arXiv subjects

Dong Jin

Publications and source records attributed to Dong Jin.

14 recordsLinked to original sources

arXiv2026

GSTEP: Global Spatio-Temporal Density-Driven Visual Token Pruning for Efficient Video Large Language Models

Video large language models (VideoLLMs) achieve strong video understanding performance, but their inference remains expensive due to the large number of redundant spatio-temporal visual tokens in long videos. Existing token pruning methods alleviate this cost by reducing redundant tokens, yet most of them rely on segment-level local pruning, where videos are partitioned into isolated segments and tokens are selected independently within each segment. Such designs may under-preserve short but semantically dense segments and discard tokens that appear non-salient locally but remain critical from a global perspective. To address this issue, we propose GSTEP (Global Spatio-Temporal Density Pruning), a plug-and-play pruning framework that models video as a continuous spatio-temporal information flow. GSTEP constructs a token-level spatio-temporal density by combining a continuous temporal density, obtained from a smoothed centered frame-level change signal, with intra-frame spatial density, and then performs global token sampling by jointly balancing information density and coverage. Extensive experiments on multiple VideoLLMs and public benchmarks demonstrate that GSTEP consistently achieves strong accuracy-efficiency trade-offs and generalizes well across model architectures and evaluation settings. On LLaVA-OneVision-7B, GSTEP prunes 75% of visual tokens, preserves up to 100.2% of the original average performance across benchmarks, and achieves a 1.17 end-to-end speedup.

cs.CV↗

arXiv2026

Rethinking Stepwise Model Routing: A Cost-Efficient Table Reasoning Perspective

Large Reasoning Models (LRMs) achieve strong performance on table reasoning tasks but incur substantial inference cost due to long reasoning traces. Stepwise model routing mitigates this issue by dynamically assigning reasoning steps to smaller or larger models. However, stepwise model routing for table reasoning remains underexplored. Through empirical analysis, we find that reasoning steps involving tables contain two types of tokens with distinct uncertainty distributions: table tokens grounded in table structure, such as cell values and headers, and text tokens representing surrounding natural-language reasoning. The uncertainty of both token types is correlated with the risk that the model makes an error in the next reasoning step. However, existing methods fail to model them separately, leading to suboptimal routing decisions. To address this, we propose EcoTab, a table-aware stepwise routing framework for efficient table reasoning. At each reasoning step, EcoTab separately estimates the uncertainties of table tokens and text tokens, maps them to next-step failure risks for the small model, and combines the two risks for routing. Experiments on multiple table reasoning benchmarks show that EcoTab consistently outperforms strong baselines and achieves a better balance between accuracy and efficiency.

cs.CL↗

arXiv2026

Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Search

Table Question Answering (TableQA) benefits significantly from table pruning, which extracts compact sub-tables by eliminating redundant cells to streamline downstream reasoning. However, existing pruning methods typically rely on sequential revisions driven by unreliable critique signals, often failing to detect the loss of answer-critical data. To address this limitation, we propose TabTrim, a novel table pruning framework which transforms table pruning from sequential revisions to gold trajectory-supervised parallel search. TabTrim derives a gold pruning trajectory using the intermediate sub-tables in the execution process of gold SQL queries, and trains a pruner and a verifier to make the step-wise pruning result align with the gold pruning trajectory. During inference, TabTrim performs parallel search to explore multiple candidate pruning trajectories and identify the optimal sub-table. Extensive experiments demonstrate that TabTrim achieves state-of-the-art performance across diverse tabular reasoning tasks: TabTrim-8B reaches 73.5% average accuracy, outperforming the strongest baseline by 3.2%, including 79.4% on WikiTQ and 61.2% on TableBench.

cs.CL↗

arXiv2025

SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models

Existing alignment methods for preference optimization of large language models (LLMs) aim to enhance model performance by utilizing pairs of positive and negative samples. However, due to the limited capacity of models in scoring or generating responses, the quality of positive and negative samples may become similar during training, which complicates optimization for preference learning. To address this issue, we introduce SeaPO, a Strategic Error Amplification method that leverages three error types commonly occurring in LLMs to introduce specific error patterns into the model Preference Optimization. This strategy ensures that negative samples are more erroneous than positive samples and preference-based training is employed to mitigate the occurrence of these errors, thereby enhancing model performance. Evaluations across five capability dimensions and different model scales (1.5B to 14B) demonstrate that the generated data significantly improved overall model performance, particularly in terms of truthfulness, with improvements of 5-10 percentage points observed. Further analysis reveals that task performance varies depending on the error types introduced. Injecting the most common error types improves performance in related tasks, while a mix of error types leads to a broader performance enhancement: most tasks show stable improvements, while a few tasks exhibit significant gains.

