arXiv subjects

Yi Jiang

Publications and source records attributed to Yi Jiang.

At least 55 records · Page 3Linked to original sources

arXiv2026

A Nonequilibrium Equation of State for a Turbulent 2D Bose Gas

Nonequilibrium equations of state can provide an effective thermodynamic-like description of far-from-equilibrium systems. We experimentally construct such an equation for a direct energy cascade in a turbulent two-dimensional Bose gas. Our homogeneous gas is continuously driven on a large length scale and, with matching dissipation on a small length scale, exhibits a nonthermal but stationary power-law momentum distribution. Our equation of state links the cascade amplitude with the underlying scale-invariant energy flux, and can, for different drive strengths, gas densities, and interaction strengths, be recast into a universal power-law form using scalings consistent with the Gross-Pitaevskii model.

cond-mat.quant-gas↗

arXiv2026

Machine Learning-Guided Discovery of Kagome Superconductors YRu3B2 and LuRu3B2

We report the experimental discovery of bulk superconductivity in two kagome lattice compounds, YRu$_3$B$_2$ and LuRu$_3$B$_2$, which were predicted through machine learning-accelerated high-throughput screening combined with first principles calculations. These materials crystallize in the hexagonal CeCo$_3$B$_2$-type structure with planar kagome networks formed by Ru atoms. We observe superconducting critical temperatures of $T_{c} = 0.81$~K for YRu$_3$B$_2$ and $T_{c} = 0.95$~K for LuRu$_3$B$_2$, confirmed through magnetization and specific heat measurements. Both compounds exhibit nearly 100\% superconducting volume fractions, demonstrating bulk superconductivity. Compared with LaRu$_3$Si$_2$, YRu$_3$B$_2$ and LuRu$_3$B$_2$ show a more dispersive Ru local $d_{x^2-y^2}$ quasi-flat band (and thus a reduced DOS at $E_F$) together with an overall hardening of the phonon spectrum, both of which lower the electron-phonon coupling (EPC) constant $λ$. Meanwhile, the dominant real-space EPC between Ru local $d_{x^2-y^2}$ states and the low-frequency Ru in-plane local $x$ branch remains nearly unchanged, indicating that the reduction of $λ$ originates from the $d_{x^2-y^2}$ DOS reduction and the overall phonon hardening. Superfluid weight calculations show that conventional contributions dominate over quantum geometric effects due to the dispersive nature of bands near the Fermi level. This work demonstrates the effectiveness of integrating machine learning screening, first principles theory, and experimental synthesis for accelerating the discovery of new superconducting materials.

cond-mat.supr-con↗

arXiv2026

S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs

Large language models (LLMs) equipped with chain-of-thought (CoT) achieve strong performance and offer a window into LLM behavior. However, recent evidence suggests that improvements in CoT capabilities often come with redundant reasoning processes, motivating a key question: Can LLMs acquire a fast-thinking mode analogous to human System 1 reasoning? To explore this, our study presents a self-sampling framework based on activation steering for efficient CoT learning. Our method can induce style-aligned and variable-length reasoning traces from target LLMs themselves without any teacher guidance, thereby alleviating a central bottleneck of SFT-based methods-the scarcity of high-quality supervision data. Using filtered data by gold answers, we perform SFT for efficient CoT learning with (i) a human-like dual-cognitive system, and (ii) a progressive compression curriculum. Furthermore, we explore a self-evolution regime in which SFT is driven solely by prediction-consistent data of variable-length variants, eliminating the need for gold answers. Extensive experiments on math benchmarks, together with cross-domain generalization tests in medicine, show that our method yields stable improvements for both general and R1-style LLMs. Our data and model checkpoints can be found at https://github.com/DYR1/S3-CoT.

