arXiv subjects

Long Qian

Publications and source records attributed to Long Qian.

At least 37 records · Page 2Linked to original sources

arXiv2025

Automated Symmetric Constructions in Discrete Geometry

We present a computational methodology for obtaining rotationally symmetric sets of points satisfying discrete geometric constraints, and demonstrate its applicability by discovering new solutions to some well-known problems in combinatorial geometry. Our approach takes the usage of SAT solvers in discrete geometry further by directly embedding rotational symmetry into the combinatorial encoding of geometric configurations. Then, to realize concrete point sets corresponding to abstract designs provided by a SAT solver, we introduce a novel local-search realizability solver, which shows excellent practical performance despite the intrinsic $\exists \mathbb{R}$-completeness of the problem. Leveraging this combined approach, we provide symmetric extremal solutions to the Erdős-Szekeres problem, as well as a minimal odd-sized solution with 21 points for the everywhere-unbalanced-points problem, improving on the previously known 23-point configuration. The imposed symmetries yield more aesthetically appealing solutions, enhancing human interpretability, and simultaneously offer computational benefits by significantly reducing the number of variables required to encode discrete geometric problems.

cs.DM↗

arXiv2025

Bootstrapped Model Predictive Control

Model Predictive Control (MPC) has been demonstrated to be effective in continuous control tasks. When a world model and a value function are available, planning a sequence of actions ahead of time leads to a better policy. Existing methods typically obtain the value function and the corresponding policy in a model-free manner. However, we find that such an approach struggles with complex tasks, resulting in poor policy learning and inaccurate value estimation. To address this problem, we leverage the strengths of MPC itself. In this work, we introduce Bootstrapped Model Predictive Control (BMPC), a novel algorithm that performs policy learning in a bootstrapped manner. BMPC learns a network policy by imitating an MPC expert, and in turn, uses this policy to guide the MPC process. Combined with model-based TD-learning, our policy learning yields better value estimation and further boosts the efficiency of MPC. We also introduce a lazy reanalyze mechanism, which enables computationally efficient imitation learning. Our method achieves superior performance over prior works on diverse continuous control tasks. In particular, on challenging high-dimensional locomotion tasks, BMPC significantly improves data efficiency while also enhancing asymptotic performance and training stability, with comparable training time and smaller network sizes. Code is available at https://github.com/wertyuilife2/bmpc.

cs.LG↗

arXiv2025

STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training

Video Large Language Models (Video-LLMs) have recently shown strong performance in basic video understanding tasks, such as captioning and coarse-grained question answering, but struggle with compositional reasoning that requires multi-step spatio-temporal inference across object relations, interactions, and events. The hurdles to enhancing this capability include extensive manual labor, the lack of spatio-temporal compositionality in existing data and the absence of explicit reasoning supervision. In this paper, we propose STEP, a novel graph-guided self-training method that enables Video-LLMs to generate reasoning-rich fine-tuning data from any raw videos to improve itself. Specifically, we first induce Spatio-Temporal Scene Graph (STSG) representation of diverse videos to capture fine-grained, multi-granular video semantics. Then, the STSGs guide the derivation of multi-step reasoning Question-Answer (QA) data with Chain-of-Thought (CoT) rationales. Both answers and rationales are integrated as training objective, aiming to enhance model's reasoning abilities by supervision over explicit reasoning steps. Experimental results demonstrate the effectiveness of STEP across models of varying scales, with a significant 21.3\% improvement in tasks requiring three or more reasoning steps. Furthermore, it achieves superior performance with a minimal amount of self-generated rationale-enriched training samples in both compositional reasoning and comprehensive understanding benchmarks, highlighting the broad applicability and vast potential.

