Author name cluster

Jiajun Liu

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.

28 papers

2 author rows

AAAI Conference 2026 Conference Paper

Balanced Knowledge Distillation for Large Language Models with Mix-of-Experts

Jiajun Liu
Yao He
Wenjun Ke
Peng Wang
Ziyu Shang
Guozheng Li
Zijie Xu

Mixture-of-Experts (MoE) architectures have recently become a more prevalent choice for large language models (LLMs) than dense architectures due to their superior performance. However, billions of parameters bring MoE LLMs a huge cost for deployment and inference. To address these issues, knowledge distillation (KD) has become a widely adopted technique to compress LLMs. Existing KD methods for LLMs can be divided into dense-to-dense and moe-to-dense distillation. Dense-to-dense distillation transfers knowledge between single dense LLMs, while moe-to-dense distillation attempts to transfer knowledge between the MoE LLMs and the dense LLMs. However, the architectural mismatch prevents the student from fully absorbing knowledge when distilling MoE LLMs. To address this limitation, we investigate a new distillation setting, moe-to-moe, which aims to fully leverage expert knowledge of teachers and enable the student to absorb it more effectively. Compared to dense-to-dense and moe-to-dense, moe-to-moe suffers from two imbalance issues. First, expert-coverage deficiency reflects an imbalanced knowledge transfer of teacher experts: traditional distillation utilizes only the few experts activated by the teacher router. Second, routing imbalance appears when the student routing distribution drifts from the teacher, which makes it difficult for students to learn how to distribute different experts. To overcome these issues, we propose a novel distillation framework for moe-to-moe, Balanced Distillation (B-Distill), which equally spreads teacher expertise across student experts while regularizing the student router toward teacher-consistent balance. First, to mitigate expert-coverage deficiency, we introduce Monte Carlo exploration, which stochastically perturbs router probabilities so every teacher and student expert is sampled without enlarging the search space. Second, to correct routing imbalance and avert load collapse, we propose an entropy-aware router distillation mechanism that aligns the student router with the teacher while curbing over-concentration. Experiments show that B-Distill outperforms baselines by up to 6.6% in Rouge-L.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Benchmarking and Enhancing Rule Knowledge-Driven Reasoning of Large Language Models

Zijie Xu
Wenjun Ke
Peng Wang
Guozheng Li
Qingjian Ni
Jiajun Liu
Ziyu Shang
Jing Zhou

Large Language Models (LLMs) have demonstrated strong capabilities across diverse tasks under the example-driven learning paradigm. However, in high-stakes domains such as emergency response and industrial safety, historical incidents are scarce, confidential, or both, while concise rule books are abundant. We formalize this underexplored setting as rule knowledge-driven reasoning and ask: Can LLMs reason reliably when rules are plentiful but examples are nearly absent? To study this question, we introduce RULER, an automatic benchmark that generates 32K rigorously verified questions from 1K expert-curated emergency response rules to probe three core abilities: rule memorization, single-rule application, and multi-rule complex reasoning. RULER is further equipped with a hallucination-aware evaluation suite and novel relational metrics. A comprehensive empirical study of five representative LLMs and five enhancement strategies shows that, even when models achieve reliable performance on rule memorization and single-rule application, multi-rule complex reasoning plateaus at 5.4 on a 10-point scale. To address this limitation, we propose RAMPS, a Rule knowledge-Aware Monte Carlo Tree Search Process-reward Supervision framework. RAMPS injects rule knowledge priors into MCTS, distills 12K step-level traces without human annotation, and trains an advantage-based reward model that scores candidate reasoning paths during beam search inference. Experimental results show that RAMPS significantly improves multi-rule complex reasoning performance to 7.7.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Optimizing LoRA Allocation of MoE with the Alignment of Topic Correlation

Hengyuan Xu
Wenjun Ke
Yao He
Jiajun Liu
Dong Nie
Peng Wang
Ziyu Shang
Zijie Xu

Mixture of experts (MoE) dynamically routes inputs to specialized expert networks to scale model capacity with low inference overhead. However, the excessive parameter growth in MoE models poses challenges in low-resource settings. To address these issues, MoE with parameter-efficient fine-tuning (PEFT) methods have emerged as a lightweight adaptation paradigm that distributes knowledge among experts via multiple LoRA blocks. Existing MoE-PEFT methods can be broadly categorized into External and Internal PEFT methods. External PEFT methods incorporate lightweight models into existing MoE architectures without modifying their routing, which limits the model’s parameter efficiency. To overcome these issues, Internal PEFT methods integrate MoE architectures into PEFT, enabling minimal parameter overhead. However, they still face two major challenges: (1) lack of expert functional differentiation, resulting in overlapping specialization across modules, and (2) absence of a structured attribution mechanism to guide expert selection based on semantic relevance. To alleviate these challenges, we propose TopicLoRA, a novel three-stage framework that leverages topic knowledge as semantic anchors to guide expert allocation. Specifically, (1) to address expert redundancy, we construct a topic-level prior graph using Graph Neural Network-enhanced representation learning over Big-Bench categories, enforcing structural separation among expert embeddings, and (2) to introduce semantic attribution, we design a dual-loss training mechanism that softly aligns input-query relevance with topic-guided routing distributions via KL divergence. Extensive experiments on representative datasets (e.g., MMLU, GSM8K, Flanv2) demonstrate that TopicLoRA outperforms state-of-the-art PEFT baselines by 2.40% on average in accuracy. Notably, the maximum improvement is 4.21%. Furthermore, ablation studies demonstrate that our framework's robustness to intricate topics and input sequence variations, which stems from the dual-loss training mechanism.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Can Large Models Teach Student Models to Solve Mathematical Problems Like Human Beings? A Reasoning Distillation Method via Multi-LoRA Interaction