cs.CL↗

arXiv2026

FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation

DiT models have achieved great success in text-to-video generation, leveraging their scalability in model capacity and data scale. High content and motion fidelity aligned with text prompts, however, often require large model parameters and a substantial number of function evaluations (NFEs). Realistic and visually appealing details are typically reflected in high-resolution outputs, further amplifying computational demands-especially for single-stage DiT models. To address these challenges, we propose a novel two-stage framework, FlashVideo, which strategically allocates model capacity and NFEs across stages to balance generation fidelity and quality. In the first stage, prompt fidelity is prioritized through a low-resolution generation process utilizing large parameters and sufficient NFEs to enhance computational efficiency. The second stage achieves a nearly straight ODE trajectory between low and high resolutions via flow matching, effectively generating fine details and fixing artifacts with minimal NFEs. To ensure a seamless connection between the two independently trained stages during inference, we carefully design degradation strategies during the second-stage training. Quantitative and visual results demonstrate that FlashVideo achieves state-of-the-art high-resolution video generation with superior computational efficiency. Additionally, the two-stage design enables users to preview the initial output and accordingly adjust the prompt before committing to full-resolution generation, thereby significantly reducing computational costs and wait times as well as enhancing commercial viability.

cs.CV↗

arXiv2026

New energy conversion system based on charge-exchange and inner-shell electron transitions

The rapidly growing demand for compact, high-energy power sources has outpaced the capabilities of conventional electrochemical systems that rely on outer-shell redox reactions. In this work, we present a new energy platform that utilizes inner-shell electron transitions that are previously inaccessible due to their high energy thresholds. By leveraging charge exchange processes between bare argon ions (Ar^18+) and neutral helium atoms, we provide clear evidence for the emission of soft X-ray and extreme-ultraviolet photons across a broad spectra range, resulting from inner-shell electron capture and cascade de-excitation. This strategy overcomes the limitations of radiative recombination by enhancing photon energy utilization through broader emission profiles more compatible with practical energy converters. Our design of a helium-filled chamber design enables precise control of output via pressure tuning, achieving a remarkable radiation power density of 6.29*10^8 W L^-1 and an unprecedented energy density of 2.64*10^6 Wh kg^-1. These results may provide a new and effective paradigm for energy conversion systems with ultra-high power and energy densities based on inner-shell electrons.

physics.atom-ph↗

arXiv2026

OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) improves generation quality by incorporating evidence retrieved from large external corpora. However, most existing methods rely on statically selecting top-k passages based on individual relevance, which fails to exploit combinatorial gains among passages and often introduces substantial redundancy. To address this limitation, we propose OptiSet, a set-centric framework that unifies set selection and set-level ranking for RAG. OptiSet adopts an "Expand-then-Refine" paradigm: it first expands a query into multiple perspectives to enable a diverse candidate pool and then refines the candidate pool via re-selection to form a compact evidence set. We then devise a self-synthesis strategy without strong LLM supervision to derive preference labels from the set conditional utility changes of the generator, thereby identifying complementary and redundant evidence. Finally, we introduce a set-list wise training strategy that jointly optimizes set selection and set-level ranking, enabling the model to favor compact, high-gain evidence sets. Extensive experiments demonstrate that OptiSet improves performance on complex combinatorial problems and makes generation more efficient. The source code is publicly available.

cs.AI↗

arXiv2026

ArcAligner: Adaptive Recursive Aligner for Compressed Context Embeddings in RAG

Retrieval-Augmented Generation (RAG) helps LLMs stay accurate, but feeding long documents into a prompt makes the model slow and expensive. This has motivated context compression, ranging from token pruning and summarization to embedding-based compression. While researchers have tried ''compressing'' these documents into smaller summaries or mathematical embeddings, there is a catch: the more you compress the data, the more the LLM struggles to understand it. To address this challenge, we propose ArcAligner (Adaptive recursive context *Aligner*), a lightweight module integrated into the language model layers to help the model better utilize highly compressed context representations for downstream generation. It uses an adaptive ''gating'' system that only adds extra processing power when the information is complex, keeping the system fast. Across knowledge-intensive QA benchmarks, ArcAligner consistently beats compression baselines at comparable compression rates, especially on multi-hop and long-tail settings. The source code is publicly available.

