arXiv subjects

Feng Li

Publications and source records attributed to Feng Li.

At least 19 recordsLinked to original sources

arXiv2026

SphereSOD: Geometry-Structure Coupled Learning for 360 Salient Object Detection

360{\deg} salient object detection (SOD) aims to accurately segment salient regions across a full field of view. However, equirectangular projection (ERP) introduces severe spatial distortion when mapping the spherical domain onto a planar representation. Existing methods mainly focus on compensating projection distortion while overlooking the interaction between panoramic geometry and salient object structure during feature perception and prediction refinement. To this end, we propose SphereSOD, an ERP-native framework that couples panoramic geometry with evolving salient structures. Specifically, spherical geometry governs feature sampling and spatial weighting, while coarse-grained saliency and contour prediction influence context aggregation during the progressive decoding process. SphereSOD first initializes deformable sampling based on spherical projection geometry and then employs bounded, content-adaptive offsets, yielding features that are better aligned with the underlying panoramic geometry. Subsequently, the decoder performs structure-guided context aggregation and progressive refinement to recover complete salient regions and accurate boundaries. Extensive experiments on three public 360{\deg} SOD benchmarks demonstrate state-of-the-art performance and a favorable accuracy-efficiency trade-off, supporting structurepreserving inference directly in ERP space as a promising alternative to projection-heavy panoramic pipelines.

cs.CV↗

arXiv2026

Deploying and Evaluating a Smart-Agriculture Agentic Engine for Full-Season Soybean Farm Operations

This paper presents FAIRY, a full-stack smart-agriculture agent system developed for and deployed to an operating soybean research farm at Harbin Institute of Technology's smart-agriculture site. We develop FAIRY to execute and evaluate agentic agronomic operations on full-season spatiotemporal workflows that span ridge preparation, planting, irrigation, fertilization, pest and disease treatment, harvest, grain handling, drying, and storage. FAIRY integrates APIs and infrastructure across production-grade machinery, fixed soil and canopy sensors, multispectral and thermal drones, satellite vegetation products, a weather station, calibrated crop-process models, agronomic records, and multi-season yield histories. The system is built around the novel "everything is an event" execution paradigm, which represents spatiotemporal world evolution, remote sensing and UAV observations, sensor readings, crop-growth transitions, machinery actions, and management interventions as state-changing events in a shared farm process engine. On top of this event-driven world model, FAIRY implements a complete agentic stack: a knowledge library of atomic agronomic skills; multi-agent controller and orchestration backends; frontier- and edge-model execution; full-path trace logging; and deployment profiling on local nodes. We use FAIRY to evaluate nine state-of-the-art agent controllers across one hundred full-season soybean scenarios that preserve the operational coupling between spatial observations in a 64-ridge field, temporal decision sequences, agronomic constraints, delayed effects, and final yield. We develop an evaluation suite that combines agentic success, full-path spatiotemporal correctness, token cost, and edge-device runtime.

cs.AI↗

arXiv2026

PailitaoGR: Latent Think-with-Images for Generative Image Retrieval

Generative retrieval has demonstrated strong performance by directly generating product semantic identifiers (SIDs). Extending this paradigm to image search, however, is nontrivial because real-world query images contain diverse information, including the search target, useful auxiliary evidence, and irrelevant visual content. This requires the model to identify and focus on the search target while selectively utilizing auxiliary evidence. In this paper, we propose \textbf{PailitaoGR}, a \emph{Latent Think-with-Images} method for generative image retrieval, which internalizes target-focused perception and selective auxiliary-evidence utilization into a the generative retrieval model, enabling \textit{Zooming without Cropping} and \textit{Reading without OCR}. Specifically, we design a target-focused perception mechanism that identifies and enhances visual tokens of the search target, consisting of a target Enhancer and a learning strategy based on on-policy distillation and attention guidance loss, enabling the model to focus on search-target regions. We also design a selective auxiliary-evidence utilization mechanism that identifies and enhances visual tokens of auxiliary evidence, including an auxiliary enhancer and an in-capacity incremental contrastive distillation strategy, enabling the model to exploit auxiliary evidence. We construct training and validation sets sampled from real-world online image-search logs. Experiments show that our method outperforms existing baselines by an average of 13.8\%, validating its effectiveness.

