Super-resolution (SR) of satellite imagery is challenging due to the lack of paired low-/high-resolution data. Recent self-supervised SR methods overcome this limitation by exploiting the temporal redundancy in burst observations, but they lack a mechanism to quantify uncertainty in the reconstruction. In this work, we introduce a novel self-supervised loss that allows to estimate uncertainty in image super-resolution without ever accessing the ground-truth high-resolution data. We adopt a decision-theoretic perspective and show that minimizing the corresponding Bayesian risk yields the posterior mean and variance as optimal estimators. We validate our approach on a synthetic SkySat L1B dataset and demonstrate that it produces calibrated uncertainty estimates comparable to supervised methods. Our work bridges self-supervised restoration with uncertainty quantification, making a practical framework for uncertainty-aware image reconstruction.

Despite recent advances in Text-to-Video (T2V) synthesis, generating high-fidelity and dynamic motion remains a significant challenge. Existing methods primarily rely on Classifier-Free Guidance (CFG), often with explicit negative prompts (e.g. "static", "blurry"), to suppress undesired artifacts. However, such explicit negations frequently introduce unintended semantic bias and distort object integrity; a phenomenon we define as Content-Motion Drift. To address this, we propose MotionCFG, a framework that enhances motion dynamics by contrasting a target concept with its noise-perturbed counterparts. Specifically, by injecting Gaussian noise into the concept embeddings, MotionCFG creates localized negative anchors that encapsulate a broad complementary space of sub-optimal motion variations. Unlike explicit negations, this approach facilitates implicit hard negative mining without shifting the global semantic identity, allowing for a focused refinement of temporal details. Combined with a piecewise guidance schedule that confines intervention to the early denoising steps, MotionCFG consistently improves motion dynamics across state-of-the-art T2V frameworks with negligible computational overhead and minimal compromise in visual quality. Additionally, we demonstrate that this noise-induced contrastive mechanism is effective not only for sharpening motion trajectories but also for steering complex, non-linear concepts such as precise object numerosity, which are typically difficult to modulate via standard text-based guidance.

The occurrence of large-scale power outages induced by natural disasters has been on the rise in a changing climate. Such power outages often last extended durations, causing substantial financial losses and socioeconomic impacts to customers. Accurate estimation of outage duration is thus critical for enhancing the resilience of energy infrastructure under severe weather. We formulate such a task as a machine learning (ML) problem with focus on unique real-world challenges: high-order spatial dependency in the data, a moderate number of large-scale outage events, heterogeneous types of such events, and different impacts in a region within each event. To address these challenges, we develop a Bimodal Gated Graph Attention Network (BiGGAT), a graph-based neural network model, that integrates a Graph Attention Network (GAT) with a Gated Recurrent Unit (GRU) to capture the complex spatial characteristics. We evaluate the approach in a setting of inductive learning, using large-scale power outage data from six major hurricanes in the Southeastern United States. Experimental results demonstrate that BiGGAT achieves a superior performance compared to benchmark models.

In teleoperation of contact-rich manipulation tasks, selecting robot impedance is critical but difficult. The robot must be compliant to avoid damaging the environment, but stiff to remain responsive and to apply force when needed. In this paper, we present Stiffness Copilot, a vision-based policy for shared-control teleoperation in which the operator commands robot pose and the policy adjusts robot impedance online. To train Stiffness Copilot, we first infer direction-dependent stiffness matrices in simulation using privileged contact information. We then use these matrices to supervise a lightweight vision policy that predicts robot stiffness from wrist-camera images and transfers zero-shot to real images at runtime. In a human-subject study, Stiffness Copilot achieved safety comparable to using a constant low stiffness while matching the efficiency of using a constant high stiffness.

Diffusion models are the go-to method for Text-to-Image generation, but their iterative denoising processes has high inference latency. Quantization reduces compute time by using lower bitwidths, but applies a fixed precision across all denoising timesteps, leaving an entire optimization axis unexplored. We propose TMPDiff, a temporal mixed-precision framework for diffusion models that assigns different numeric precision to different denoising timesteps. We hypothesize that quantization errors accumulate additively across timesteps, which we then validate experimentally. Based on our observations, we develop an adaptive bisectioning-based algorithm, which assigns per-step precisions with linear evaluation complexity, reducing an otherwise exponential search problem. Across four state-of-the-art diffusion models and three datasets, TMPDiff consistently outperforms uniform-precision baselines at matched speedup, achieving 10 to 20% improvement in perceptual quality. On FLUX.1-dev, TMPDiff achieves 90% SSIM relative to the full-precision model at a speedup of 2.5x over 16-bit inference.

