arXiv subjects

Jialin Liu

Publications and source records attributed to Jialin Liu.

At least 37 records · Page 2Linked to original sources

arXiv2026

INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling

Building world models with spatial consistency and real-time interactivity remains a fundamental challenge in computer vision. Current video generation paradigms often struggle with a lack of spatial persistence and insufficient visual realism, making it difficult to support seamless navigation in complex environments. To address these challenges, we propose INSPATIO-WORLD, a novel real-time framework capable of recovering and generating high-fidelity, dynamic interactive scenes from a single reference video. At the core of our approach is a Spatiotemporal Autoregressive (STAR) architecture, which enables consistent and controllable scene evolution through two tightly coupled components: Implicit Spatiotemporal Cache aggregates reference and historical observations into a latent world representation, ensuring global consistency during long-horizon navigation; Explicit Spatial Constraint Module enforces geometric structure and translates user interactions into precise and physically plausible camera trajectories. Furthermore, we introduce Joint Distribution Matching Distillation (JDMD). By using real-world data distributions as a regularizing guide, JDMD effectively overcomes the fidelity degradation typically caused by over-reliance on synthetic data. Extensive experiments demonstrate that INSPATIO-WORLD significantly outperforms existing state-of-the-art (SOTA) models in spatial consistency and interaction precision, ranking first among real-time interactive methods on the WorldScore-Dynamic benchmark, and establishing a practical pipeline for navigating 4D environments reconstructed from monocular videos.

cs.CV↗

arXiv2026

Triviality Corrected Endogenous Reward

Reinforcement learning for open-ended text generation is constrained by the lack of verifiable rewards, necessitating reliance on judge models that require either annotated data or powerful closed-source models. Inspired by recent work on unsupervised reinforcement learning for mathematical reasoning using confidence-based endogenous rewards, we investigate whether this principle can be adapted to open-ended writing tasks. We find that directly applying confidence rewards leads to Triviality Bias: the policy collapses toward high-probability outputs, reducing diversity and meaningful content. We propose TCER (Triviality Corrected Endogenous Reward), which addresses this bias by rewarding the relative information gain between a specialist policy and a generalist reference policy, modulated by a probability-dependent correction mechanism. Across multiple writing benchmarks and model architectures, TCER achieves consistent improvements without external supervision. Furthermore, TCER also transfers effectively to mathematical reasoning, validating the generality of our approach across different generation tasks.

cs.CL↗

arXiv2026

HACache: Leveraging Read Performance with Cache in a Heterogeneous Array

In cost-sensitive deployments, RAID arrays may combine SSDs with different performance levels. Such heterogeneity arises when aging SSDs degrade yet remain usable, or when failed drives are replaced with new devices of explicitly better performance. While this reduces procurement cost, it creates performance challenges: traditional striping mecahnism distributes requests evenly, but slower SSDs become bottlenecks, leaving faster ones underutilized and limiting overall bandwidth to the slowest drive. To address this, we propose HACache (Heterogeneity Adaptive Cache) for read-intensive workloads. HACache introduces high-performance SSDs as read caches to rebalance request distribution. First, we formalize the request diversion problem and solve it formally. Second, to support optimal diversion ratios searching at runtime, HACache adopts a two-phase request diversion ratio adjustment mechanism. Finally, a cache capacity regulation is adopted to adapt quotas for each backend SSD based on hit rates and request diversion needs. This design maximizes bandwidth utilization. Experiments show HACache improves heterogeneous RAID read performance significantly, with bandwidth gains of about 35\% in typical mixed configurations.

cs.OS↗

arXiv2026

Expressive Power of Implicit Models: Rich Equilibria and Test-Time Scaling

Implicit models, an emerging model class, compute outputs by iterating a single parameter block to a fixed point. This architecture realizes an infinite-depth, weight-tied network that trains with constant memory, significantly reducing memory needs for the same level of performance compared to explicit models. While it is empirically known that these compact models can often match or even exceed the accuracy of larger explicit networks by allocating more test-time compute, the underlying mechanism remains poorly understood. We study this gap through a nonparametric analysis of expressive power. We provide a strict mathematical characterization, showing that a simple and regular implicit operator can, through iteration, progressively express more complex mappings. We prove that for a broad class of implicit models, this process lets the model's expressive power scale with test-time compute, ultimately matching a much richer function class. The theory is validated across four domains: image reconstruction, scientific computing, operations research, and LLM reasoning, demonstrating that as test-time iterations increase, the complexity of the learned mapping rises, while the solution quality simultaneously improves and stabilizes.