cs.CV↗

arXiv2026

On-Policy Self-Distillation in Diffusion Models

Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint rewards do not specify how an intermediate denoising prediction should change. We introduce DiffusionOPSD as an on-policy self-distillation framework that converts image-level reward guidance into explicit targets for clean-output predictions at sampled queries. At each outer iteration, a frozen behavior policy generates trajectories and supplies query states and anchors. Reward gradients construct bounded positive and negative targets around each anchor. The trainable policy fits these targets as detached supervision through finite fitting before an exponential moving average update refreshes the behavior policy. This setup lets us measure target construction and finite realization separately. Controlled same-query experiments show that larger target-construction gains do not necessarily translate into larger realized gains after a single fitting update. Across SD 3.5-M and the step-distilled Z-Image-Turbo, our approach achieves the best final held-out scores in 19 of 20 reward-matched settings across two backbones and ten evaluators. It outperforms the strongest competing method by up to 44.0% and reduces training GPU-hours relative to DiffusionNFT by 40% on SD 3.5-M and 63% on Z-Image-Turbo. These results support on-policy self-distillation as an efficient and analyzable approach to diffusion post-training by converting image-level reward guidance into explicit and continually refreshed intermediate supervision, thereby opening a path toward more efficient and diagnosable alignment.

cs.CV↗

arXiv2026

Collective Blinking of Upconversion Emission in Lanthanide-doped Nanocrystals

Fluorescence blinking, often regarded as a limitation for stable emitters, can enable super-resolution localization microscopy and serve as a versatile reporter of the photophysical states of quantum emitters and their interactions with local environment. However, conventional blinking emitters are typically single quantum systems with Stokes-shifted fluorescence, making them susceptible to autofluorescence background, weak signal, and irreversible photodegradation under prolonged excitation. In contrast, single lanthanide-doped upconversion nanocrystals are effectively background-free anti-Stokes emitters and demonstrate robust resistance to photodegradation, yet they are generally considered non-blinking owing to the presence of a large ensemble of uncorrelated emitting lanthanide ions within a single nanocrystal. Here we report the discovery and control of collective blinking in the upconversion luminescence of thousands of lanthanide ions within a single nanocrystal. The blinking exhibits on-off intensity ratio exceeding 10, persists for over 15 hours (over 10,000 cycles) without discernible photodegradation, and can be reversibly controlled by adjusting the excitation power. We elucidate a universal, activator-independent upconversion blinking mechanism, whereby a single quencher, stochastically generated via a cooperative multi-ion process, can intercept delocalized excitation energy within the Yb3+ sensitizer network and darken the whole nanocrystal. Benefiting from the high-contrast, long-term photostable blinking and background-free emission, we achieve robust super-resolution localization microscopy that resolves individual nanocrystals in aggregates with 1.2 nm precision. This work establishes a general strategy to realize and control collective blinking in photostable multi-emitter nanosystems, opening new opportunities in nanoscience, bioimaging, and quantum technologies.

physics.optics↗

arXiv2026

3D Topologically Polarized Elastic Metamaterials Enable Asymmetric Energy Isolation at Low Frequencies

Topologically polarized elasticity has been extensively studied in lower-dimensions, yet its three-dimensional (3D) counterpart remains largely unexplored. Here, we demonstrate omnidirectional topological elasticity in 3D structures that incorporate bending stiffness, which elevates zero-frequency topological mechanical states into finite-frequency phononic modes. These modes are localized at a single boundary, creating a pronounced stiffness contrast in both static and finite-frequency dynamic regimes. This three-dimensional structure exhibits highly polarized mechanical behavior across all spatial dimensions, establishing omnidirectional asymmetric topological elasticity. Experimental and numerical results confirm robust, asymmetric energy isolation, arising from the interplay between bulk topological polarization and boundary-localized surface modes. Our findings establish a paradigm for 3D metamaterials, with promising applications in vibration shielding and directional wave manipulation.