Xinhe Li
Jiajun Liu
Peng Wang

Recent studies have demonstrated that Large Language Models (LLMs) have strong mathematical reasoning abilities but rely on hundreds of billions of parameters. To tackle the challenge of poor reasoning in Small Language Models (SLMs), existing methods typically leverage LLMs to generate massive amounts of data for cramming training. In psychology, they are akin to System 1 thinking, which resolves reasoning problems rapidly based on experience and intuition. However, human learning also requires System 2 thinking, where knowledge is first acquired and then reinforced through practice. Inspired by such two distinct modes of thinking, we propose a novel method based on the multi-LoRA Interaction for mathematical reasoning Distillation (LoRID). First, we input the question and reasoning of each sample into an LLM to create knowledge-enhanced datasets. Subsequently, we train a LoRA block on the student model as an Intuitive Reasoner (IR), which directly generates Chain-of-Thoughts for problem-solving. Then, to imitate System 2 thinking, we train the Knowledge Generator (KG) and Deep Reasoner (DR), respectively. The former outputs only knowledge after receiving problems, while the latter uses that knowledge to perform reasoning. Finally, to address the randomness in the generation of IR and DR, we evaluate whether their outputs are consistent, and the inference process needs to be iterated if not. This step can enhance the mathematical reasoning ability of SLMs through mutual feedback. Experimental results show that LoRID achieves state-of-the-art performance, especially on the GSM8K dataset, where it outperforms the second-best method by 2. 3%, 16. 1%, 2. 4%, 12. 3%, and 1. 8% accuracy across the five base models, respectively. Meanwhile, we select four strong baselines as System 1, and after integrating them with our method, the reasoning ability of student models is consistently and significantly improved. The datasets and codes are available at https: //github. com/Xinhe-Li/LoRID.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation

Wenbo Zhang
Tianrun Hu
Hanbo Zhang
Yanyuan Qiao
Yuchu Qin
Yang Li
Jiajun Liu
Tao Kong

We present Chain-of-Action (CoA), a novel visuomotor policy paradigm built upon Trajectory Autoregressive Modeling. Unlike conventional approaches that predict next step action(s) forward, CoA generates an entire trajectory by explicit backward reasoning with task-specific goals through an action-level Chain-of-Thought (CoT) process. This process is unified within a single autoregressive structure: (1) the first token corresponds to a stable keyframe action that encodes the task-specific goals; and (2) subsequent action tokens are generated autoregressively, conditioned on the initial keyframe and previously predicted actions. This backward action reasoning enforces a global-to-local structure, allowing each local action to be tightly constrained by the final goal. To further realize the action reasoning structure, CoA incorporates four complementary designs: continuous action token representation; dynamic stopping for variable-length trajectory generation; reverse temporal ensemble; and multi-token prediction to balance action chunk modeling with global structure. As a result, CoA gives strong spatial generalization capabilities while preserving the flexibility and simplicity of a visuomotor policy. Empirically, we observe that CoA outperforms representative imitation learning algorithms such as ACT and Diffusion Policy across 60 RLBench tasks and 8 real-world tasks.

PDF Details

ICRA Conference 2025 Conference Paper

Effective Tuning Strategies for Generalist Robot Manipulation Policies

Wenbo Zhang 0009
Yang Li
Yanyuan Qiao
Siyuan Huang 0004
Jiajun Liu
Feras Dayoub
Xiao Ma
Lingqiao Liu

Generalist robot manipulation policies (GMPs) have the potential to generalize across a wide range of tasks, devices, and environments. However, existing policies continue to struggle with out-of-distribution scenarios due to the inherent difficulty of collecting sufficient action data to cover extensively diverse domains. While fine-tuning offers a practical way to quickly adapt a GMPs to novel domains and tasks with limited samples, we observe that the performance of the resulting GMPs differs significantly with respect to the design choices of fine-tuning strategies. In this work, we first conduct an indepth empirical study to investigate the effect of key factors in GMPs fine-tuning strategies, covering the action space, policy head, supervision signal and the choice of tunable parameters, where 2, 500 rollouts are evaluated for a single configuration. We systematically discuss and summarize our findings and identify the key design choices, which we believe give a practical guideline for GMPs fine-tuning. We observe that in a lowdata regime, with carefully chosen fine-tuning strategies, a GMPs significantly outperforms the state-of-the-art imitation learning algorithms. The results presented in this work establish a new baseline for future studies on fine-tuned GMPs.

