arXiv subjects

Jingxin Li

Publications and source records attributed to Jingxin Li.

10 recordsLinked to original sources

arXiv2026

Where Is the Tradeoff in Using Third-Party API Routers for Agentic Software Development?

Third-party API routers have become a common layer that unifies access across increasingly diverse LLM providers. In coding-agent workflows, high-autonomy operation is widely adopted because it reduces interaction overhead. As a result, a third-party API router, which sits between the agent and the upstream provider, inevitably occupies the trusted path. It can inspect and modify every request and response, yet no mechanism verifies alignment between the provider's output and the repository-level actions ultimately executed by the agent. Consequently, client-side permission mechanisms may become ineffective in practice. Whether this control gap produces real, hard-to-detect effects on software development tasks remains empirically unmeasured. In this paper, we conduct an empirical study of router-side injection in coding agents, examining four intervention levels of increasing subtlety: Response Substitution (L1), Response Append (L2), LLM-Polished Injection (L3), and LLM-Polished with Distribution Alignment Injection (L4). Moreover, we develop SIDEL, a framework for trace recording, replay, injection, and defense evaluation, with a curated dataset of 400 samples. We evaluate four representative coding agents, and further evaluate whitelist-based execution control and LLM review. Router-side intervention substantially alters repository-level actions and remains difficult for existing client-side safeguards to detect. Without additional mitigations, all evaluated agents achieved a defense success rate of 0 percent across all injection levels. Client-side mitigations and reactive reviews improve resistance but do not fully restore end-to-end control, motivating provider-side output-integrity guarantees. Our code is available at https://github.com/Riyasushin/SIDEL.

cs.SE↗

arXiv2026

ToProVAR: Efficient Visual Autoregressive Modeling via Tri-Dimensional Entropy-Aware Semantic Analysis and Sparsity Optimization

Visual Autoregressive(VAR) models enhance generation quality but face a critical efficiency bottleneck in later stages. In this paper, we present a novel optimization framework for VAR models that fundamentally differs from prior approaches such as FastVAR and SkipVAR. Instead of relying on heuristic skipping strategies, our method leverages attention entropy to characterize the semantic projections across different dimensions of the model architecture. This enables precise identification of parameter dynamics under varying token granularity levels, semantic scopes, and generation scales. Building on this analysis, we further uncover sparsity patterns along three critical dimensions-token, layer, and scale-and propose a set of fine-grained optimization strategies tailored to these patterns. Extensive evaluation demonstrates that our approach achieves aggressive acceleration of the generation process while significantly preserving semantic fidelity and fine details, outperforming traditional methods in both efficiency and quality. Experiments on Infinity-2B and Infinity-8B models demonstrate that ToProVAR achieves up to 3.4x acceleration with minimal quality loss, effectively mitigating the issues found in prior work. Our code will be made publicly available.

cs.CV↗

arXiv2025

NTIRE 2025 XGC Quality Assessment Challenge: Methods and Results

This paper reports on the NTIRE 2025 XGC Quality Assessment Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2025. This challenge is to address a major challenge in the field of video and talking head processing. The challenge is divided into three tracks, including user generated video, AI generated video and talking head. The user-generated video track uses the FineVD-GC, which contains 6,284 user generated videos. The user-generated video track has a total of 125 registered participants. A total of 242 submissions are received in the development phase, and 136 submissions are received in the test phase. Finally, 5 participating teams submitted their models and fact sheets. The AI generated video track uses the Q-Eval-Video, which contains 34,029 AI-Generated Videos (AIGVs) generated by 11 popular Text-to-Video (T2V) models. A total of 133 participants have registered in this track. A total of 396 submissions are received in the development phase, and 226 submissions are received in the test phase. Finally, 6 participating teams submitted their models and fact sheets. The talking head track uses the THQA-NTIRE, which contains 12,247 2D and 3D talking heads. A total of 89 participants have registered in this track. A total of 225 submissions are received in the development phase, and 118 submissions are received in the test phase. Finally, 8 participating teams submitted their models and fact sheets. Each participating team in every track has proposed a method that outperforms the baseline, which has contributed to the development of fields in three tracks.

cs.CV↗

arXiv2024

Structure and magnetic properties of a family of two-leg spin ladder compounds Ba2RE2Ge4O13 (RE = Pr, Nd, and Gd-Ho) with strong rung interaction