Large language model agents demonstrate expert-level reasoning, yet consistently fail on enterprise-specific tasks due to missing domain knowledge -- terminology, operational procedures, system interdependencies, and institutional decisions that exist largely as tribal knowledge. Current approaches fall into two categories: top-down knowledge engineering, which documents domain knowledge before agents use it, and bottom-up automation, where agents learn from task experience. Both have fundamental limitations: top-down efforts produce bloated, untested knowledge bases; bottom-up approaches cannot acquire knowledge that exists only in human heads. We present Demand-Driven Context (DDC), a problem-first methodology that uses agent failure as the primary signal for what domain knowledge to curate. Inspired by Test-Driven Development, DDC inverts knowledge engineering: instead of curating knowledge and hoping it is useful, DDC gives agents real problems, lets them demand the context they need, and curates only the minimum knowledge required to succeed. We describe the methodology, its entity meta-model, and a convergence hypothesis suggesting that 20-30 problem cycles produce a knowledge base sufficient for a given domain role. We demonstrate DDC through a worked example in retail order fulfillment, where nine cycles targeting an SRE incident management agent produce a reusable knowledge base of 46 entities. Finally, we propose a scaling architecture for enterprise adoption with semi-automated curation and human governance.

Diffusion-based trajectory planners can synthesize rich, multimodal action sequences for offline reinforcement learning, but their iterative denoising incurs substantial inference-time cost, making closed-loop planning slow under tight compute budgets. We study the problem of achieving diffusion-like trajectory planning behavior with one-step inference, while retaining the ability to sample diverse candidate plans and condition on the current state in a receding-horizon control loop. Our key observation is that conditional trajectory generation fails under naïve distribution-matching objectives when the similarity measure used to align generated trajectories with the dataset is dominated by unconstrained future dimensions. In practice, this causes attraction toward average trajectories, collapses action diversity, and yields near-static behavior. Our key insight is that conditional generative planning requires a conditioning-aware notion of neighborhood: trajectory updates should be computed using distances in a compact key space that reflects the condition, while still applying updates in the full trajectory space. Building on this, we introduce Keyed Drifting Policies (KDP), a one-step trajectory generator trained with a drift-field objective that attracts generated trajectories toward condition-matched dataset windows and repels them from nearby generated samples, using a stop-gradient drifted target to amortize iterative refinement into training. At inference, the resulting policy produces a full trajectory window in a single forward pass. Across standard RL benchmarks and real-time hardware deployments, KDP achieves strong performance with one-step inference and substantially lower planning latency than diffusion sampling. Project website, code and videos: https://keyed-drifting.github.io/

Modern Translation Systems heavily rely on high-quality, large parallel datasets for state-of-the-art performance. However, such resources are largely unavailable for most of the South Asian languages. Among them, Nepali and Tamang fall into such category, with Tamang being among the least digitally resourced languages in the region. This work addresses the gap by developing NepTam20K, a 20K gold standard parallel corpus, and NepTam80K, an 80K synthetic Nepali-Tamang parallel corpus, both sentence-aligned and designed to support machine translation. The datasets were created through a pipeline involving data scraping from Nepali news and online sources, pre-processing, semantic filtering, balancing for tense and polarity (in NepTam20K dataset), expert translation into Tamang by native speakers of the language, and verification by an expert Tamang linguist. The dataset covers five domains: Agriculture, Health, Education and Technology, Culture, and General Communication. To evaluate the dataset, baseline machine translation experiments were carried out using various multilingual pre-trained models: mBART, M2M-100, NLLB-200, and a vanilla Transformer model. The fine-tuning on the NLLB-200 achieved the highest sacreBLEU scores of 40.92 (Nepali-Tamang) and 45.26 (Tamang-Nepali).

The enhancement of reasoning capabilities in large language models (LLMs) has garnered significant attention, with supervised fine-tuning (SFT) and reinforcement learning emerging as dominant paradigms. While recent studies recognize the importance of reflection in reasoning processes, existing methodologies seldom address proactive reflection encouragement during training. This study focuses on mathematical reasoning by proposing a four-stage framework integrating Group Relative Policy Optimization (GRPO) with reflection reward mechanisms to strengthen LLMs' self-reflective capabilities. Besides, this approach incorporates established accuracy and format reward. Experimental results demonstrate GRPO's state-of-the-art performance through reflection-encouraged training, with ablation studies confirming the reflection reward's pivotal role. Comparative evaluations demonstrate full-parameter SFT's superiority over low-rank adaptation (LoRA) despite heightened computational demands. Building on these cumulative findings, this research substantiates GRPO's methodological significance in post-training optimization and envisions its potential to serve as a pivotal enabler for future LLM-based intelligent agents through the synergistic integration of cognitive rewards with dynamic environmental interactions.