Details

ICLR Conference 2025 Conference Paper

General Scene Adaptation for Vision-and-Language Navigation

Haodong Hong
Yanyuan Qiao
Sen Wang 0001
Jiajun Liu
Qi Wu 0001

Vision-and-Language Navigation (VLN) tasks mainly evaluate agents based on one-time execution of individual instructions across multiple environments, aiming to develop agents capable of functioning in any environment in a zero-shot manner. However, real-world navigation robots often operate in persistent environments with relatively consistent physical layouts, visual observations, and language styles from instructors. Such a gap in the task setting presents an opportunity to improve VLN agents by incorporating continuous adaptation to specific environments. To better reflect these real-world conditions, we introduce GSA-VLN (General Scene Adaptation for VLN), a novel task requiring agents to execute navigation instructions within a specific scene and simultaneously adapt to it for improved performance over time. To evaluate the proposed task, one has to address two challenges in existing VLN datasets: the lack of out-of-distribution (OOD) data, and the limited number and style diversity of instructions for each scene. Therefore, we propose a new dataset, GSA-R2R, which significantly expands the diversity and quantity of environments and instructions for the Room-to-Room (R2R) dataset to evaluate agent adaptability in both ID and OOD contexts. Furthermore, we design a three-stage instruction orchestration pipeline that leverages large language models (LLMs) to refine speaker-generated instructions and apply role-playing techniques to rephrase instructions into different speaking styles. This is motivated by the observation that each individual user often has consistent signatures or preferences in their instructions, taking the use case of home robotic assistants as an example. We conducted extensive experiments on GSA-R2R to thoroughly evaluate our dataset and benchmark various methods, revealing key factors enabling agents to adapt to specific environments. Based on our findings, we propose a novel method, Graph-Retained DUET (GR-DUET), which incorporates memory-based navigation graphs with an environment-specific training strategy, achieving state-of-the-art results on all GSA-R2R splits.

Details

ICLR Conference 2025 Conference Paper

Medium-Difficulty Samples Constitute Smoothed Decision Boundary for Knowledge Distillation on Pruned Datasets

Yudong Chen 0002
Xuwei Xu
Frank de Hoog
Jiajun Liu
Sen Wang 0001

This paper tackles a new problem of dataset pruning for Knowledge Distillation (KD), from a fresh perspective of Decision Boundary (DB) preservation and drifts. Existing dataset pruning methods generally assume that the post-pruning DB formed by the selected samples can be well-captured by future networks that use those samples for training. Therefore, they tend to preserve hard samples since hard samples are closer to the DB and better characterize the nuances in the distribution of the entire dataset. However, in KD, the limited learning capacity from the student network leads to imperfect preservation of the teacher's feature distribution, resulting in the drift of DB in the student space. Specifically, hard samples worsen such drifts as they are difficult for the student to learn, creating a situation where the student's DB can drift deeper into other classes and make incorrect classifications. Motivated by these findings, our method selects medium-difficulty samples for KD-based dataset pruning. We show that these samples constitute a smoothed version of the teacher's DB and are easier for the student to learn, obtaining a general feature distribution preservation for a class of samples and reasonable DB between different classes for the student. In addition, to reduce the distributional shift due to dataset pruning, we leverage the class-wise distributional information of the teacher's outputs to reshape the logits of the preserved samples. Experiments show that the proposed static pruning method can even perform better than the state-of-the-art dynamic pruning method which needs access to the entire dataset. In addition, our method halves the training times of KD and improves the student's accuracy by 0.4% on ImageNet with a 50% keep ratio. When the ratio further increases to 70%, our method achieves higher accuracy over the vanilla KD while reducing the training times by 30%. Code is available at https://github.com/chenyd7/MDSLR.

Details

ICML Conference 2025 Conference Paper

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers

Xuwei Xu
Yang Li 0184
Yudong Chen 0002
Jiajun Liu
Sen Wang 0001

We reveal that feedforward network (FFN) layers, rather than attention layers, are the primary contributors to Vision Transformer (ViT) inference latency, with their impact signifying as model size increases. This finding highlights a critical opportunity for optimizing the efficiency of large-scale ViTs by focusing on FFN layers. In this work, we propose a novel channel idle mechanism that facilitates post-training structural reparameterization for efficient FFN layers during testing. Specifically, a set of feature channels remains idle and bypasses the nonlinear activation function in each FFN layer, thereby forming a linear pathway that enables structural reparameterization during inference. This mechanism results in a family of RePa rameterizable Vi sion T ransformers (RePaViTs), which achieve remarkable latency reductions with acceptable sacrifices (sometimes gains) in accuracy across various ViTs. The benefits of our method scale consistently with model sizes, demonstrating greater speed improvements and progressively narrowing accuracy gaps or even higher accuracies on larger models. In particular, RePa-ViT-Large and RePa-ViT-Huge enjoy 66. 8% and 68. 7% speed-ups with +1. 7% and +1. 1% higher top-1 accuracies under the same training strategy, respectively. RePaViT is the first to employ structural reparameterization on FFN layers to expedite ViTs to our best knowledge, and we believe that it represents an auspicious direction for efficient ViTs. Source code is available at https: //github. com/Ackesnal/RePaViT.

Details

ICRA Conference 2024 Conference Paper

A Detachable FBG-Based Contact Force Sensor for Capturing Gripper-Vegetable Interactions

Wenjie Lai
Jiajun Liu
Bing Rui Sim
Joel Ming Rui Tan
Chidanand Hegde
Shlomo Magdassi
Soo Jay Phee

Vertical farming, a sustainable key for urban agriculture, has garnered attention for its land use optimization and enhanced food production capabilities. The adoption of automation in vertical farming is a pivotal response to labor shortages, addressing the need for increased efficiency, particularly in labor-intensive tasks like harvesting. Although soft robotic grippers offer a significant promise for delicately handling fragile objects, the absence of sensors has hindered their full potential to execute precise and secure grasping. To address this challenge, we present a new solution: a detachable Fiber Bragg Grating-based flexible contact force sensor to capture gripper-vegetable interactions. The sensing module was 3D printed using soft material, and the FBG fiber was attached to the module using epoxy. From evaluation tests, this lightweight sensor demonstrated a wide measurement range of up to 9. 87 N, with a high sensitivity of 141. 7 pm/N, good repeatability, and a hysteresis of 7. 96%. Compared to commercial load cells, our sensor achieves a small measurement RMSE of 0. 41 N and a percentage error of 4. 15%. The sensor was integrated into two robotic 3D-printed soft grippers to enable real-time monitoring of dynamic contact force during vegetable harvesting in vertical farming scenarios. By reflecting contact status, this sensor provides a promising glimpse into the future of agricultural automation, enhancing operational efficiency and strengthening situation awareness and decision-making capabilities in vertical farms. Beyond agriculture, the versatility of this sensor extends to application in areas such as warehousing, logistics, and the food and beverage industry.