cond-mat.soft↗

arXiv2026

Record Loss Sets a Rare-Trajectory Limit on Quantum Purification

Continuous quantum feedback uses time-resolved measurement records to steer monitored systems toward pure states. Yet how the information available to a controller determines the ultimate purification speed remains unresolved. We establish this relation for a qubit under fixed-spectrum Hermitian monitoring with detector loss, obtaining the exact long-time impurity-moment spectrum optimized over causal basis controls at each horizon. Rare records with nearly canceled evidence then make all moments from half order upward decay at the Bhattacharyya information rate between two quantum nondemolition record laws. Aligned quantum nondemolition monitoring preserves that binary distinguishability and attains the limit, while complete detection restores an order-dependent branch. The mechanism extends to higher dimensions, where an attainable rank-two ceiling lies above the full-rank qutrit upper bound over a finite moment interval, establishing retained record distinguishability as a purification resource.

quant-ph↗

arXiv2026

Efficiency-Induced Freezing in Quantum-State Purification

Any nonzero detection loss qualitatively changes feedback-controlled purification under diffusive monitoring. In every finite dimension, we prove a sharp, dimension-independent ceiling on the decay of trajectory-averaged impurity moments, uniformly over admissible predictable feedback protocols.Below unit efficiency, this ceiling becomes independent of moment order above a critical value and is attained on extremal rank-two quantum-nondemolition (QND) faces. For generic observable spectra, a determinant-root law precludes every full-rank state from attaining this boundary rate over an explicit moment-order interval. For qubits at $0<\eta<1$, the frozen rate is the exact optimum, set by rare, persistently mixed trajectories. Parameter-free finite-action scaling functions resolve both the rounded QND moment-order transition and the near-unit QND--always-unbiased crossover.

quant-ph↗

arXiv2026

Geometry-Aware Visual Odometry for Bronchoscopic Navigation via High-Gain Observer Fusion

Navigational bronchoscopy is critical for pulmonary interventions, yet current platforms depend heavily on pre-operative CT or external sensors, limiting their use in critical care and resource-constrained settings. Vision-only navigation offers a scalable alternative, but conventional visual odometry (VO) struggles with texture-poor airway images, specularities, and the vanishing-point singularities of tubular anatomy, leading to frequent tracking failures and drift. We present a geometry-aware VO framework that explicitly leverages vanishing-point cues from airway lumens. Detected lumens are back-projected to 3D rays, whose weighted fusion yields a stable forward heading even when parallax cues are absent. This heading, together with looming-based velocity estimates, is fused with noisy VO outputs using a bespoke high-gain observer that enforces airway-following priors and rejects drift. We validate the method on ex-vivo mechanically ventilated human lungs with electromagnetic tracking ground truth. Compared to state-of-the-art pipelines (ORB-SLAM2, LoFTR-VO, DPVO), our approach reduces absolute trajectory error by more than 50% and achieves the lowest relative pose error across all test sequences.

cs.RO↗

arXiv2026

Sparse-Aware Vector Quantization for Bandwidth-Efficient Collaborative 3D Semantic Occupancy Prediction

Collaborative perception extends single-agent perception by enabling multiple vehicles to exchange complementary perceptual information. However, it introduces an inherent trade-off between perception gain and communication overhead, which is particularly severe for 3D semantic occupancy prediction that relies on fine-grained spatial structures. Existing methods typically compress 3D features into 2D, causing severe spatial information loss, or transmit dense 3D representations, hindering real-world deployment. To overcome these limitations, we propose a bandwidth-efficient collaborative Vector Quantization Semantic Occupancy Prediction (VQSOP) framework. VQSOP employs a Sparse-Aware Vector Quantization (SAVQ) mechanism that exploits 3D scene sparsity to compactly encode informative regions, drastically reducing communication overhead while preserving complete geometric context. Furthermore, to enhance structural consistency and feature continuity, we design a Dual-Branch Adaptive Spatial Refinement (ASR) module that dynamically fuses local high-frequency details with broad contextual semantics. Extensive experiments demonstrate that our approach achieves state-of-the-art performance while reducing communication volume by up to 82x.

cs.CV↗

arXiv2026

Search for L4 Earth Trojan asteroids with the 2.5-meter Wide Field Survey Telescope