cs.CL↗

arXiv2026

NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation

We present NextFlow, a unified decoder-only autoregressive transformer trained on 6 trillion interleaved text-image discrete tokens. By leveraging a unified vision representation within a unified autoregressive architecture, NextFlow natively activates multimodal understanding and generation capabilities, unlocking abilities of image editing, interleaved content and video generation. Motivated by the distinct nature of modalities - where text is strictly sequential and images are inherently hierarchical - we retain next-token prediction for text but adopt next-scale prediction for visual generation. This departs from traditional raster-scan methods, enabling the generation of 1024x1024 images in just 5 seconds - orders of magnitude faster than comparable AR models. We address the instabilities of multi-scale generation through a robust training recipe. Furthermore, we introduce a prefix-tuning strategy for reinforcement learning. Experiments demonstrate that NextFlow achieves state-of-the-art performance among unified models and rivals specialized diffusion baselines in visual quality.

cs.CV↗

arXiv2026

VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation

Visual generation is dominated by three paradigms: AutoRegressive (AR), diffusion, and Visual AutoRegressive (VAR) models. Unlike AR and diffusion, VARs operate on heterogeneous input structures across their generation steps, which creates severe asynchronous policy conflicts. This issue becomes particularly acute in reinforcement learning (RL) scenarios, leading to unstable training and suboptimal alignment. To resolve this, we propose a novel framework to enhance Group Relative Policy Optimization (GRPO) by explicitly managing these conflicts. Our method integrates three synergistic components: 1) a stabilizing intermediate reward to guide early-stage generation; 2) a dynamic time-step reweighting scheme for precise credit assignment; and 3) a novel mask propagation algorithm, derived from principles of Reward Feedback Learning (ReFL), designed to isolate optimization effects both spatially and temporally. Our approach demonstrates significant improvements in sample quality and objective alignment over the vanilla GRPO baseline, enabling robust and effective optimization for VAR models.

cs.CV↗

arXiv2025

BARD: budget-aware reasoning distillation

While long Chain-of-Thought (CoT) distillation effectively transfers reasoning capability to smaller language models, the reasoning process often remains redundant and computational budget uncontrollable, leading to inefficient resource usage. To address this limitation, we propose \textbf{Budget-Aware Reasoning Distillation (BARD)}, a novel framework that simultaneously distills reasoning capability and enables fine-grained control over the reasoning length. BARD uses the thinking budget as a user-specified control signal, allowing the model to dynamically balance reasoning performance and computational efficiency. To achieve this concept, BARD introduces a two-phase training regimen. The first phase, Supervised Fine-Tuning (SFT) on teacher-generated long CoT data compressed to various budget levels, bootstrapping the model's understanding of budget constraints. The second phase leverages Reinforcement Learning (RL) from a reward signal in consideration of reasoning performance and budget fidelity simultaneously. Incorporating the two-phase regimen is crucial to avoiding policy degradation and ensuring that both objectives are optimized jointly. Extensive experiments demonstrate that our method empowers an 8B student model to achieve strong performance on challenging reasoning benchmarks (\textit{AIME24, AIME25, GPQA}) while providing precise and adaptive control over its reasoning length across a wide range of budgets.

cs.CL↗

arXiv2025

Phonon spectra, quantum geometry, and the Goldstone theorem

Phonons are essential quasi-particles of all crystals and play a key role in fundamental properties such as thermal transport and superconductivity. In particular, acoustic phonons can be interpreted as Goldstone modes that emerge due to the spontaneous breaking of translational symmetry. In this article, we investigate the quantum geometric contribution to the phonon spectrum in the absence of Holstein phonons. Using graphene as a case study, we decompose the dynamical matrix into distinct terms that exhibit different dependencies on the electron energy and wavefunction. We then examine the role of quantum geometry in shaping the material's phonon spectrum, and we find that removing the nontrivial quantum geometric contribution from the dynamical matrix causes the acoustic phonon modes to behave in a non-analytic fashion.