Details

IJCAI Conference 2024 Conference Paper

Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-shot Hierarchical Text Classification

Ke Ji
Peng Wang
Wenjun Ke
Guozheng Li
Jiajun Liu
Jingsheng Gao
Ziyu Shang

Recently, various pre-trained language models (PLMs) have been proposed to prove their impressive performances on a wide range of few-shot tasks. However, limited by the unstructured prior knowledge in PLMs, it is difficult to maintain consistent performance on complex hierarchically dependent tasks, especially when the downstream data is extremely scarce. The main challenge is how to transfer the unstructured semantic space in PLMs to the downstream domain hierarchy. Unlike previous work on hierarchical text classification (HTC) which directly performs multi-label classification or uses graph neural network (GNN) to inject label hierarchy, in this work, we study the HTC problem under a few-shot setting to adapt knowledge in PLMs from an unstructured manner to the downstream hierarchy. Technically, we design a simple yet effective method named Hierarchical Iterative Conditional Random Field (HierICRF) to search the most domain-challenging directions and exquisitely crafts domain-hierarchy adaptation as a hierarchical iterative language modeling problem, and then it encourages the model to make hierarchical consistency self-correction during the inference, thereby achieving knowledge transfer with hierarchical consistency preservation. We perform HierICRF on various architectures, and extensive experiments on two popular HTC datasets demonstrate that prompt with HierICRF significantly boosts the few-shot HTC performance with an average Micro-F1 by 28. 80% to 1. 50% and Macro-F1 by 36. 29% to 1. 5% over the previous state-of-the-art (SOTA) baselines under few-shot settings (1->16), while remaining SOTA hierarchical consistency performance.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Empirical Analysis of Dialogue Relation Extraction with Large Language Models

Guozheng Li
Zijie Xu
Ziyu Shang
Jiajun Liu
Ke Ji
Yikai Guo

Dialogue relation extraction (DRE) aims to extract relations between two arguments within a dialogue, which is more challenging than standard RE due to the higher person pronoun frequency and lower information density in dialogues. However, existing DRE methods still suffer from two serious issues: (1) hard to capture long and sparse multi-turn information, and (2) struggle to extract golden relations based on partial dialogues, which motivates us to discover more effective methods that can alleviate the above issues. We notice that the rise of large language models (LLMs) has sparked considerable interest in evaluating their performance across diverse tasks. To this end, we initially investigate the capabilities of different LLMs in DRE, considering both proprietary models and open-source models. Interestingly, we discover that LLMs significantly alleviate two issues in existing DRE methods. Generally, we have following findings: (1) scaling up model size substantially boosts the overall DRE performance and achieves exceptional results, tackling the difficulty of capturing long and sparse multi-turn information; (2) LLMs encounter with much smaller performance drop from entire dialogue setting to partial dialogue setting compared to existing methods; (3) LLMs deliver competitive or superior performances under both full-shot and few-shot settings compared to current state-of-the-art; (4) LLMs show modest performances on inverse relations but much stronger improvements on general relations, and they can handle dialogues of various lengths especially for longer sequences.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Fast and Continual Knowledge Graph Embedding via Incremental LoRA

Jiajun Liu
Wenjun Ke
Peng Wang
Jiahao Wang
Jinhua Gao
Ziyu Shang
Guozheng Li
Zijie Xu

Continual Knowledge Graph Embedding (CKGE) aims to efficiently learn new knowledge and simultaneously preserve old knowledge. Dominant approaches primarily focus on alleviating catastrophic forgetting of old knowledge but neglect efficient learning for the emergence of new knowledge. However, in real-world scenarios, knowledge graphs (KGs) are continuously growing, which brings a significant challenge to fine-tuning KGE models efficiently. To address this issue, we propose a fast CKGE framework (FastKGE), incorporating an incremental low-rank adapter (IncLoRA) mechanism to efficiently acquire new knowledge while preserving old knowledge. Specifically, to mitigate catastrophic forgetting, FastKGE isolates and allocates new knowledge to specific layers based on the fine-grained influence between old and new KGs. Subsequently, to accelerate fine-tuning, FastKGE devises an efficient IncLoRA mechanism, which embeds the specific layers into incremental low-rank adapters with fewer training parameters. Moreover, IncLoRA introduces adaptive rank allocation, which makes the LoRA aware of the importance of entities and adjusts its rank scale adaptively. We conduct experiments on four public datasets and two new datasets with a larger initial scale. Experimental results demonstrate that FastKGE can reduce training time by 34%-49% while still achieving competitive link prediction performance against state-of-the-art models on four public datasets (average MRR score of 21. 0% vs. 21. 1%). Meanwhile, on two newly constructed datasets, FastKGE saves 51%-68% training time and improves link prediction performance by 1. 5%.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Incorporating Schema-Aware Description into Document-Level Event Extraction