cs.LG↗

arXiv2026

EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation

Although the effectiveness of Large Language Models (LLMs) as judges (LLM-as-a-judge) has been validated, their performance remains limited in open-ended tasks, particularly in story evaluation. Accurate story evaluation is crucial not only for assisting human quality judgment but also for providing key signals to guide story generation. However, existing methods face a dilemma: prompt engineering for closed-source models suffers from poor adaptability, while fine-tuning approaches for open-source models lack the rigorous reasoning capabilities essential for story evaluation. To address this, we propose the Self-Evolving Pairwise Reasoning (EvolvR) framework. Grounded in pairwise comparison, the framework first self-synthesizes score-aligned Chain-of-Thought (CoT) data via a multi-persona strategy. To ensure data quality, these raw CoTs undergo a self-filtering process, utilizing multi-agents to guarantee their logical rigor and robustness. Finally, the evaluator trained on the refined data is deployed as a reward model to guide the story generation task. Experimental results demonstrate that our framework achieves state-of-the-art (SOTA) performance on three evaluation benchmarks including StoryER, HANNA and OpenMEVA. Furthermore, when served as a reward model, it significantly enhances the quality of generated stories, thereby fully validating the superiority of our self-evolving approach.

cs.CL↗

arXiv2026

MoToRec: Sparse-Regularized Multimodal Tokenization for Cold-Start Recommendation

Graph neural networks (GNNs) have revolutionized recommender systems by effectively modeling complex user-item interactions, yet data sparsity and the item cold-start problem significantly impair performance, particularly for new items with limited or no interaction history. While multimodal content offers a promising solution, existing methods result in suboptimal representations for new items due to noise and entanglement in sparse data. To address this, we transform multimodal recommendation into discrete semantic tokenization. We present Sparse-Regularized Multimodal Tokenization for Cold-Start Recommendation (MoToRec), a framework centered on a sparsely-regularized Residual Quantized Variational Autoencoder (RQ-VAE) that generates a compositional semantic code of discrete, interpretable tokens, promoting disentangled representations. MoToRec's architecture is enhanced by three synergistic components: (1) a sparsely-regularized RQ-VAE that promotes disentangled representations, (2) a novel adaptive rarity amplification that promotes prioritized learning for cold-start items, and (3) a hierarchical multi-source graph encoder for robust signal fusion with collaborative signals. Extensive experiments on three large-scale datasets demonstrate MoToRec's superiority over state-of-the-art methods in both overall and cold-start scenarios. Our work validates that discrete tokenization provides an effective and scalable alternative for mitigating the long-standing cold-start challenge.

cs.LG↗

arXiv2026

Lifelong Learning with Behavior Consolidation for Vehicle Routing

Recent neural solvers have demonstrated promising performance in learning to solve routing problems. However, existing studies are primarily based on one-off training on one or a set of predefined problem distributions and scales, i.e., tasks. When a new task arises, they typically rely on either zero-shot generalization, which may be poor due to the discrepancies between the new task and the training task(s), or fine-tuning the pretrained solver on the new task, which possibly leads to catastrophic forgetting of knowledge acquired from previous tasks. This paper explores a novel lifelong learning paradigm for neural VRP solvers, where multiple tasks with diverse distributions and scales arise sequentially over time. Solvers are required to effectively and efficiently learn to solve new tasks while maintaining their performance on previously learned tasks. Consequently, a novel framework called Lifelong Learning Router with Behavior Consolidation (LLR-BC) is proposed. LLR-BC consolidates prior knowledge effectively by aligning behaviors of the solver trained on a new task with the buffered ones in a decision-seeking way. To encourage more focus on crucial experiences, LLR-BC assigns greater consolidated weights to decisions with lower confidence. Extensive experiments on capacitated vehicle routing problems and traveling salesman problems demonstrate LLR-BC's effectiveness in training high-performance neural solvers in a lifelong learning setting, addressing the catastrophic forgetting issue, maintaining their plasticity, and improving zero-shot generalization ability.