cond-mat.mes-hall↗

arXiv2025

Unveiling the Attribute Misbinding Threat in Identity-Preserving Models

Identity-preserving models have led to notable progress in generating personalized content. Unfortunately, such models also exacerbate risks when misused, for instance, by generating threatening content targeting specific individuals. This paper introduces the \textbf{Attribute Misbinding Attack}, a novel method that poses a threat to identity-preserving models by inducing them to produce Not-Safe-For-Work (NSFW) content. The attack's core idea involves crafting benign-looking textual prompts to circumvent text-filter safeguards and leverage a key model vulnerability: flawed attribute binding that stems from its internal attention bias. This results in misattributing harmful descriptions to a target identity and generating NSFW outputs. To facilitate the study of this attack, we present the \textbf{Misbinding Prompt} evaluation set, which examines the content generation risks of current state-of-the-art identity-preserving models across four risk dimensions: pornography, violence, discrimination, and illegality. Additionally, we introduce the \textbf{Attribute Binding Safety Score (ABSS)}, a metric for concurrently assessing both content fidelity and safety compliance. Experimental results show that our Misbinding Prompt evaluation set achieves a \textbf{5.28}\% higher success rate in bypassing five leading text filters (including GPT-4o) compared to existing main-stream evaluation sets, while also demonstrating the highest proportion of NSFW content generation. The proposed ABSS metric enables a more comprehensive evaluation of identity-preserving models by concurrently assessing both content fidelity and safety compliance.

cs.CR↗

arXiv2025

Adapting General-Purpose Foundation Models for X-ray Ptychography in Low-Data Regimes

The automation of workflows in advanced microscopy is a key goal where foundation models like Language Models (LLMs) and Vision-Language Models (VLMs) show great potential. However, adapting these general-purpose models for specialized scientific tasks is critical, and the optimal domain adaptation strategy is often unclear. To address this, we introduce PtychoBench, a new multi-modal, multi-task benchmark for ptychographic analysis. Using this benchmark, we systematically compare two specialization strategies: Supervised Fine-Tuning (SFT) and In-Context Learning (ICL). We evaluate these strategies on a visual artifact detection task with VLMs and a textual parameter recommendation task with LLMs in a data-scarce regime. Our findings reveal that the optimal specialization pathway is task-dependent. For the visual task, SFT and ICL are highly complementary, with a fine-tuned model guided by context-aware examples achieving the highest mean performance (Micro-F1 of 0.728). Conversely, for the textual task, ICL on a large base model is the superior strategy, reaching a peak Micro-F1 of 0.847 and outperforming a powerful "super-expert" SFT model (0-shot Micro-F1 of 0.839). We also confirm the superiority of context-aware prompting and identify a consistent contextual interference phenomenon in fine-tuned models. These results, benchmarked against strong baselines including GPT-4o and a DINOv3-based classifier, offer key observations for AI in science: the optimal specialization path in our benchmark is dependent on the task modality, offering a clear framework for developing more effective science-based agentic systems.

cs.CV↗

arXiv2025

Automated Penetration Testing with LLM Agents and Classical Planning

While penetration testing plays a vital role in cybersecurity, achieving fully automated, hands-off-the-keyboard execution remains a significant research challenge. In this paper, we introduce the "Planner-Executor-Perceptor (PEP)" design paradigm and use it to systematically review existing work and identify the key challenges in this area. We also evaluate existing penetration testing systems, with a particular focus on the use of Large Language Model (LLM) agents for this task. The results show that the out-of-the-box Claude Code and Sonnet 4.5 exhibit superior penetration capabilities observed to date, substantially outperforming all prior systems. However, a detailed analysis of their testing processes reveals specific strengths and limitations; notably, LLM agents struggle with maintaining coherent long-horizon plans, performing complex reasoning, and effectively utilizing specialized tools. These limitations significantly constrain its overall capability, efficiency, and stability. To address these limitations, we propose CHECKMATE, a framework that integrates enhanced classical planning with LLM agents, providing an external, structured "brain" that mitigates the inherent weaknesses of LLM agents. Our evaluation shows that CHECKMATE outperforms the state-of-the-art system (Claude Code) in penetration capability, improving benchmark success rates by over 20%. In addition, it delivers substantially greater stability, cutting both time and monetary costs by more than 50%.