Zijie Xu
Peng Wang
Wenjun Ke
Guozheng Li
Jiajun Liu
Ke Ji
Xiye Chen
Chenxiao Wu

Document-level event extraction (DEE) aims to extract the structured event information from a given document, facing two critical challenges: (1) event arguments always scatter across sentences (arguments-scattering); (2) multiple events can co-occur in one document (multi-event). Most recent studies mainly follow two simplified settings to ease the challenges: one simplifies DEE with the no-trigger-words design (NDEE), and the other focuses on event argument extraction (DEAE), a sub-task of DEE. However, the former excludes trigger extraction and suffers from error propagation in the sub-tasks. The latter relies heavily on the gold triggers as prerequisites and struggles to distinguish multiple arguments playing the same role in different events. To address the limitations above, we propose a novel joint trigger and argument extraction paradigm SEELE to enhance the DEE model via incorporating SchEma-awarE descriptions into Document-Level Event extraction. Specifically, the schema-aware descriptions are leveraged from two aspects: (1) guiding the attention mechanism among event-aware tokens across sentences, which relieves arguments-scattering without error propagation; (2) performing the fine-grained contrastive learning to distinguish different events, which mitigates multi-event without gold triggers. Extensive experiments show the superiority of SEELE, achieving notable improvements (2. 1% to 9. 7% F1) on three NDEE datasets and competitive performance on two DEAE datasets. Our code is available at https: //github. com/TheoryRhapsody/SEELE.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Learning Multi-Granularity and Adaptive Representation for Knowledge Graph Reasoning

Ziyu Shang
Peng Wang
Wenjun Ke
Jiajun Liu
Hailang Huang
Guozheng Li
Chenxiao Wu
Jianghan Liu

Knowledge graph reasoning (KGR) aims to infer new factual triples from existing knowledge graphs (KGs). Recently, a new category of methods, possessing both transductive and inductive reasoning capabilities, has been proposed to tackle this task via learning entity-independent representations from local neighboring structures. However, these methods are plagued by inefficiency issues and they exclusively capture evidence from well-designed local structures, ignoring the correlation between the query and different structures within KGs. In this work, we first propose a novel multi-granularity and adaptive representation framework, MulGA, exploiting the connectivity subgraph to uniformly and hierarchically model query-related triples, relation paths, and subgraphs without explicitly extracting any graph structure, hence mitigating inefficiency issues. Second, we introduce a message-passing mechanism across connectivity subgraphs, facilitating all entities to attain query-related structural representations of diverse granularity levels, i. e. , triple and relation paths of different lengths. Third, we design a self-attention-based merging mechanism that allocates weights to different granularities and then consolidates them into subgraph granularity representations for reasoning. The systematic experiments have been conducted on 15 benchmarks and MulGA achieves a significant improvement in MRR by an average of 1. 5% on transductive and 2. 7% on inductive tasks than existing state-of-the-art methods. Moreover, MulGA boasts faster convergence speed, competitive inference time, and alleviates the over-smoothing prevalent in graph neural networks.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Meta In-Context Learning Makes Large Language Models Better Zero and Few-Shot Relation Extractors

Guozheng Li
Peng Wang
Jiajun Liu
Yikai Guo
Ke Ji
Ziyu Shang
Zijie Xu

Relation extraction (RE) is an important task that aims to identify the relationships between entities in texts. While large language models (LLMs) have revealed remarkable in-context learning (ICL) capability for general zero and few-shot learning, recent studies indicate that current LLMs still struggle with zero and few-shot RE. Previous studies are mainly dedicated to design prompt formats and select good examples for improving ICL-based RE. Although both factors are vital for ICL, if one can fundamentally boost the ICL capability of LLMs in RE, the zero and few-shot RE performance via ICL would be significantly improved. To this end, we introduce Micre (Meta In-Context learning of LLMs for Relation Extraction), a new meta-training framework for zero and few-shot RE where an LLM is tuned to do ICL on a diverse collection of RE datasets (i. e. , learning to learn in context for RE). Through meta-training, the model becomes more effectively to learn a new RE task in context by conditioning on a few training examples with no parameter updates or task-specific templates at inference time, enabling better zero and few-shot task generalization. We experiment Micre on various LLMs with different model scales and 12 public RE datasets, and then evaluate it on unseen RE benchmarks under zero and few-shot settings. Micre delivers comparable or superior performance compared to a range of baselines including supervised fine-tuning and typical in-context learning methods. We find that the gains are particular significant for larger model scales, and using a diverse set of the meta-training RE datasets is key to improvements. Empirically, we show that Micre can transfer the relation semantic knowledge via relation label name during inference on target RE datasets.

PDF Details DOI

AAAI Conference 2024 Conference Paper

OntoFact: Unveiling Fantastic Fact-Skeleton of LLMs via Ontology-Driven Reinforcement Learning