cs.AI↗

arXiv2026

OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration

As high-quality public text approaches exhaustion, a phenomenon known as the Data Wall, pre-training is shifting from more tokens to better tokens. However, existing methods either rely on heuristic static filters that ignore training dynamics, or use dynamic yet optimizer-agnostic criteria based on raw gradients. We propose OPUS (Optimizer-induced Projected Utility Selection), a dynamic data selection framework that defines utility in the optimizer-induced update space. OPUS scores candidates by projecting their effective updates, shaped by modern optimizers, onto a target direction derived from a stable, in-distribution proxy. To ensure scalability, we employ Ghost technique with CountSketch for computational efficiency, and Boltzmann sampling for data diversity, incurring only 4.7\% additional compute overhead. OPUS achieves remarkable results across diverse corpora, quality tiers, optimizers, and model scales. In pre-training of GPT-2 Large/XL on FineWeb and FineWeb-Edu with 30B tokens, OPUS outperforms industrial-level baselines and even full 200B-token training. Moreover, when combined with industrial-level static filters, OPUS further improves pre-training efficiency, even with lower-quality data. Furthermore, in continued pre-training of Qwen3-8B-Base on SciencePedia, OPUS achieves superior performance using only 0.5B tokens compared to full training with 3B tokens, demonstrating significant data efficiency gains in specialized domains.

cs.CL↗

arXiv2026

Deeply Learned Robust Matrix Completion for Large-scale Low-rank Data Recovery

Robust matrix completion (RMC) is a widely used machine learning tool that simultaneously tackles two critical issues in low-rank data analysis: missing data entries and extreme outliers. This paper proposes a novel scalable and learnable non-convex approach, coined Learned Robust Matrix Completion (LRMC), for large-scale RMC problems. LRMC enjoys low computational complexity with linear convergence. Motivated by the proposed theorem, the free parameters of LRMC can be effectively learned via deep unfolding to achieve optimum performance. Furthermore, this paper proposes a flexible feedforward-recurrent-mixed neural network framework that extends deep unfolding from fix-number iterations to infinite iterations. The superior empirical performance of LRMC is verified with extensive experiments against state-of-the-art on synthetic datasets and real applications, including video background subtraction, ultrasound imaging, face modeling, and cloud removal from satellite imagery.

cs.LG↗

arXiv2026

The identification of new Herbig Ae/Be stars from LAMOST DR7

Herbig Ae/Be stars (HAeBes) are critical tracers of intermediate- and high-mass star formation, yet their census remains incomplete compared to low-mass young stellar objects like T-Tauri stars. To expand the known population, we systematically searched for HAeBes in LAMOST DR7 low-resolution spectra. Following Sun et al., we applied Uniform Manifold Approximation and Projection (UMAP) for dimensionality reduction and Support Vector Machine (SVM) classification, identifying $\sim$240,000 spectra with potential H$α$ emission. After removing contaminants (non-stellar objects, extragalactic sources, CVs, and Algol systems) and restricting to B/A-type stars, we obtained 1,835 candidates through 2MASS/WISE visual inspection. Spectral energy distribution analysis confirmed 143 sources with infrared excess ($J$-band or longer wavelengths), including 92 known HAeBes. From the remaining 51 candidates, we classified 26 with strong infrared excess as new HAeBes. Color-index analysis of confirmed HAeBes and classical Ae/Be stars (CAeBes) revealed that the $(K-W1)_0$ vs. $(W2-W3)_0$ diagram effectively separates these populations: CAeBes predominantly occupy $(K-W1)_0 \leq 0.5$ and $(W2-W3)_0 \leq 1.1$, while other regions trace transition disks ($(K-W1)_0 < 0.5$ and $(W2-W3)_0 > 1.1$), globally depleted disks ($(K-W1)_0 > 0.5$ and $(W2-W3)_0 < 1.1$), and Class I/Flat/II HAeBes ($(K-W1)_0 > 0.5$ and $(W2-W3)_0 > 1.1$). More importantly, the HAeBes exhibit a clear evolutionary gradient on this diagram, with those in the Class III, Class II, Flat-SED, and Class I evolutionary stages being effectively distinguished by concentric ellipses that are roughly centered at (0,0) with semi-major axes of $a$=1.5, $a$=3.0, and $a$=4.0, and a semi-major to semi-minor axis ratio of 1.6:1.