cs.CV↗

arXiv2025

Topolectrical space-time circuits

Topolectrical circuits have emerged as a pivotal platform for realizing static topological states that are challenging to construct in other systems, facilitating the design of robust circuit devices. In addition to spatial dimensionality, synergistic engineering of both temporal and spatial degrees in circuit networks holds tremendous potential across diverse technologies, such as wireless communications, non-reciprocal electronics and dynamic signal controls with exotic space-time topology. However, the realization of space-time modulated circuit networks is still lacking due to the necessity for flexible modulation of node connections in both spatial and temporal domains. Here, we propose a new class of topolectrical circuits, referred to as topolectrical space-time circuits, to bridge this gap. By designing and applying a novel time-varying circuit element controlled by external voltages, we can construct circuit networks exhibiting discrete space-time translational symmetries in any dimensionality, where the circuit dynamical equation is in the same form with time-dependent Schrodinger equation. Through the implementation of topolectrical space-time circuits, three distinct types of topological space-time crystals are experimentally demonstrated, including the (1+1)-dimensional topological space-time crystal with midgap edge modes, (2+1)-dimensional topological space-time crystal with chiral edge states, and (3+1)-dimensional Weyl space-time semimetals. Our work establishes a solid foundation for the exploration of intricate space-time topological phenomena and holds potential applications in the field of dynamically manipulating electronic signals with unique space-time topology

cond-mat.mes-hall↗

arXiv2024

Enhancing Decision Transformer with Diffusion-Based Trajectory Branch Generation

Decision Transformer (DT) can learn effective policy from offline datasets by converting the offline reinforcement learning (RL) into a supervised sequence modeling task, where the trajectory elements are generated auto-regressively conditioned on the return-to-go (RTG).However, the sequence modeling learning approach tends to learn policies that converge on the sub-optimal trajectories within the dataset, for lack of bridging data to move to better trajectories, even if the condition is set to the highest RTG.To address this issue, we introduce Diffusion-Based Trajectory Branch Generation (BG), which expands the trajectories of the dataset with branches generated by a diffusion model.The trajectory branch is generated based on the segment of the trajectory within the dataset, and leads to trajectories with higher returns.We concatenate the generated branch with the trajectory segment as an expansion of the trajectory.After expanding, DT has more opportunities to learn policies to move to better trajectories, preventing it from converging to the sub-optimal trajectories.Empirically, after processing with BG, DT outperforms state-of-the-art sequence modeling methods on D4RL benchmark, demonstrating the effectiveness of adding branches to the dataset without further modifications.

cs.LG↗

arXiv2024

Axiomatization of Compact Initial Value Problems: Open Properties

This article proves the completeness of an axiomatization for initial value problems (IVPs) with compact initial conditions and compact time horizons for bounded open safety, open liveness and existence properties. Completeness systematically reduces the proofs of these properties to a complete axiomatization for differential equation invariants. This result unifies symbolic logic and numerical analysis by a computable procedure that generates symbolic proofs with differential invariants for rigorous error bounds of numerical solutions to polynomial initial value problems. The procedure is modular and works for all polynomial IVPs with rational coefficients and initial conditions and symbolic parameters constrained to compact sets. Furthermore, this paper discusses generalizations to IVPs with initial conditions/symbolic parameters that are not necessarily constrained to compact sets, achieved through the derivation of fully symbolic axioms/proof-rules based on the axiomatization.

cs.LO↗

arXiv2024

The BRAVO Semantic Segmentation Challenge Results in UNCV2024

We propose the unified BRAVO challenge to benchmark the reliability of semantic segmentation models under realistic perturbations and unknown out-of-distribution (OOD) scenarios. We define two categories of reliability: (1) semantic reliability, which reflects the model's accuracy and calibration when exposed to various perturbations; and (2) OOD reliability, which measures the model's ability to detect object classes that are unknown during training. The challenge attracted nearly 100 submissions from international teams representing notable research institutions. The results reveal interesting insights into the importance of large-scale pre-training and minimal architectural design in developing robust and reliable semantic segmentation models.

cs.CV↗

arXiv2024

Grounded Answers for Multi-agent Decision-making Problem through Generative World Model

Recent progress in generative models has stimulated significant innovations in many fields, such as image generation and chatbots. Despite their success, these models often produce sketchy and misleading solutions for complex multi-agent decision-making problems because they miss the trial-and-error experience and reasoning as humans. To address this limitation, we explore a paradigm that integrates a language-guided simulator into the multi-agent reinforcement learning pipeline to enhance the generated answer. The simulator is a world model that separately learns dynamics and reward, where the dynamics model comprises an image tokenizer as well as a causal transformer to generate interaction transitions autoregressively, and the reward model is a bidirectional transformer learned by maximizing the likelihood of trajectories in the expert demonstrations under language guidance. Given an image of the current state and the task description, we use the world model to train the joint policy and produce the image sequence as the answer by running the converged policy on the dynamics model. The empirical results demonstrate that this framework can improve the answers for multi-agent decision-making problems by showing superior performance on the training and unseen tasks of the StarCraft Multi-Agent Challenge benchmark. In particular, it can generate consistent interaction sequences and explainable reward functions at interaction states, opening the path for training generative models of the future.