Ziyu Shang
Wenjun Ke
Nana Xiu
Peng Wang
Jiajun Liu
Yanhui Li
Zhizhao Luo
Ke Ji

Large language models (LLMs) have demonstrated impressive proficiency in information retrieval, while they are prone to generating incorrect responses that conflict with reality, a phenomenon known as intrinsic hallucination. The critical challenge lies in the unclear and unreliable fact distribution within LLMs trained on vast amounts of data. The prevalent approach frames the factual detection task as a question-answering paradigm, where the LLMs are asked about factual knowledge and examined for correctness. However, existing studies primarily focused on deriving test cases only from several specific domains, such as movies and sports, limiting the comprehensive observation of missing knowledge and the analysis of unexpected hallucinations. To address this issue, we propose OntoFact, an adaptive framework for detecting unknown facts of LLMs, devoted to mining the ontology-level skeleton of the missing knowledge. Specifically, we argue that LLMs could expose the ontology-based similarity among missing facts and introduce five representative knowledge graphs (KGs) as benchmarks. We further devise a sophisticated ontology-driven reinforcement learning (ORL) mechanism to produce error-prone test cases with specific entities and relations automatically. The ORL mechanism rewards the KGs for navigating toward a feasible direction for unveiling factual errors. Moreover, empirical efforts demonstrate that dominant LLMs are biased towards answering Yes rather than No, regardless of whether this knowledge is included. To mitigate the overconfidence of LLMs, we leverage a hallucination-free detection (HFD) strategy to tackle unfair comparisons between baselines, thereby boosting the result robustness. Experimental results on 5 datasets, using 32 representative LLMs, reveal a general lack of fact in current LLMs. Notably, ChatGPT exhibits fact error rates of 51.6% on DBpedia and 64.7% on YAGO, respectively. Additionally, the ORL mechanism demonstrates promising error prediction scores, with F1 scores ranging from 70% to 90% across most LLMs. Compared to the exhaustive testing, ORL achieves an average recall of 80% while reducing evaluation time by 35.29% to 63.12%.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Real-time Multi-modal Object Detection and Tracking on Edge for Regulatory Compliance Monitoring

Jia Syuen Lim
Ziwei Wang
Jiajun Liu
Abdelwahed Khamis
Reza Arablouei
Robert Barlow
Ryan McAllister

Regulatory compliance auditing in agrifood processing facilities is crucial for upholding the highest standards of quality assurance and traceability. However, the current manual and intermittent approaches to auditing present significant challenges and risks, potentially leading to gaps or loopholes in the system. To address these shortcomings, we introduce a real-time, multi-modal sensing system that utilizes 3D time-of-flight and RGB cameras and leverages unsupervised learning techniques on edge AI devices. The proposed system enables continuous object tracking, leading to improved efficiency in record-keeping and reduced manual labor. We demonstrate the effectiveness of the system in a knife sanitization monitoring scenario, showcasing its capability to overcome occlusion and low-light performance limitations commonly encountered with conventional RGB cameras.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction

Guozheng Li
Peng Wang
Wenjun Ke
Yikai Guo
Ke Ji
Ziyu Shang
Jiajun Liu
Zijie Xu

Relation extraction (RE) aims to identify relations between entities mentioned in texts. Although large language models (LLMs) have demonstrated impressive in-context learning (ICL) abilities in various tasks, they still suffer from poor performances compared to most supervised fine-tuned RE methods. Utilizing ICL for RE with LLMs encounters two challenges: (1) retrieving good demonstrations from training examples, and (2) enabling LLMs exhibit strong ICL abilities in RE. On the one hand, retrieving good demonstrations is a non-trivial process in RE, which easily results in low relevance regarding entities and relations. On the other hand, ICL with an LLM achieves poor performance in RE while RE is different from language modeling in nature or the LLM is not large enough. In this work, we propose a novel recall-retrieve-reason RE framework that synergizes LLMs with retrieval corpora (training examples) to enable relevant retrieving and reliable in-context reasoning. Specifically, we distill the consistently ontological knowledge from training datasets to let LLMs generate relevant entity pairs grounded by retrieval corpora as valid queries. These entity pairs are then used to retrieve relevant training examples from the retrieval corpora as demonstrations for LLMs to conduct better ICL via instruction tuning. Extensive experiments on different LLMs and RE datasets demonstrate that our method generates relevant and valid entity pairs and boosts ICL abilities of LLMs, achieving competitive or new state-of-the-art performance on sentence-level RE compared to previous supervised fine-tuning methods and ICL-based methods.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Towards Continual Knowledge Graph Embedding via Incremental Distillation

Jiajun Liu
Wenjun Ke
Peng Wang
Ziyu Shang
Jinhua Gao
Guozheng Li
Ke Ji
Yanhe Liu

Traditional knowledge graph embedding (KGE) methods typically require preserving the entire knowledge graph (KG) with significant training costs when new knowledge emerges. To address this issue, the continual knowledge graph embedding (CKGE) task has been proposed to train the KGE model by learning emerging knowledge efficiently while simultaneously preserving decent old knowledge. However, the explicit graph structure in KGs, which is critical for the above goal, has been heavily ignored by existing CKGE methods. On the one hand, existing methods usually learn new triples in a random order, destroying the inner structure of new KGs. On the other hand, old triples are preserved with equal priority, failing to alleviate catastrophic forgetting effectively. In this paper, we propose a competitive method for CKGE based on incremental distillation (IncDE), which considers the full use of the explicit graph structure in KGs. First, to optimize the learning order, we introduce a hierarchical strategy, ranking new triples for layer-by-layer learning. By employing the inter- and intra-hierarchical orders together, new triples are grouped into layers based on the graph structure features. Secondly, to preserve the old knowledge effectively, we devise a novel incremental distillation mechanism, which facilitates the seamless transfer of entity representations from the previous layer to the next one, promoting old knowledge preservation. Finally, we adopt a two-stage training paradigm to avoid the over-corruption of old knowledge influenced by under-trained new knowledge. Experimental results demonstrate the superiority of IncDE over state-of-the-art baselines. Notably, the incremental distillation mechanism contributes to improvements of 0.2%-6.5% in the mean reciprocal rank (MRR) score. More exploratory experiments validate the effectiveness of IncDE in proficiently learning new knowledge while preserving old knowledge across all time steps.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Unveiling LoRA Intrinsic Ranks via Salience Analysis