astro-ph.SR↗

arXiv2025

Introducing LongCat-Flash-Thinking: A Technical Report

We present LongCat-Flash-Thinking, an efficient 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model. Its advanced capabilities are cultivated through a meticulously crafted training process, beginning with long Chain-of-Thought (CoT) data cold-start and culminating in large-scale Reinforcement Learning (RL). We first employ a well-designed cold-start training strategy, which significantly enhances the reasoning potential and equips the model with specialized skills in both formal and agentic reasoning. Then, a core innovation is our domain-parallel training scheme, which decouples optimization across distinct domains (e.g., STEM, Code, Agentic) and subsequently fuses the resulting expert models into a single, nearly Pareto-optimal model. This entire process is powered by our Dynamic ORchestration for Asynchronous rollout (DORA) system, a large-scale RL framework that delivers a greater than threefold training speedup over synchronous methods on tens of thousands of accelerators. As a result, LongCat-Flash-Thinking achieves state-of-the-art performance among open-source models on a suite of complex reasoning tasks. The model exhibits exceptional efficiency in agentic reasoning, reducing average token consumption by 64.5% (from 19, 653 to 6, 965) on AIME-25, without degrading task accuracy. We release LongCat-Flash-Thinking to promote further advances in reasoning systems and agentic AI research.

cs.AI↗

arXiv2025

Style Attack Disguise: When Fonts Become a Camouflage for Adversarial Intent

With social media growth, users employ stylistic fonts and font-like emoji to express individuality, creating visually appealing text that remains human-readable. However, these fonts introduce hidden vulnerabilities in NLP models: while humans easily read stylistic text, models process these characters as distinct tokens, causing interference. We identify this human-model perception gap and propose a style-based attack, Style Attack Disguise (SAD). We design two sizes: light for query efficiency and strong for superior attack performance. Experiments on sentiment classification and machine translation across traditional models, LLMs, and commercial services demonstrate SAD's strong attack performance. We also show SAD's potential threats to multimodal tasks including text-to-image and text-to-speech generation.

cs.CL↗

arXiv2025

Expanding Horizons of Level Diversity via Multi-objective Evolutionary Learning

In recent years, the generation of diverse game levels has gained increasing interest, contributing to a richer and more engaging gaming experience. A number of level diversity metrics have been proposed in literature, which are naturally multi-dimensional, leading to conflicted, complementary, or both relationships among these dimensions. However, existing level generation approaches often fail to comprehensively assess diversity across those dimensions. This paper aims to expand horizons of level diversity by considering multi-dimensional diversity when training generative models. We formulate the model training as a multi-objective learning problem, where each diversity metric is treated as a distinct objective. Furthermore, a multi-objective evolutionary learning framework that optimises multiple diversity metrics simultaneously throughout the model training process is proposed. Our case study on the commonly used benchmark Super Mario Bros. demonstrates that our proposed framework can enhance multi-dimensional diversity and identify a Pareto front of generative models, which provides a range of tradeoffs among playability and two representative diversity metrics, including a content-based one and a player-centered one. Such capability enables decision-makers to make informed choices when selecting generators accommodating a variety of scenarios and the diverse needs of players and designers.

cs.LG↗

arXiv2025

Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs

Quadratic programming (QP) is the most widely applied category of problems in nonlinear programming. Many applications require real-time/fast solutions, though not necessarily with high precision. Existing methods either involve matrix decomposition or use the preconditioned conjugate gradient method. For relatively large instances, these methods cannot achieve the real-time requirement unless there is an effective preconditioner. Recently, graph neural networks (GNNs) opened new possibilities for QP. Some promising empirical studies of applying GNNs for QP tasks show that GNNs can capture key characteristics of an optimization instance and provide adaptive guidance accordingly to crucial configurations during the solving process, or directly provide an approximate solution. However, the theoretical understanding of GNNs in this context remains limited. Specifically, it is unclear what GNNs can and cannot achieve for QP tasks in theory. This work addresses this gap in the context of linearly constrained QP tasks. In the continuous setting, we prove that message-passing GNNs can universally represent fundamental properties of convex quadratic programs, including feasibility, optimal objective values, and optimal solutions. In the more challenging mixed-integer setting, while GNNs are not universal approximators, we identify a subclass of QP problems that GNNs can reliably represent.