Compared to the intensive investigation on the 3d transition-metal (TM)-based spin ladder compounds, less attention has been paid to the ones constructed by the rare-earth (RE) ions. Herein, we report a family of RE-based spin ladder compounds Ba2RE2Ge4O13 (RE = Pr, Nd, Gd-Ho) crystallized into the monoclinic structure with the space group C2/c. The RE ions are arranged on a two-leg spin ladder motif along the b-axis, where the rung and leg exchange interactions are bridged via the RE-O-RE pathways and RE-O-Ge-O-RE routes, respectively. Moreover, the much shorter rung distance in the RE2O12 dimer units than the leg distance suggests Ba2RE2Ge4O13 to be a strong-rung spin ladder system. All the synthesized Ba2RE2Ge4O13 (RE = Pr, Nd, Gd-Ho) compounds exhibit the dominant antiferromagnetic (AFM) interactions and absence of magnetic order down to 1.8 K. Among the family members, Ba2Dy2Ge4O13 can be described by Jeff = 1/2 Kramers doublet states, the low temperature specific heat indicates the coexistence of spin dimerized state with broad maximum at ~ 2.4 K and long-range AFM order with TN = 0.81 K. This family of Ba2RE2Ge4O13 compounds thereby provides a rare platform to investigate the novel spin ladder physics constructed by 4f electrons.

cond-mat.str-el↗

arXiv2024

R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Models

Code completion models have made significant progress in recent years. Recently, repository-level code completion has drawn more attention in modern software development, and several baseline methods and benchmarks have been proposed. However, existing repository-level code completion methods often fall short of fully using the extensive context of a project repository, such as the intricacies of relevant files and class hierarchies. Besides, the existing benchmarks usually focus on limited code completion scenarios, which cannot reflect the repository-level code completion abilities well of existing methods. To address these limitations, we propose the R2C2-Coder to enhance and benchmark the real-world repository-level code completion abilities of code Large Language Models, where the R2C2-Coder includes a code prompt construction method R2C2-Enhance and a well-designed benchmark R2C2-Bench. Specifically, first, in R2C2-Enhance, we first construct the candidate retrieval pool and then assemble the completion prompt by retrieving from the retrieval pool for each completion cursor position. Second, based on R2C2 -Enhance, we can construct a more challenging and diverse R2C2-Bench with training, validation and test splits, where a context perturbation strategy is proposed to simulate the real-world repository-level code completion well. Extensive results on multiple benchmarks demonstrate the effectiveness of our R2C2-Coder.

cs.CL↗

arXiv2024

A family of rare-earth Quasi-One-Dimensional spin-chain compounds K2RENb5O15 (RE=Ce,Pr,Nd,Sm,Gd-Ho) with large interchain distance

One-dimensional spin chain systems have received special attention to discover the novel magnetic ground states and emergent phenomena, while the magnetic studies on rare-earth (RE)-based 1D spin chain materials are still rare. Here, we report the synthesis, structure and magnetic behaviors on a family of tetragonal tungsten-bronze structure K2RENb5O15 (RE = Ce, Pr, Nd, Sm, Gd-Ho) compounds, which consist of 1D linear spin-chain structure built by RE3+ ions along the c-axis and well spatially separated by the nonmagnetic K/Nb-O polyhedrons with large interchain distances of ~ 8.80-8.88 {\AA} in the ab-plane. The low temperature magnetic measurements reveal the absence of long-range magnetic order down to 1.8 K for all serial K2RENb5O15 compounds and the dominant ferromagnetic interactions for RE=Ce,Dy and antiferromagnetic interactions for other members. Among them, K2GdNb5O15 with spin only magnetic moment S=7/2, exhibits a long-range magnetic order with TN~0.31 K and strong spin fluctuations at low temperatures due to its low-dimension characteristics. Moreover, a large magnetocaloric effect under low field change of 0-2 T is realized at temperatures below 1 K for K2GdNb5O15, letting it as an ideal candidate for adiabatic magnetic refrigeration applications at sub-kelvin temperatures. The K2RENb5O15 become a rare family of insulting RE-based magnets to explore the novel 1D spin chain physics beyond the 3d TM-based counterparts, in terms of its combination of low dimension, strong spin-orbital coupling and the rich diversity of RE ions.

cond-mat.str-el↗

arXiv2023

Ba6RE2Ti4O17 (RE= Nd, Sm,Gd, Dy-Yb): A family of Rare-earth based layered triangular lattice magnets