cs.CR↗

arXiv2025

InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation

We introduce InfinityStar, a unified spacetime autoregressive framework for high-resolution image and dynamic video synthesis. Building on the recent success of autoregressive modeling in both vision and language, our purely discrete approach jointly captures spatial and temporal dependencies within a single architecture. This unified design naturally supports a variety of generation tasks such as text-to-image, text-to-video, image-to-video, and long interactive video synthesis via straightforward temporal autoregression. Extensive experiments demonstrate that InfinityStar scores 83.74 on VBench, outperforming all autoregressive models by large margins, even surpassing some diffusion competitors like HunyuanVideo. Without extra optimizations, our model generates a 5s, 720p video approximately 10x faster than leading diffusion-based methods. To our knowledge, InfinityStar is the first discrete autoregressive video generator capable of producing industrial level 720p videos. We release all code and models to foster further research in efficient, high-quality video generation.

cs.CV↗

arXiv2025

A Mathematical Model of Opinion Dynamics with Application to Vaccine Denial

Public health outcomes can be heavily influenced by the landscape of public opinion; hence, it is important to understand how that landscape changes over time. For one, opinions on public health issues are responsive to official pronouncements, whether from the governmental or professional medical establishments. Additionally, in today's world of high speed communication, opinion can also be highly responsive to the broadcast opinions of "influencers" whose large numbers of followers assure them of a broad reach. To understand the opinion landscape in a general sense, we develop an ordinary differential equation model for opinion change that is based primarily on attraction to the opinions of prominent sources. The individual opinion change model is then used to develop a Fokker-Planck-type partial differential equation model for the overall opinion landscape. This model is shown to have a stable equilibrium solution, and the dependence of the equilibrium solution on key model parameters is illustrated with examples based on opinion regarding vaccination.

physics.soc-ph↗

arXiv2025

MA-SLAM: Active SLAM in Large-Scale Unknown Environment using Map Aware Deep Reinforcement Learning

Active Simultaneous Localization and Mapping (Active SLAM) involves the strategic planning and precise control of a robotic system's movement in order to construct a highly accurate and comprehensive representation of its surrounding environment, which has garnered significant attention within the research community. While the current methods demonstrate efficacy in small and controlled settings, they face challenges when applied to large-scale and diverse environments, marked by extended periods of exploration and suboptimal paths of discovery. In this paper, we propose MA-SLAM, a Map-Aware Active SLAM system based on Deep Reinforcement Learning (DRL), designed to address the challenge of efficient exploration in large-scale environments. In pursuit of this objective, we put forward a novel structured map representation. By discretizing the spatial data and integrating the boundary points and the historical trajectory, the structured map succinctly and effectively encapsulates the visited regions, thereby serving as input for the deep reinforcement learning based decision module. Instead of sequentially predicting the next action step within the decision module, we have implemented an advanced global planner to optimize the exploration path by leveraging long-range target points. We conducted experiments in three simulation environments and deployed in a real unmanned ground vehicle (UGV), the results demonstrate that our approach significantly reduces both the duration and distance of exploration compared with state-of-the-art methods.

cs.RO↗

arXiv2025

StochEP: Stochastic Equilibrium Propagation for Spiking Convergent Recurrent Neural Networks

Spiking Neural Networks (SNNs) promise energy-efficient, sparse, biologically inspired computation. Training them with Backpropagation Through Time (BPTT) and surrogate gradients achieves strong performance but remains biologically implausible. Equilibrium Propagation (EP) provides a more local and biologically grounded alternative. However, existing EP frameworks, primarily based on deterministic neurons, either require complex mechanisms to handle discontinuities in spiking dynamics or fail to scale beyond simple visual tasks. Inspired by the stochastic nature of biological spiking mechanism and recent hardware trends, we propose a stochastic EP framework that integrates probabilistic spiking neurons into the EP paradigm. This formulation smoothens the optimization landscape, stabilizes training, and enables scalable learning in deep convolutional spiking convergent recurrent neural networks (CRNNs). We provide theoretical guarantees showing that the proposed stochastic EP dynamics approximate deterministic EP under mean-field theory, thereby inheriting its underlying theoretical guarantees. The proposed framework narrows the gap to both BPTT-trained SNNs and EP-trained non-spiking CRNNs in vision benchmarks while preserving locality, highlighting stochastic EP as a promising direction for neuromorphic and on-chip learning.

cs.ET↗