cs.LG↗

arXiv2025

ConZone+: Practical Zoned Flash Storage Emulation for Consumer Devices

To facilitate the understanding and efficient enhancement of software and hardware design for consumer-grade zoned flash storage, ConZone is proposed as the first emulator designed to model the resource constraints and architectural features typical of such systems. It incorporates essential components commonly deployed in consumer-grade devices, including limited logical to physical mapping caches, constrained write buffers, and hybrid flash media management. However, ConZone cannot be mounted with the file system due to the lack of in-place update capability, which is required by the metadata area of F2FS. To improve the usability of the emulator, ConZone+ extends ConZone with support for a block interface. We also provide a script to help the deployment and introduces several enhancements over the original version. Users can explore the internal architecture of consumer-grade zoned flash storage and integrate their optimizations with system software using ConZone+. We validate the accuracy of ConZone+ by comparing a hardware architecture representative of consumer-grade zoned flash storage and comparing it with the state-of-the-art. In addition, we conduct several case studies using ConZone+ to investigate the design of zoned storage and explore the inadequacies of the current file system.

cs.AR↗

arXiv2025

Ethical Considerations of Large Language Models in Game Playing

Large language models (LLMs) have demonstrated tremendous potential in game playing, while little attention has been paid to their ethical implications in those contexts. This work investigates and analyses the ethical considerations of applying LLMs in game playing, using Werewolf, also known as Mafia, as a case study. Gender bias, which affects game fairness and player experience, has been observed from the behaviour of LLMs. Some roles, such as the Guard and Werewolf, are more sensitive than others to gender information, presented as a higher degree of behavioural change. We further examine scenarios in which gender information is implicitly conveyed through names, revealing that LLMs still exhibit discriminatory tendencies even in the absence of explicit gender labels. This research showcases the importance of developing fair and ethical LLMs. Beyond our research findings, we discuss the challenges and opportunities that lie ahead in this field, emphasising the need for diving deeper into the ethical implications of LLMs in gaming and other interactive domains.

cs.CL↗

arXiv2025

Robust Dynamic Material Handling via Adaptive Constrained Evolutionary Reinforcement Learning

Dynamic material handling (DMH) involves the assignment of dynamically arriving material transporting tasks to suitable vehicles in real time for minimising makespan and tardiness. In real-world scenarios, historical task records are usually available, which enables the training of a decision policy on multiple instances consisting of historical records. Recently, reinforcement learning has been applied to solve DMH. Due to the occurrence of dynamic events such as new tasks, adaptability is highly required. Solving DMH is challenging since constraints including task delay should be satisfied. A feedback is received only when all tasks are served, which leads to sparse reward. Besides, making the best use of limited computational resources and historical records for training a robust policy is crucial. The time allocated to different problem instances would highly impact the learning process. To tackle those challenges, this paper proposes a novel adaptive constrained evolutionary reinforcement learning (ACERL) approach, which maintains a population of actors for diverse exploration. ACERL accesses each actor for tackling sparse rewards and constraint violation to restrict the behaviour of the policy. Moreover, ACERL adaptively selects the most beneficial training instances for improving the policy. Extensive experiments on eight training and eight unseen test instances demonstrate the outstanding performance of ACERL compared with several state-of-the-art algorithms. Policies trained by ACERL can schedule the vehicles while fully satisfying the constraints. Additional experiments on 40 unseen noised instances show the robust performance of ACERL. Cross-validation further presents the overall effectiveness of ACREL. Besides, a rigorous ablation study highlights the coordination and benefits of each ingredient of ACERL.

cs.NE↗

arXiv2025

A Universal Flexible Neuromorphic Tactile System with Multithreshold Strategy

Extremely increased unstructured data brought by the large-scale intelligent sensing devices application have big challenges not only in data storing and processing but also power consumption surging. Therefore, to improve energy efficiency and processing speed, a new generation system structure and construction strategy is necessary. Most biological nervous systems, especially the tactile system, have a good flexibility and data processing performance with low power usage. Inspired from this mechanism, to optimize the intelligent system, we report a universal fully flexible neuromorphic perception system with a strong compatibility and multi-threshold signal processing strategy by mimicking tactile nervous system. Peak signal accumulated from spike encoded sensor signal in front-end processing unit can be used for recognition task directly since the bionic synaptic plasticity. Compared with conventional systems, power consumption of our system significantly decreases about 1 order of magnitude in a same recognition task. What is more, the design of voltage-based matching circuit and multithreshold processing circuit provide an excellent compatibility and multi-signal processing capability in our system. In feasibility verification, our system can output trend of different input signals (continuous signal and frequency signal etc.) accurately and have a high recognition accuracy of 90% in the symbol pattern and 90% in Morse code. These properties of our neuromorphic system show a great application potential in intelligent devices and bionic robots.

cs.NE↗