Rare-earth-based triangular-lattice magnets provide the fertile ground to explore the exotic quantum magnetic state. Herein, we report a new family of RE-based triangular-lattice magnets Ba6RE2Ti4O17(RE= rare earth ions) crystallized into the hexagonal structure with space group of P63 mmc, where magnetic rare earth ions form an ideal triangular lattice within the ab-plane and stack in an AA -type fashion along the c-axis. The low-temperature magnetic susceptibility results reveal all the serial compounds have the dominant antiferromagnetic interactions and an absence of magnetic ordering down to 1.8 K. The magnetization and electron spin resonance results indicate distinct magnetic anisotropy for the compounds with different RE ions. Moreover, Ba6Nd2Ti4O17 single crystal is successfully grown and it exhibits strong Ising like anisotropy with magnetic easy-axis perpendicular to the triangle-lattice plane, being a candidate to explore quantum spin liquid state with dominant Ising-type interaction.

cond-mat.mtrl-sci↗

arXiv2023

Opportunistic Transmission of Distributed Learning Models in Mobile UAVs

In this paper, we propose an opportunistic scheme for the transmission of model updates from Federated Learning (FL) clients to the server, where clients are wireless mobile users. This proposal aims to opportunistically take advantage of the proximity of users to the base station or the general condition of the wireless transmission channel, rather than traditional synchronous transmission. In this scheme, during the training, intermediate model parameters are uploaded to the server, opportunistically and based on the wireless channel condition. Then, the proactively-transmitted model updates are used for the global aggregation if the final local model updates are delayed. We apply this novel model transmission scheme to one of our previous work, which is a hybrid split and federated learning (HSFL) framework for UAVs. Simulation results confirm the superiority of using proactive transmission over the conventional asynchronous aggregation scheme for the staled model by obtaining higher accuracy and more stable training performance. Test accuracy increases by up to 13.47% with just one round of extra transmission.

cs.DC↗

arXiv2023

Ba9RE2(SiO4)6 (RE=Ho-Yb): A New Family of Rare-earth based Honeycomb Lattice Magnets

Rare-earth (RE) based honeycomb-lattice materials with strong spin-orbit coupled Jeff=1/2 moments have attracted great interest as a platform to realize Kitaev quantum spin liquid (QSL) state. Herein, we report the discovery of a new family of RE based honeycomb-lattice magnets Ba9RE2(SiO4)6(RE=Ho-Yb), which crystallize into the rhombohedral structure with space group R-3. In these serial compounds, magnetic RE3+ ions are arranged on a perfect honeycomb lattice within the ab-plane and stacked in the ABCABC-type fashion along the c-axis. All Ba9RE2(SiO4)6(RE=Ho-Yb) polycrystals exhibit the dominant antiferromagnetic interactions and absence of magnetic order down to 2 K. In combination with the magnetization and electron spin resonance (ESR) results, distinct anisotropic magnetic behaviors are proposed for compounds with different RE ions. Moreover, the synthesized Ba9Yb2Si6O24 single crystals show large magnetic frustration and no long-range magnetic ordering down to 0.15 K, being a possible QSL candidate state. These serial compounds are attractive for exploring the exotic magnetic phases of Kitaev materials with 4f electrons.

cond-mat.str-el↗

arXiv2023

Distributed Learning in Heterogeneous Environment: federated learning with adaptive aggregation and computation reduction

Although federated learning has achieved many breakthroughs recently, the heterogeneous nature of the learning environment greatly limits its performance and hinders its real-world applications. The heterogeneous data, time-varying wireless conditions and computing-limited devices are three main challenges, which often result in an unstable training process and degraded accuracy. Herein, we propose strategies to address these challenges. Targeting the heterogeneous data distribution, we propose a novel adaptive mixing aggregation (AMA) scheme that mixes the model updates from previous rounds with current rounds to avoid large model shifts and thus, maintain training stability. We further propose a novel staleness-based weighting scheme for the asynchronous model updates caused by the dynamic wireless environment. Lastly, we propose a novel CPU-friendly computation-reduction scheme based on transfer learning by sharing the feature extractor (FES) and letting the computing-limited devices update only the classifier. The simulation results show that the proposed framework outperforms existing state-of-the-art solutions and increases the test accuracy, and training stability by up to 2.38%, 93.10% respectively. Additionally, the proposed framework can tolerate communication delay of up to 15 rounds under a moderate delay environment without significant accuracy degradation.

cs.LG↗