) plays an important role in mitigating the “hallucination” issue inherent in multimodal large language models (MLLMs). Although promising, existing heuristic mRAGs typically predefined fixed retrieval processes, which causes two issues: (1) Non-adaptive Retrieval Queries. (2) Overloaded Retrieval Queries. However, these flaws cannot be adequately reflected by current knowledge-seeking visual question answering (VQA) datasets, since the most required knowledge can be readily obtained with a standard two-step retrieval. To bridge the dataset gap, we first construct Dyn-VQA dataset, consisting of three types of ``dynamic'' questions, which require complex knowledge retrieval strategies variable in query, tool, and time: (1) Questions with rapidly changing answers. (2) Questions requiring multi-modal knowledge. (3) Multi-hop questions. Experiments on Dyn-VQA reveal that existing heuristic mRAGs struggle to provide sufficient and precisely relevant knowledge for dynamic questions due to their rigid retrieval processes. Hence, we further propose the first self-adaptive planning agent for multimodal retrieval, **OmniSearch**. The underlying idea is to emulate the human behavior in question solution which dynamically decomposes complex multimodal questions into sub-question chains with retrieval action. Extensive experiments prove the effectiveness of our OmniSearch, also provide direction for advancing mRAG. Code and dataset will be open-sourced.

Details

AAAI Conference 2025 Conference Paper

DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion

Yinghui Li
Qianyu Zhou
Jingyu Gong
Ye Zhu
Richard Dazeley
Xinkui Zhao
Xuequan Lu

Point Transformers (PoinTr) have shown great potential in point cloud completion recently. Nevertheless, effective domain adaptation that improves transferability toward target domains remains unexplored. In this paper, we delve into this topic and empirically discover that direct feature alignment on point Transformer’s CNN backbone only brings limited improvements since it cannot guarantee sequence-wise domain-invariant features in the Transformer. To this end, we propose a pioneering Domain Adaptive Point Transformer (DAPoinTr) framework for point cloud completion. DAPoinTr consists of three novel components: Domain Query-based Feature Alignment (DQFA), Point Token-wise Feature alignment (PTFA), and Voted Prediction Consistency (VPC). In particular, DQFA is presented to narrow the global domain gaps from the sequence via the presented domain proxy and domain query at the Transformer encoder and decoder, respectively. PTFA is proposed to close the local domain shifts by aligning the tokens, i.e., point proxy and dynamic query, at the Transformer encoder and decoder, respectively. VPC is designed to consider different Transformer decoders as multiple of experts (MoE) for ensembled prediction voting and pseudo-label generation. Extensive experiments with visualization on several challenging domain adaptation benchmarks demonstrate the effectiveness and superiority of our DAPoinTr compared with other state-of-the-art methods.

PDF Details DOI

AAAI Conference 2025 Conference Paper

EXCGEC: A Benchmark for Edit-Wise Explainable Chinese Grammatical Error Correction

Jingheng Ye
Shang Qin
Yinghui Li
Xuxin Cheng
Libo Qin
Hai-Tao Zheng
Ying Shen
Peng Xing

Existing studies explore the explainability of Grammatical Error Correction (GEC) in a limited scenario, where they ignore the interaction between corrections and explanations and have not established a corresponding comprehensive benchmark. To bridge the gap, this paper first introduces the task of EXplainable GEC (EXGEC), which focuses on the integral role of correction and explanation tasks. To facilitate the task, we propose EXCGEC, a tailored benchmark for Chinese EXGEC consisting of 8,216 explanation-augmented samples featuring the design of hybrid edit-wise explanations. We then benchmark several series of LLMs in multi-task learning settings, including post-explaining and pre-explaining. To promote the development of the task, we also build a comprehensive evaluation suite by leveraging existing automatic metrics and conducting human evaluation experiments to demonstrate the human consistency of the automatic metrics for free-text explanations. Our experiments reveal the effectiveness of evaluating free-text explanations using traditional metrics like METEOR and ROUGE, and the inferior performance of multi-task models compared to the pipeline solution, indicating its challenges to establish positive effects in learning both tasks.