cs.AI↗

arXiv2024

Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning

Large Language Models (LLMs) demonstrate remarkable proficiency in comprehending and handling text-based tasks. Many efforts are being made to transfer these attributes to video modality, which are termed Video-LLMs. However, existing Video-LLMs can only capture the coarse-grained semantics and are unable to effectively handle tasks related to comprehension or localization of specific video segments. In light of these challenges, we propose Momentor, a Video-LLM capable of accomplishing fine-grained temporal understanding tasks. To support the training of Momentor, we design an automatic data generation engine to construct Moment-10M, a large-scale video instruction dataset with segment-level instruction data. We train Momentor on Moment-10M, enabling it to perform segment-level reasoning and localization. Zero-shot evaluations on several tasks demonstrate that Momentor excels in fine-grained temporally grounded comprehension and localization.

cs.CV↗

arXiv2024

Navigate Biopsy with Ultrasound under Augmented Reality Device: Towards Higher System Performance

Purpose: Biopsies play a crucial role in determining the classification and staging of tumors. Ultrasound is frequently used in this procedure to provide real-time anatomical information. Using augmented reality (AR), surgeons can visualize ultrasound data and spatial navigation information seamlessly integrated with real tissues. This innovation facilitates faster and more precise biopsy operations. Methods: We developed an AR biopsy navigation system with low display latency and high accuracy. Ultrasound data is initially read by an image capture card and streamed to Unity via net communication. In Unity, navigation information is rendered and transmitted to the HoloLens 2 device using holographic remoting. Retro-reflective tool tracking is implemented on the HoloLens 2, enabling simultaneous tracking of the ultrasound probe and biopsy needle. Distinct navigation information is provided during in-plane and out-of-plane punctuation. To evaluate the effectiveness of our system, we conducted a study involving ten participants, for puncture accuracy and biopsy time, comparing to traditional methods. Results: Our proposed framework enables ultrasound visualization in AR with only $16.22\pm11.45ms$ additional latency. Navigation accuracy reached $1.23\pm 0.68mm$ in the image plane and $0.95\pm 0.70mm$ outside the image plane. Remarkably, the utilization of our system led to $98\%$ and $95\%$ success rate in out-of-plane and in-plane biopsy. Conclusion: To sum up, this paper introduces an AR-based ultrasound biopsy navigation system characterized by high navigation accuracy and minimal latency. The system provides distinct visualization contents during in-plane and out-of-plane operations according to their different characteristics. Use case study in this paper proved that our system can help young surgeons perform biopsy faster and more accurately.

cs.HC↗

arXiv2023

EVD Surgical Guidance with Retro-Reflective Tool Tracking and Spatial Reconstruction using Head-Mounted Augmented Reality Device

Augmented Reality (AR) has been used to facilitate surgical guidance during External Ventricular Drain (EVD) surgery, reducing the risks of misplacement in manual operations. During this procedure, the key challenge is accurately estimating the spatial relationship between pre-operative images and actual patient anatomy in AR environment. This research proposes a novel framework utilizing Time of Flight (ToF) depth sensors integrated in commercially available AR Head Mounted Devices (HMD) for precise EVD surgical guidance. As previous studies have proven depth errors for ToF sensors, we first assessed their properties on AR-HMDs. Subsequently, a depth error model and patient-specific parameter identification method are introduced for accurate surface information. A tracking pipeline combining retro-reflective markers and point clouds is then proposed for accurate head tracking. The head surface is reconstructed using depth data for spatial registration, avoiding fixing tracking targets rigidly on the patient's skull. Firstly, $7.580\pm 1.488 mm$ depth value error was revealed on human skin, indicating the significance of depth correction. Our results showed that the error was reduced by over $85\%$ using proposed depth correction method on head phantoms in different materials. Meanwhile, the head surface reconstructed with corrected depth data achieved sub-millimetre accuracy. An experiment on sheep head revealed $0.79 mm$ reconstruction error. Furthermore, a user study was conducted for the performance in simulated EVD surgery, where five surgeons performed nine k-wire injections on a head phantom with virtual guidance. Results of this study revealed $2.09 \pm 0.16 mm$ translational accuracy and $2.97\pm 0.91$ degree orientational accuracy.