cs.CL↗

arXiv2025

When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables

Table question answering (TableQA) is a fundamental task in natural language processing (NLP). The strong reasoning capabilities of large language models (LLMs) have brought significant advances in this field. However, as real-world applications involve increasingly complex questions and larger tables, substantial noisy data is introduced, which severely degrades reasoning performance. To address this challenge, we focus on improving two core capabilities: Relevance Filtering, which identifies and retains information truly relevant to reasoning, and Table Pruning, which reduces table size while preserving essential content. Based on these principles, we propose EnoTab, a dual denoising framework for complex questions and large-scale tables. Specifically, we first perform Evidence-based Question Denoising by decomposing the question into minimal semantic units and filtering out those irrelevant to answer reasoning based on consistency and usability criteria. Then, we propose Evidence Tree-guided Table Denoising, which constructs an explicit and transparent table pruning path to remove irrelevant data step by step. At each pruning step, we observe the intermediate state of the table and apply a post-order node rollback mechanism to handle abnormal table states, ultimately producing a highly reliable sub-table for final answer reasoning. Finally, extensive experiments show that EnoTab achieves outstanding performance on TableQA tasks with complex questions and large-scale tables, confirming its effectiveness.

cs.CL↗

arXiv2025

APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training

Large Language Models (LLMs) often require domain-specific fine-tuning to address targeted tasks, which risks degrading their general capabilities. Maintaining a balance between domain-specific enhancements and general model utility is a key challenge. This paper proposes a novel approach named APT (Weakness Case Acquisition and Iterative Preference Training) to enhance domain-specific performance with self-generated dis-preferred weakness data (bad cases and similar cases). APT uniquely focuses on training the model using only those samples where errors occur, alongside a small, similar set of samples retrieved for this purpose. This targeted training minimizes interference with the model's existing knowledge base, effectively retaining generic capabilities. Experimental results on the LLama-2 and Mistral-V0.3 models across various benchmarks demonstrate that APT ensures no reduction in generic capacity and achieves superior performance on downstream tasks compared to various existing methods. This validates our method as an effective strategy for enhancing domain-specific capabilities without sacrificing the model's broader applicability.

cs.CL↗

arXiv2025

SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMs

Large Language models (LLMs) have demonstrated significant potential in text-to-SQL reasoning tasks, yet a substantial performance gap persists between existing open-source models and their closed-source counterparts. In this paper, we introduce SQLForge, a novel approach for synthesizing reliable and diverse data to enhance text-to-SQL reasoning in LLMs. We improve data reliability through SQL syntax constraints and SQL-to-question reverse translation, ensuring data logic at both structural and semantic levels. We also propose an SQL template enrichment and iterative data domain exploration mechanism to boost data diversity. Building on the augmented data, we fine-tune a variety of open-source models with different architectures and parameter sizes, resulting in a family of models termed SQLForge-LM. SQLForge-LM achieves the state-of-the-art performance on the widely recognized Spider and BIRD benchmarks among the open-source models. Specifically, SQLForge-LM achieves EX accuracy of 85.7% on Spider Dev and 59.8% on BIRD Dev, significantly narrowing the performance gap with closed-source methods.

cs.CL↗

arXiv2021

Parallel Simulation of Quantum Networks with Distributed Quantum State Management

Quantum network simulators offer the opportunity to cost-efficiently investigate potential avenues to building networks that scale with the number of users, communication distance, and application demands by simulating alternative hardware designs and control protocols. Several quantum network simulators have been recently developed with these goals in mind. However, as the size of the simulated networks increases, sequential execution becomes time consuming. Parallel execution presents a suitable method for scalable simulations of large-scale quantum networks, but the unique attributes of quantum information create some unexpected challenges. In this work we identify requirements for parallel simulation of quantum networks and develop the first parallel discrete event quantum network simulator by modifying the existing serial SeQUeNCe simulator. Our contributions include the design and development of a quantum state manager (QSM) that maintains shared quantum information distributed across multiple processes. We also optimize our parallel code by minimizing the overhead of the QSM and decreasing the amount of synchronization among processes. Using these techniques, we observe a speedup of 2 to 25 times when simulating a 1,024-node linear network with 2 to 128 processes. We also observe efficiency greater than 0.5 for up to 32 processes in a linear network topology of the same size and with the same workload. We repeat this evaluation with a randomized workload on a caveman network. Finally, we also introduce several methods for partitioning networks by mapping them to different parallel simulation processes. We released the parallel SeQUeNCe simulator as an open-source tool alongside the existing sequential version.