PDF Details DOI

IROS Conference 2025 Conference Paper

Learning Natural and Robust Hexapod Locomotion over Complex Terrains via Motion Priors based on Deep Reinforcement Learning

Xin Liu 0106
Jinze Wu
Yinghui Li
Chenkun Qi
Yufei Xue
Feng Gao 0011

Multi-legged robots offer enhanced stability to navigate complex terrains with their multiple legs interacting with the environment. However, how to effectively coordinate the multiple legs in a larger action exploration space to generate natural and robust movements is a key issue. In this paper, we introduce a motion prior-based approach, successfully applying deep reinforcement learning algorithms to a real hexapod robot. We generate a dataset of optimized motion priors, and train an adversarial discriminator based on the priors to guide the hexapod robot to learn natural gaits. The learned policy is then successfully transferred to a real hexapod robot, and demonstrate natural gait patterns and remarkable robustness without visual information in complex terrains. This is the first time that a reinforcement learning controller has been used to achieve complex terrain walking on a real hexapod robot.

Details

ICML Conference 2025 Conference Paper

One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs

Yinghui Li
Jiayi Kuang
Haojing Huang 0001
Zhikun Xu
Xinnian Liang
Yi Yu
Wenlian Lu
Yangning Li

Leveraging mathematical Large Language Models (LLMs) for proof generation is a fundamental topic in LLMs research. We argue that the ability of current LLMs to prove statements largely depends on whether they have encountered the relevant proof process during training. This reliance limits their deeper understanding of mathematical theorems and related concepts. Inspired by the pedagogical method of "proof by counterexamples" commonly used in human mathematics education, our work aims to enhance LLMs’ ability to conduct mathematical reasoning and proof through counterexamples. Specifically, we manually create a high-quality, university-level mathematical benchmark, COUNTERMATH, which requires LLMs to prove mathematical statements by providing counterexamples, thereby assessing their grasp of mathematical concepts. Additionally, we develop a data engineering framework to automatically obtain training data for further model improvement. Extensive experiments and detailed analyses demonstrate that COUNTERMATH is challenging, indicating that LLMs, such as OpenAI o1, have insufficient counterexample-driven proof capabilities. Moreover, our exploration into model training reveals that strengthening LLMs’ counterexample-driven conceptual reasoning abilities is crucial for improving their overall mathematical capabilities. We believe that our work offers new perspectives on the community of mathematical LLMs.

Details

ICLR Conference 2025 Conference Paper

Refine Knowledge of Large Language Models via Adaptive Contrastive Learning

Yinghui Li
Haojing Huang 0001
Jiayi Kuang
Yangning Li
Shu-Yu Guo
Chao Qu
Xiaoyu Tan
Hai-Tao Zheng 0002

How to alleviate the hallucinations of Large Language Models (LLMs) has always been the fundamental goal pursued by the LLMs research community. Looking through numerous hallucination-related studies, a mainstream category of methods is to reduce hallucinations by optimizing the knowledge representation of LLMs to change their output. Considering that the core focus of these works is the knowledge acquired by models, and knowledge has long been a central theme in human societal progress, we believe that the process of models refining knowledge can greatly benefit from the way humans learn. In our work, by imitating the human learning process, we design an Adaptive Contrastive Learning strategy. Our method flexibly constructs different positive and negative samples for contrastive learning based on LLMs' actual mastery of knowledge. This strategy helps LLMs consolidate the correct knowledge they already possess, deepen their understanding of the correct knowledge they have encountered but not fully grasped, forget the incorrect knowledge they previously learned, and honestly acknowledge the knowledge they lack. Extensive experiments and detailed analyses on widely used datasets demonstrate the effectiveness and competitiveness of our method.