eess.IV↗

arXiv2023

Scientific Machine Learning Framework to Understand Flash Graphene Synthesis

Flash Joule heating (FJH) is a far-from-equilibrium (FFE) processing method for converting low-value carbon-based materials to flash graphene (FG). Despite its promise in scalability and performance, attempts to explore the reaction mechanism have been limited due to complexity involved in the FFE process. Data-driven machine learning (ML) models effectively account for this complexity, but the model training requires considerable amount of experimental data. To tackle this challenge, we constructed a scientific ML (SML) framework trained by using both direct processing variables and indirect, physics-informed variables to predict the FG yield. The indirect variables include current-derived features (final current, maximum current, and charge density) predicted from the proxy ML models and reaction temperatures simulated from multi-physics modeling. With the combined indirect features, the final ML model achieves an average R2 score of 0.81 +/- 0.05 and an average RMSE of 12.1% +/- 2.0% in predicting the FG yield, which is significantly higher than the model trained without them (R2 of 0.73 +/- 0.05 and an RMSE of 14.3% +/- 2.0%). Feature importance analysis validates the key roles of these indirect features in determining the reaction outcome. These results illustrate the promise of this SML to elucidate FFE material synthesis outcomes, thus paving a new avenue to processing other datasets from the materials systems involving the same or different FFE processes.

physics.app-ph↗

arXiv2022

Enhancement of charge-neutral fermionic excitation near spin-flop transition\\ in magnetic Kondo material YbIr$_3$Si$_7$

The new Kondo material YbIr$_3$Si$_7$, similar to other Kondo insulators, has been reported to exhibit charge-neutral fermionic excitations through measurements of specific heat and thermal conductivity at low temperatures. We performed $^{29}$Si-NMR on YbIr$_3$Si$_7$ to investigate the magnetic response of charge-neutral fermions from a microscopic perspective. In low magnetic fields parallel to the $c$ axis, a single NMR peak in the paramagnetic state splits into three peaks below $T_{\rm N}$. In contrast, only a slight shift of the single NMR peak was observed in high magnetic fields. This spectral change as a function of the $c$-axis magnetic field is interpreted as spin-flop transition, at which the magnetic moments oriented along the $c$ axis (AF-I phase) are rotated to the $ab$ plane with ferromagnetic component along the $c$-axis (AF-II phase). In the vicinity of the spin-flop magnetic field $H_{\rm M}$, nuclear spin-lattice relaxation rate $1/T_1$ was found to be proportional to temperature at low temperatures, indicating the existence of charge-neutral fermions. Furthermore, a peak of $1/T_1$ vs. the $c$-axis magnetic field suggests that the charge-neutral fermions in YbIr$_3$Si$_7$ are closely related to its magnetic properties. Our findings shed light on the origin of charge-neutral fermions in insulators.

cond-mat.str-el↗

arXiv2022

Fine-Grained Semantically Aligned Vision-Language Pre-Training

Large-scale vision-language pre-training has shown impressive advances in a wide range of downstream tasks. Existing methods mainly model the cross-modal alignment by the similarity of the global representations of images and texts, or advanced cross-modal attention upon image and text features. However, they fail to explicitly learn the fine-grained semantic alignment between visual regions and textual phrases, as only global image-text alignment information is available. In this paper, we introduce LOUPE, a fine-grained semantically aLigned visiOn-langUage PrE-training framework, which learns fine-grained semantic alignment from the novel perspective of game-theoretic interactions. To efficiently compute the game-theoretic interactions, we further propose an uncertainty-aware neural Shapley interaction learning module. Experiments show that LOUPE achieves state-of-the-art performance on a variety of vision-language tasks. Furthermore, without any object-level human annotations and fine-tuning, LOUPE achieves competitive performance on object detection and visual grounding. More importantly, LOUPE opens a new promising direction of learning fine-grained semantics from large-scale raw image-text pairs. The repository of this work is at https://github.com/YYJMJC/LOUPE.