quant-ph↗

arXiv2020

SeQUeNCe: A Customizable Discrete-Event Simulator of Quantum Networks

Recent advances in quantum information science enabled the development of quantum communication network prototypes and created an opportunity to study full-stack quantum network architectures. This work develops SeQUeNCe, a comprehensive, customizable quantum network simulator. Our simulator consists of five modules: Hardware models, Entanglement Management protocols, Resource Management, Network Management, and Application. This framework is suitable for simulation of quantum network prototypes that capture the breadth of current and future hardware technologies and protocols. We implement a comprehensive suite of network protocols and demonstrate the use of SeQUeNCe by simulating a photonic quantum network with nine routers equipped with quantum memories. The simulation capabilities are illustrated in three use cases. We show the dependence of quantum network throughput on several key hardware parameters and study the impact of classical control message latency. We also investigate quantum memory usage efficiency in routers and demonstrate that redistributing memory according to anticipated load increases network capacity by 69.1% and throughput by 6.8%. We design SeQUeNCe to enable comparisons of alternative quantum network technologies, experiment planning, and validation and to aid with new protocol design. We are releasing SeQUeNCe as an open source tool and aim to generate community interest in extending it.

quant-ph↗

arXiv2020

Deep Medical Image Analysis with Representation Learning and Neuromorphic Computing

We explore three representative lines of research and demonstrate the utility of our methods on a classification benchmark of brain cancer MRI data. First, we present a capsule network that explicitly learns a representation robust to rotation and affine transformation. This model requires less training data and outperforms both the original convolutional baseline and a previous capsule network implementation. Second, we leverage the latest domain adaptation techniques to achieve a new state-of-the-art accuracy. Our experiments show that non-medical images can be used to improve model performance. Finally, we design a spiking neural network trained on the Intel Loihi neuromorphic chip (Fig. 1 shows an inference snapshot). This model consumes much lower power while achieving reasonable accuracy given model reduction. We posit that more research in this direction combining hardware and learning advancements will power future medical imaging (on-device AI, few-shot prediction, adaptive scanning).

eess.IV↗

arXiv2019

Real-time Anomaly Detection and Classification in Streaming PMU Data

Ensuring secure and reliable operations of the power grid is a primary concern of system operators. Phasor measurement units (PMUs) are rapidly being deployed in the grid to provide fast-sampled operational data that should enable quicker decision-making. This work presents a general interpretable framework for analyzing real-time PMU data, and thus enabling grid operators to understand the current state and to identify anomalies on the fly. Applying statistical learning tools on the streaming data, we first learn an effective dynamical model to describe the current behavior of the system. Next, we use the probabilistic predictions of our learned model to define in a principled way an efficient anomaly detection tool. Finally, the last module of our framework produces on-the-fly classification of the detected anomalies into common occurrence classes using features that grid operators are familiar with. We demonstrate the efficacy of our interpretable approach through extensive numerical experiments on real PMU data collected from a transmission operator in the USA.

eess.SP↗

arXiv2019

Learning to Navigate in Indoor Environments: from Memorizing to Reasoning

Autonomous navigation is an essential capability of smart mobility for mobile robots. Traditional methods must have the environment map to plan a collision-free path in workspace. Deep reinforcement learning (DRL) is a promising technique to realize the autonomous navigation task without a map, with which deep neural network can fit the mapping from observation to reasonable action through explorations. It should not only memorize the trained target, but more importantly, the planner can reason out the unseen goal. We proposed a new motion planner based on deep reinforcement learning that can arrive at new targets that have not been trained before in the indoor environment with RGB image and odometry only. The model has a structure of stacked Long Short-Term memory (LSTM). Finally, experiments were implemented in both simulated and real environments. The source code is available: https://github.com/marooncn/navbot.

cs.RO↗

arXiv2019

Homogeneous and Mixed Energy Communities Discovery with Spatial-Temporal Net Energy

Smart grid has integrated an increasing number of distributed energy resources to improve the efficiency and flexibility of power generation and consumption as well as the resilience of the power grid. The energy consumers on the power grid (e.g., households) equipped with the distributed energy resources can be considered as "microgrids" that both generate and consume electricity. In this paper, we study the energy community discovery problems which identify multiple kinds of energy communities for the microgrids to facilitate energy management (e.g., power supply adjustment, load balancing, energy sharing) on the grid, such as homogeneous energy communities (HECs), mixed energy communities (MECs), and self-sufficient energy communities (SECs). Specifically, we present efficient algorithms to discover such communities of microgrids by taking into account not only their geo-locations but also their net energy over any period. Finally, we experimentally validate the performance of the algorithms using both synthetic and real datasets.

eess.SY↗

arXiv2018

Bitcoin Payment-channels for Resource Limited IoT Devices

Resource-constrained devices are unable to maintain a full copy of the Bitcoin Blockchain in memory. This paper proposes a bidirectional payment channel framework for IoT devices. This framework utilizes Bitcoin Lightning-Network-like payment channels with low processing and storage requirements. This protocol enables IoT devices to open and maintain payment channels with traditional Bitcoin nodes without a view of the blockchain. Unlike existing solutions, it does not require a trusted third party to interact with the blockchain nor does it burden the peer-to-peer network in the way SPV clients do. The contribution of this paper includes a secure and crypto-economically fair protocol for bidirectional Bitcoin payment channels. In addition, we demonstrate the security and fairness of the protocol by formulating it as a game in which the equilibrium is reached when all players follow the protocol.

cs.CR↗