Details

NeurIPS Conference 2025 Conference Paper

SSRB: Direct Natural Language Querying to Massive Heterogeneous Semi-Structured Data

Xin Zhang
Mingxin Li
Yanzhao Zhang
Dingkun Long
Yongqi Li
Yinghui Li
Pengjun Xie
Meishan Zhang

Searching over semi-structured data with natural language (NL) queries has attracted sustained attention, enabling broader audiences to access information easily. As more applications, such as LLM agents and RAG systems, emerge to search and interact with semi-structured data, two major challenges have become evident: (1) the increasing diversity of domains and schema variations, making domain-customized solutions prohibitively costly; (2) the growing complexity of NL queries, which combine both exact field matching conditions and fuzzy semantic requirements, often involving multiple fields and implicit reasoning. These challenges make formal language querying or keyword-based search insufficient. In this work, we explore neural retrievers as a unified non-formal querying solution by directly index semi-structured collections and understand NL queries. We employ LLM-based automatic evaluation and build a large-scale semi-structured retrieval benchmark (SSRB) using LLM generation and filtering, containing 14M semi-structured objects from 99 different schemas across 6 domains, along with 8, 485 test queries that combine both exact and fuzzy matching conditions. Our systematic evaluation of popular retrievers shows that current state-of-the-art models could achieve acceptable performance, yet they still lack precise understanding of matching constraints. While by in-domain training of dense retrievers, the performance can be significantly improved. We believe that our SSRB could serve as a valuable resource for future research in this area, and we hope to inspire further exploration of semi-structured retrieval with complex queries.

PDF Details

IROS Conference 2024 Conference Paper

Experience-Learning Inspired Two-Step Reward Method for Efficient Legged Locomotion Learning Towards Natural and Robust Gaits

Yinghui Li
Jinze Wu
Xin Liu
Weizhong Guo
Yufei Xue

Legged robots excel in navigating complex terrains, yet learning natural and robust motions in such environments remains challenging. Inspired by animals’ experience-based stepwise learning process, we propose a two-stage framework for legged robots to progressively learn naturally robust movements using a two-step reward method. Initially robots learn the fundamental gaits on flat terrains with gait-rewards and generating valuable motion data. Subsequently, leveraging learned motion experience, they adopt adversarial imitation learning to tackle challenging terrains with refined movements. Our method addresses the challenge of acquiring effective imitation data and facilitates the learning process under various gait parameters with ease. The effectiveness of this approach has been validated on both quadruped and hexapod robots, demonstrating naturally robust gaits in real-world applications.

Details

AAAI Conference 2024 Conference Paper

MESED: A Multi-Modal Entity Set Expansion Dataset with Fine-Grained Semantic Classes and Hard Negative Entities

Yangning Li
Tingwei Lu
Hai-Tao Zheng
Yinghui Li
Shulin Huang
Tianyu Yu
Jun Yuan
Rui Zhang

The Entity Set Expansion (ESE) task aims to expand a handful of seed entities with new entities belonging to the same semantic class. Conventional ESE methods are based on mono-modality (i.e., literal modality), which struggle to deal with complex entities in the real world such as (1) Negative entities with fine-grained semantic differences. (2) Synonymous entities. (3) Polysemous entities. (4) Long-tailed entities. These challenges prompt us to propose novel Multi-modal Entity Set Expansion (MESE), where models integrate information from multiple modalities to represent entities. Intuitively, the benefits of multi-modal information for ESE are threefold: (1) Different modalities can provide complementary information. (2) Multi-modal information provides a unified signal via common visual properties for the same semantic class or entity. (3) Multi-modal information offers robust alignment signals for synonymous entities. To assess model performance in MESE, we constructed the MESED dataset which is the first multi-modal dataset for ESE with large-scale and elaborate manual calibration. A powerful multi-modal model MultiExpan is proposed which is pre-trained on four multimodal pre-training tasks. The extensive experiments and analyses on MESED demonstrate the high quality of the dataset and the effectiveness of our MultiExpan, as well as pointing the direction for future research. The benchmark and code are public at https://github.com/THUKElab/MESED.