Wenjun Ke
Jiahao Wang
Peng Wang
Jiajun Liu
Dong Nie
Guozheng Li
Yining Li

The immense parameter scale of large language models underscores the necessity for parameter-efficient fine-tuning methods. Methods based on Low-Rank Adaptation (LoRA) assume the low-rank characteristics of the incremental matrix and optimize the matrix obtained from low-rank decomposition. Although effective, these methods are constrained by a fixed and unalterable intrinsic rank, neglecting the variable importance of matrices. Consequently, methods for adaptive rank allocation are proposed, among which AdaLoRA demonstrates excellent fine-tuning performance. AdaLoRA conducts adaptation based on singular value decomposition (SVD), dynamically allocating intrinsic ranks according to importance. However, it still struggles to achieve a balance between fine-tuning effectiveness and efficiency, leading to limited rank allocation space. Additionally, the importance measurement focuses only on parameters with minimal impact on the loss, neglecting the dominant role of singular values in SVD-based matrices and the fluctuations during training. To address these issues, we propose SalientLoRA, which adaptively optimizes intrinsic ranks of LoRA via salience measurement. Firstly, during rank allocation, the salience measurement analyses the variation of singular value magnitudes across multiple time steps and establishes their inter-dependency relationships to assess the matrix importance. This measurement mitigates instability and randomness that may arise during importance assessment. Secondly, to achieve a balance between fine-tuning performance and efficiency, we propose an adaptive adjustment of time-series window, which adaptively controls the size of time-series for significance measurement and rank reduction during training, allowing for rapid rank allocation while maintaining training stability. This mechanism enables matrics to set a higher initial rank, thus expanding the allocation space for ranks. To evaluate the generality of our method across various tasks, we conduct experiments on natural language understanding (NLU), natural language generation (NLG), and large model instruction tuning tasks. Experimental results demonstrate the superiority of SalientLoRA, which outperforms state-of-the-art methods by 0. 96\%-3. 56\% on multiple datasets. Furthermore, as the rank allocation space expands, our method ensures fine-tuning efficiency, achieving a speed improvement of 94. 5\% compared to AdaLoRA. The code is publicly available at https: //github. com/Heyest/SalientLoRA.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts

Haodong Hong
Sen Wang
Zi Huang
Qi Wu
Jiajun Liu

Current Vision-and-Language Navigation (VLN) tasks mainly employ textual instructions to guide agents. However, being inherently abstract, the same textual instruction can be associated with different visual signals, causing severe ambiguity and limiting the transfer of prior knowledge in the vision domain from the user to the agent. To fill this gap, we propose Vision-and-Language Navigation with Multi-modal Prompts (VLN-MP), a novel task augmenting traditional VLN by integrating both natural language and images in instructions. VLN-MP not only maintains backward compatibility by effectively handling text-only prompts but also consistently shows advantages with different quantities and relevance of visual prompts. Possible forms of visual prompts include both exact and similar object images, providing adaptability and versatility in diverse navigation scenarios. To evaluate VLN-MP under a unified framework, we implement a new benchmark that offers: (1) a training-free pipeline to transform textual instructions into multi-modal forms with landmark images; (2) diverse datasets with multi-modal instructions for different downstream tasks; (3) a novel module designed to process various image prompts for seamless integration with state-of-the-art VLN models. Extensive experiments on four VLN benchmarks (R2R, RxR, REVERIE, CVDN) show that incorporating visual prompts would significantly boost navigation performance. While maintaining efficiency with text-only prompts, VLN-MP enables agents to navigate in the pre-explore setting and outperform text-based models, showing its broader applicability. Code is available at https: //github. com/honghd16/VLN-MP.

PDF Details DOI

AAAI Conference 2023 Conference Paper

IterDE: An Iterative Knowledge Distillation Framework for Knowledge Graph Embeddings

Jiajun Liu
Peng Wang
Ziyu Shang
Chenxiao Wu

Knowledge distillation for knowledge graph embedding (KGE) aims to reduce the KGE model size to address the challenges of storage limitations and knowledge reasoning efficiency. However, current work still suffers from the performance drops when compressing a high-dimensional original KGE model to a low-dimensional distillation KGE model. Moreover, most work focuses on the reduction of inference time but ignores the time-consuming training process of distilling KGE models. In this paper, we propose IterDE, a novel knowledge distillation framework for KGEs. First, IterDE introduces an iterative distillation way and enables a KGE model to alternately be a student model and a teacher model during the iterative distillation process. Consequently, knowledge can be transferred in a smooth manner between high-dimensional teacher models and low-dimensional student models, while preserving good KGE performances. Furthermore, in order to optimize the training process, we consider that different optimization objects between hard label loss and soft label loss can affect the efficiency of training, and then we propose a soft-label weighting dynamic adjustment mechanism that can balance the inconsistency of optimization direction between hard and soft label loss by gradually increasing the weighting of soft label loss. Our experimental results demonstrate that IterDE achieves a new state-of-the-art distillation performance for KGEs compared to strong baselines on the link prediction task. Significantly, IterDE can reduce the training time by 50% on average. Finally, more exploratory experiments show that the soft-label weighting dynamic adjustment mechanism and more fine-grained iterations can improve distillation performance.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process

Mengyu Wang
Henghui Ding
Jun Hao Liew
Jiajun Liu
Yao Zhao
Yunchao Wei

In this paper, we explore a principal way to enhance the quality of object masks produced by different segmentation models. We propose a model-agnostic solution called SegRefiner, which offers a novel perspective on this problem by interpreting segmentation refinement as a data generation process. As a result, the refinement process can be smoothly implemented through a series of denoising diffusion steps. Specifically, SegRefiner takes coarse masks as inputs and refines them using a discrete diffusion process. By predicting the label and corresponding states-transition probabilities for each pixel, SegRefiner progressively refines the noisy masks in a conditional denoising manner. To assess the effectiveness of SegRefiner, we conduct comprehensive experiments on various segmentation tasks, including semantic segmentation, instance segmentation, and dichotomous image segmentation. The results demonstrate the superiority of our SegRefiner from multiple aspects. Firstly, it consistently improves both the segmentation metrics and boundary metrics across different types of coarse masks. Secondly, it outperforms previous model-agnostic refinement methods by a significant margin. Lastly, it exhibits a strong capability to capture extremely fine details when refining high-resolution images. The source code and trained models are available at SegRefiner. git