cs.CV↗

arXiv2022

Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in Videos

Understanding human emotions is a crucial ability for intelligent robots to provide better human-robot interactions. The existing works are limited to trimmed video-level emotion classification, failing to locate the temporal window corresponding to the emotion. In this paper, we introduce a new task, named Temporal Emotion Localization in videos~(TEL), which aims to detect human emotions and localize their corresponding temporal boundaries in untrimmed videos with aligned subtitles. TEL presents three unique challenges compared to temporal action localization: 1) The emotions have extremely varied temporal dynamics; 2) The emotion cues are embedded in both appearances and complex plots; 3) The fine-grained temporal annotations are complicated and labor-intensive. To address the first two challenges, we propose a novel dilated context integrated network with a coarse-fine two-stream architecture. The coarse stream captures varied temporal dynamics by modeling multi-granularity temporal contexts. The fine stream achieves complex plots understanding by reasoning the dependency between the multi-granularity temporal contexts from the coarse stream and adaptively integrates them into fine-grained video segment features. To address the third challenge, we introduce a cross-modal consensus learning paradigm, which leverages the inherent semantic consensus between the aligned video and subtitle to achieve weakly-supervised learning. We contribute a new testing set with 3,000 manually-annotated temporal boundaries so that future research on the TEL problem can be quantitatively evaluated. Extensive experiments show the effectiveness of our approach on temporal emotion localization. The repository of this work is at https://github.com/YYJMJC/Temporal-Emotion-Localization-in-Videos.

cs.CV↗

arXiv2022

Descriptive Combinatorics, Computable Combinatorics, and ASI Algorithms

We introduce new types of local algorithms, which we call "ASI Algorithms", and use them to demonstrate a link between descriptive and computable combinatorics. This allows us to unify arguments from the two fields, and also sometimes to port arguments from one field to the other. As an example, we generalize a computable combinatorics result of Kierstead and use it to get within one color of the Baire measurable analogue of Vizing's Theorem. We also improve Kierstead's result for multigraphs along the way.

math.LO↗

arXiv2022

Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning

Temporal grounding in videos aims to localize one target video segment that semantically corresponds to a given query sentence. Thanks to the semantic diversity of natural language descriptions, temporal grounding allows activity grounding beyond pre-defined classes and has received increasing attention in recent years. The semantic diversity is rooted in the principle of compositionality in linguistics, where novel semantics can be systematically described by combining known words in novel ways (compositional generalization). However, current temporal grounding datasets do not specifically test for the compositional generalizability. To systematically measure the compositional generalizability of temporal grounding models, we introduce a new Compositional Temporal Grounding task and construct two new dataset splits, i.e., Charades-CG and ActivityNet-CG. Evaluating the state-of-the-art methods on our new dataset splits, we empirically find that they fail to generalize to queries with novel combinations of seen words. To tackle this challenge, we propose a variational cross-graph reasoning framework that explicitly decomposes video and language into multiple structured hierarchies and learns fine-grained semantic correspondence among them. Experiments illustrate the superior compositional generalizability of our approach. The repository of this work is at https://github.com/YYJMJC/ Compositional-Temporal-Grounding.

cs.CV↗

arXiv2019

Alignment of the Virtual Scene to the Tracking Space of a Mixed Reality Head-Mounted Display

With the mounting global interest for optical see-through head-mounted displays (OST-HMDs) across medical, industrial and entertainment settings, many systems with different capabilities are rapidly entering the market. Despite such variety, they all require display calibration to create a proper mixed reality environment. With the aid of tracking systems, it is possible to register rendered graphics with tracked objects in the real world. We propose a calibration procedure to properly align the coordinate system of a 3D virtual scene that the user sees with that of the tracker. Our method takes a blackbox approach towards the HMD calibration, where the tracker's data is its input and the 3D coordinates of a virtual object in the observer's eye is the output; the objective is thus to find the 3D projection that aligns the virtual content with its real counterpart. In addition, a faster and more intuitive version of this calibration is introduced in which the user simultaneously aligns multiple points of a single virtual 3D object with its real counterpart; this reduces the number of required repetitions in the alignment from 20 to only 4, which leads to a much easier calibration task for the user. In this paper, both internal (HMD camera) and external tracking systems are studied. We perform experiments with Microsoft HoloLens, taking advantage of its self localization and spatial mapping capabilities to eliminate the requirement for line of sight from the HMD to the object or external tracker. The experimental results indicate an accuracy of up to 4 mm in the average reprojection error based on two separate evaluation methods. We further perform experiments with the internal tracking on the Epson Moverio BT-300 to demonstrate that the method can provide similar results with other HMDs.

cs.HC↗