Earth Trojan asteroids (ETAs) are a mysterious population, and dynamically stable ETAs, if primordial, could be "living fossils" of the early solar system. To date, there are only two known ETAs, but both are temporary ETAs. The aim of our survey is to discover new temporary or stable ETAs; in the absence of detections, we derive upper limits on the population of stable ETAs. We conducted the largest wide-area survey of the Earth's L4 Lagrange point region so far using the Wide Field Survey Telescope, covering about 236.74 deg^2, corresponding to 33.24% of the probability coverage for sky regions where dynamically stable L4 ETAs are likely to reside. No new ETAs were detected in our survey. We place a cumulative upper limit of N(H < 19.1) < 19 on the stable population of objects larger than ~520 m (for an assumed albedo of 0.15). This represents the most stringent constraint on the ETA population to date.

astro-ph.EP↗

arXiv2026

ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations

This paper introduces ARM, a discrete representation-based AutoRegressive Model that unifies image understanding, generation, and editing within a next-token prediction framework. ARM is built on three efforts: first, we train a discrete semantic visual tokenizer that maps images into compact token sequences. Our tokenizer is supervised with multiple objectives that jointly promote semantic discriminability, language alignment and faithful reconstruction, thereby supporting diverse tasks in a shared latent space. With this, we train a 7B autoregressive model over large-scale text and image token sequences, seamlessly developing vision-language perception and generation capabilities. Finally, to further improve preference-aligned behavior for text-to-image generation and instruction-guided editing, ARM applies reinforcement learning (RL) to optimize task-level objectives such as visual quality, instruction adherence, and edit consistency. Surprisingly, the results show that RL not only substantially improves performance on the target tasks (e.g., raising WISE overall from 0.50 to 0.56, GEdit-Bench-EN G_O from 5.75 to 6.68), but also induces cross-task synergy between text-to-image generation and editing. Collectively, these findings highlight autoregressive modeling, when paired with strong representations and preference optimization, as a scalable foundation for multimodal intelligence. Code: https://github.com/wdrink/ARM.

cs.CV↗

arXiv2026

DPDL: Towards Differential Privacy Preservation in Decentralized Stochastic Learning on Non-IID Data

In the paradigm of decentralized learning, a group of agents collaborate to train a global model using distributed datasets without a central server. Although the power of collaboration has been verified by many state-of-the-art studies, it entails extensive gradient information exchanging among the agents and thus induces high risk of privacy leakage for the individual agents. Moreover, in real-world applications, the training data are usually non-identically and independently distributed across the agents, inducing more challenges to enable privacy-preserved decentralized learning. To address these issues, we propose a privacy-preserved decentralized learning algorithm with non-IID data, DPDL, which leverages the notion of Differential Privacy (DP) in cross-gradient aggregation through a similarity-based calibration technique. Specifically, in each round, each agent perturbs the cross-gradients (i.e., the derivatives of its neighbors' local model in its private local data) by Gaussian noise mechanism before sharing them with its neighbors; it then adopt cosine similarity to calibrate the received perturbed cross-gradients such that the aggregation of the calibrated cross-gradients can be utilized to effectively update local model in a momentum-like manner. Our rigorous theoretical analysis not only reveals the minimum noise level required to achieve a specific level of privacy preservation, but also illustrates that our algorithm still achieves a linear speedup in training with non-IID data. We finally conduct extensive experiments on real-world dataset to validate the effectiveness of our algorithm in defending privacy attacks and in training accurate models.

cs.LG↗

arXiv2026

A Locally Deployed RAG-Based Academic Advising System for Course Selection

The correct sequence of courses in the curriculum based on prerequisites between courses is of great importance for students to develop their knowledge and skills holistically. However, students crafting this sequence in isolation frequently struggle with recognition limitations and information overload that leads to confusion. Simultaneously, education institutions encounter difficulties in providing adequate academic advice for the correct sequence due to limited education resources. To address these challenges, we propose a locally deployed RAG-based academic advising system grounded in syllabus information. By combining large language models with retrieval from structured syllabus data, the system is designed to support course selection, prerequisite understanding, and personalized study planning in a privacy-preserving manner.