PDF Details DOI

AAAI Conference 2024 Conference Paper

SeqGPT: An Out-of-the-Box Large Language Model for Open Domain Sequence Understanding

Tianyu Yu
Chengyue Jiang
Chao Lou
Shen Huang
Xiaobin Wang
Wei Liu
Jiong Cai
Yangning Li

Large language models (LLMs) have shown impressive abilities for open-domain NLP tasks. However, LLMs are sometimes too footloose for natural language understanding (NLU) tasks which always have restricted output and input format. Their performances on NLU tasks are highly related to prompts or demonstrations and are shown to be poor at performing several representative NLU tasks, such as event extraction and entity typing. To this end, we present SeqGPT, a bilingual (i.e., English and Chinese) open-source autoregressive model specially enhanced for open-domain natural language understanding. We express all NLU tasks with two atomic tasks, which define fixed instructions to restrict the input and output format but still ``open'' for arbitrarily varied label sets. The model is first instruction-tuned with extremely fine-grained labeled data synthesized by ChatGPT and then further fine-tuned by 233 different atomic tasks from 152 datasets across various domains. The experimental results show that SeqGPT has decent classification and extraction ability, and is capable of performing language understanding tasks on unseen domains. We also conduct empirical studies on the scaling of data and model size as well as on the transfer across tasks. Our models are accessible at https://github.com/Alibaba-NLP/SeqGPT.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models

Yinghui Li
Qingyu Zhou
Yuanzhen Luo
Shirong Ma
Yangning Li
Hai-Tao Zheng
Xuming Hu
Philip S. Yu

Recently, Large Language Models (LLMs) make remarkable evolutions in language understanding and generation. Following this, various benchmarks for measuring all kinds of capabilities of LLMs have sprung up. In this paper, we challenge the reasoning and understanding abilities of LLMs by proposing a FaLlacy Understanding Benchmark (FLUB) containing cunning texts that are easy for humans to understand but difficult for models to grasp. Specifically, the cunning texts that FLUB focuses on mainly consist of the tricky, humorous, and misleading texts collected from the real internet environment. And we design three tasks with increasing difficulty in the FLUB benchmark to evaluate the fallacy understanding ability of LLMs. Based on FLUB, we investigate the performance of multiple representative and advanced LLMs, reflecting our FLUB is challenging and worthy of more future study. Interesting discoveries and valuable insights are achieved in our extensive experiments and detailed analyses. We hope that our benchmark can encourage the community to improve LLMs' ability to understand fallacies. Our data and codes are available at https: //github. com/THUKElab/FLUB.

PDF Details DOI

JBHI Journal 2022 Journal Article

Non-Contact Negative Mood State Detection Using Reliability-Focused Multi-Modal Fusion Model

Qian Rong
Shuai Ding
Zijie Yue
Yaping Wang
Linjie Wang
Xi Zheng
Yinghui Li

Negative mood states include tension, depression, anger, fatigue, and confusion, which represent the weak internal emotions of a human. Negative mood states exert adverse impact on individuals’ ability to make rational decisions, which entails the practicable method of negative mood state detection. The most commonly used negative mood state detection methods are based on the psychological scale, which requires additional work and brings inconvenience to the subject in the application scenarios. To overcome this challenge, this paper proposes a novel non-contact negative mood state detection method according to the knowledge of affective computing. The POMS-net model is used to extract temporal-spatial features from visible and infrared thermal videos, and the negative mood state detection is realized using data reliability-focused multi-modal fusion. The proposed method is verified using the HDT-BR dataset collected in the aerospace medicine experiment “Earth-Star II” and the VIRI public dataset. The experimental results on the datasets verify that our method outperforms the comparison methods.

Details DOI