PDF Details

NeurIPS Conference 2022 Conference Paper

Improved Feature Distillation via Projector Ensemble

Yudong Chen
Sen Wang
Jiajun Liu
Xuwei Xu
Frank de Hoog
Zi Huang

In knowledge distillation, previous feature distillation methods mainly focus on the design of loss functions and the selection of the distilled layers, while the effect of the feature projector between the student and the teacher remains under-explored. In this paper, we first discuss a plausible mechanism of the projector with empirical evidence and then propose a new feature distillation method based on a projector ensemble for further performance improvement. We observe that the student network benefits from a projector even if the feature dimensions of the student and the teacher are the same. Training a student backbone without a projector can be considered as a multi-task learning process, namely achieving discriminative feature extraction for classification and feature matching between the student and the teacher for distillation at the same time. We hypothesize and empirically verify that without a projector, the student network tends to overfit the teacher's feature distributions despite having different architecture and weights initialization. This leads to degradation on the quality of the student's deep features that are eventually used in classification. Adding a projector, on the other hand, disentangles the two learning tasks and helps the student network to focus better on the main feature extraction task while still being able to utilize teacher features as a guidance through the projector. Motivated by the positive effect of the projector in feature distillation, we propose an ensemble of projectors to further improve the quality of student features. Experimental results on different datasets with a series of teacher-student pairs illustrate the effectiveness of the proposed method. Code is available at https: //github. com/chenyd7/PEFD.

PDF Details

TIST Journal 2020 Journal Article

Geosocial Co-Clustering

Jungeun Kim
Jae-Gil Lee
Byung Suk Lee
Jiajun Liu

As location-based services using mobile devices have become globally popular these days, social network analysis (especially, community detection) increasingly benefits from combining social relationships with geographic preferences. In this regard, this article addresses the emerging problem of geosocial community detection. We first formalize the problem of geosocial co-clustering, which co-clusters the users in social networks and the locations they visited. Geosocial co-clustering detects higher-quality communities than existing approaches by improving the mapping clusterability, whereby users in the same community tend to visit locations in the same region. While geosocial co-clustering is soundly formalized as non-negative matrix tri-factorization, conventional matrix tri-factorization algorithms suffer from a significant computational overhead when handling large-scale datasets. Thus, we also develop an efficient framework for geosocial co-clustering, called GEOsocial COarsening and DEcomposition (GEOCODE). To achieve efficient matrix tri-factorization, GEOCODE reduces the numbers of users and locations through coarsening and then decomposes the single whole matrix tri-factorization into a set of multiple smaller sub-matrix tri-factorizations. Thorough experiments conducted using real-world geosocial networks show that GEOCODE reduces the elapsed time by 19–69 times while achieving the accuracy of up to 94.8% compared with the state-of-the-art co-clustering algorithm. Furthermore, the benefit of the mapping clusterability is clearly demonstrated through a local expert recommendation application.

Details DOI

ICRA Conference 2019 Conference Paper

A Novel Robotic Suturing System for Flexible Endoscopic Surgery

Lin Cao 0002
Xiaoguo Li
Phuoc Thien Phan
Anthony Meng Huat Tiong
Jiajun Liu
Soo Jay Phee

Perforations in flexible endoscopy are life-threatening. Defect closure or suturing in flexible endoscopy has long been a critical challenge due to the confined space of the access routes and surgical sites, high dexterity and force demands of suturing tasks, as well as critical size and strength requirements of wound closure. This paper introduces a novel robotic suturing system for flexible endoscopic surgery. This system features a flexible, through-the-scope, five-degree-of-freedom robotic suturing instrument. This instrument allows the surgeon to endoscopically manipulate a needle via a master console to create running stitches and knots in flexible endoscopy, which is not possible with existing devices. Successful ex-vivo trials were conducted inside porcine colons to show how surgical stitches and knots can be endoscopically created and secured in a completely new way. This new technology will change the way how surgeons close defects or perforations in flexible endoscopic surgery.

Details

ICRA Conference 2019 Conference Paper

Pneumatically Actuated Deployable Tissue Distension Device for NOTES for Colon

Muneaki Miyasaka
Jiajun Liu
Lin Cao 0002
Soo Jay Phee

When performing some surgical tasks inside colon with NOTES technology, colon tissue could block the task space and occlude the endoscopic vision. In order to solve this problem, we developed a pneumatically driven deployable and undeployable structure which can distend collapsing tissue and can be delivered through a 4. 5 mm endoscopic channel. The structure is designed to be flexible enough to pass through colon's tortuous pathway. Also, it is designed to hold its shape without continually applying air pressure after deployment. This allows to make use of an endoscopic channel for the other surgical instruments. Besides, due to the compliant nature of the device, it is safe to deploy inside a smaller space than its maximum deployable size. The functionality of the device was verified with an in-vitro experiment. The structure was successfully deployed inside a pig's colon with an inner diameter of 60 mm by applying 3. 5 bars of air pressure and created a sufficient task space for surgical operations.

Details