cs.CL↗

arXiv2026

FGRPO: Federated GRPO with Adaptive Aggregation on Non-IID Data

Recent advances in language models have established reinforcement learning as the primary paradigm for eliciting self-correction and long-chain reasoning. While group relative policy optimization (GRPO) offers superior scalability by eliminating the critic network, deploying it on a central infrastructure entails collecting a large volume of data from distributed owners, which poses significant privacy risks. To address these concerns, we introduce federated GRPO (FGRPO), a framework designed to decentralize the fine-tuning of reasoning models across heterogeneous data owners. To effectively mitigate the instability caused by divergent reward scales across heterogeneous tasks, FGRPO incorporates an adaptive aggregation mechanism based on relative performance gain. By characterizing each client's improvement relative to its personalized historical baseline, the framework dynamically prioritizes effective learning trajectories regardless of local task difficulty. FGRPO ensures robust convergence on non-IID data while preserving data privacy.

cs.LG↗

arXiv2026

DECA: Decentralizing Block-Wise Adam for Efficient LLM Full-Parameter Fine-Tuning on Non-IID Data

Fine-tuning large language models (LLMs) in privacy-sensitive and resource-constrained environments remains challenging. Since training data are often distributed across multiple clients, decentralized fine-tuning offers a natural paradigm for collaborative adaptation without a central server. However, enabling full-parameter fine-tuning (FPFT) in this decentralized setting is difficult: FPFT provides strong adaptation capacity but incurs prohibitive resource consumption for billion-scale models. Existing decentralized LLM fine-tuning methods therefore mainly rely on parameter-efficient updates, which improve efficiency but may restrict downstream performance. Moreover, client data are typically non-IID, making decentralized optimization more vulnerable to client drift and unstable convergence. To address these challenges, we propose DECA, a resource-efficient decentralized FPFT framework for LLMs on non-IID data. DECA partitions model parameters into disjoint blocks and performs sequential block-wise Adam optimization, reducing resource consumption while preserving decentralized full-parameter adaptation. To stabilize training, DECA further introduces first- and second-order block-wise moment estimates with fresh local gradient statistics and consensus-derived discrepancy signals. We provide rigorous theoretical analysis and extensive experiments, showing that DECA achieves fast convergence, strong downstream performance, and significant resource efficiency.

cs.LG↗

arXiv2026

Spectral subsampling MCMC for L\'evy-driven continuous-time ARMA models with expensive likelihood contributions

Subsampling-based Markov chain Monte Carlo (MCMC) algorithms aim to accelerate Bayesian inference by evaluating the likelihood using only a subset of the data at each iteration. However, in many standard tall-data applications, individual likelihood contributions are inexpensive to evaluate and the resulting reductions in actual computing time are often substantially smaller than the nominal reduction in data size due to computational overhead. We study a different computational regime arising in frequency-domain inference for continuous-time processes observed at equally spaced discrete time points. This gives rise to aliasing, whereby each contribution to the Whittle likelihood requires summation over shifted frequency components, unlike standard discrete-time spectral settings where spectral evaluations do not require such summation. We demonstrate that this structure makes subsampling MCMC, a subsampling-based MCMC approach that estimates the log-likelihood using data subsampling and efficient control variates, particularly effective for reducing computational cost. We illustrate the approach for Bayesian frequency-domain inference in discretely observed continuous-time autoregressive moving average models driven by finite second-moment L\'evy processes.

stat.CO↗

arXiv2026

Functional renormalization group study of the jet quenching parameter near the QCD critical end point

We investigate the jet quenching parameter $\hat{q}$ in the QCD phase diagram within a QCD-assisted low-energy effective theory using the functional renormalization group (fRG). Following the formalism that relates $\hat{q}$ to the spectral functions of the chiral order-parameter field, we compute the $\sigma$ and $\pi$ meson contributions to $\hat{q}$ at finite temperature and baryon chemical potential from analytically continued mesonic two-point functions. We find that $\hat{q}$ receives appreciable contributions mainly above the chiral phase boundary and exhibits a pronounced enhancement at large baryon chemical potential as the chiral crossover sharpens toward the critical end point (CEP), a behavior consistent with the picture of partonic critical opalescence (PCO), a pronounced enhancement of jet transverse momentum broadening induced by the critical $\sigma$ field fluctuations.

hep-ph↗