Ophthalmic decision-making depends on subtle lesion-scale cues interpreted across multimodal imaging and over time, yet most medical foundation models remain static and degrade under modality and acquisition shifts. Here we introduce EyeWorld, a generative world model that conceptualizes the eye as a partially observed dynamical system grounded in clinical imaging. EyeWorld learns an observation-stable latent ocular state shared across modalities, unifying fine-grained parsing, structure-preserving cross-modality translation and quality-robust enhancement within a single framework. Longitudinal supervision further enables time-conditioned state transitions, supporting forecasting of clinically meaningful progression while preserving stable anatomy. By moving from static representation learning to explicit dynamical modeling, EyeWorld provides a unified approach to robust multimodal interpretation and prognosis-oriented simulation in medicine.

State-of-the-art spoken dialogue models (Défossez et al. 2024; Schalkwyk et al. 2025) use neural audio codecs to "tokenize" audio signals into a lower-frequency stream of vectorial latent representations, each quantized using a hierarchy of vector codebooks. A transformer layer allows these representations to reflect some time- and context-dependent patterns. We train probes on labeled audio data from Cole et al. (2023) to test whether the pitch trajectories that characterize English phrase-final (nuclear) intonational tunes are among these patterns. Results: Linear probes trained on the unquantized latents or some of the associated codewords yield above-chance accuracy in distinguishing eight phonologically specified nuclear tunes with monotonal pitch accents (top average test accuracy (TATA): 0.31) and the five clusters of these tunes that are robust in human speech production and perception (TATA: 0.45). Greater accuracy (TATAs: 0.74-0.89) is attained for binary distinctions between classes of rising vs. falling tunes, respectively used for questions and assertions. Information about tunes is spread among all codebooks, which calls into question a distinction between 'semantic' and 'acoustic' codebooks found in the literature. Accuracies improve with nonlinear probes, but discrimination among the five clusters remains far from human performance, suggesting a fundamental limitation of current codecs.

Audio anti-spoofing systems are typically formulated as binary classifiers distinguishing bona fide from spoofed speech. This assumption fails under layered generative processing, where benign transformations introduce distributional shifts that are misclassified as spoofing. We show that phonation-modifying voice conversion and speech restoration are treated as out-of-distribution despite preserving speaker authenticity. Using a multi-class setup separating bona fide, converted, spoofed, and converted-spoofed speech, we analyse model behaviour through self-supervised learning (SSL) embeddings and acoustic correlates. The benign transformations induce a drift in the SSL space, compressing bona fide and spoofed speech and reducing classifier separability. Reformulating anti-spoofing as a multi-class problem improves robustness to benign shifts while preserving spoof detection, suggesting binary systems model the distribution of raw speech rather than authenticity itself.

\textbf{Purpose:} C-arm fluoroscopy's 3D reconstruction relies on accurate intrinsic calibration, which is often challenging in clinical practice. This study ensures high-precision reconstruction accuracy by re-optimizing the extrinsic parameters to compensate for intrinsic calibration errors. \noindent\textbf{Methods:} We conducted both simulation and real-world experiments using five commercial C-arm systems. Intrinsic parameters were perturbed in controlled increments. Focal length was increased by 100 to 700 pixels ($\approx$20 mm to 140 mm) and principal point by 20 to 200 pixels. For each perturbation, we (1) reconstructed 3D points from known phantom geometries, (2) re-estimated extrinsic poses using standard optimization, and (3) measured reconstruction and reprojection errors relative to ground truth. \noindent\textbf{Results:} Even with focal length errors up to 500 pixels ($\approx$100 mm, assuming a nominal focal length of $\sim$1000 mm), mean 3D reconstruction error remained under 0.2 mm. Larger focal length deviations (700 pixels) elevated error to only $\approx$0.3 mm. Principal point shifts up to 200 pixels introduced negligible reconstruction error once extrinsic parameters were re-optimized, with reprojection error increases below 0.5 pixels. \noindent\textbf{Conclusion:} Moderate errors in intrinsic calibration can be effectively mitigated by extrinsic re-optimization, preserving submillimeter 3D reconstruction accuracy. This intrinsic tolerance suggests a practical pathway to relax calibration precision requirements, thereby simplifying C-arm system setup and reducing clinical workflow burden without compromising performance.

A task-specific model trained on 212,231 UK Biobank subjects to predict vascular age from PPG (AI-PPG Age) fails on a different clinical population: predictions collapse to a narrow 38-67 year range regardless of true age. Meanwhile, a general-purpose foundation model with no age-related training objective achieves lower error on the same data. We investigate why this happens and what it means for PPG-based biological age prediction. We evaluate three open-source PPG models (Pulse-PPG, PaPaGei-S, AI-PPG Age) on 906 surgical patients from PulseDB, using frozen embeddings with Ridge regression and 5-fold cross-validation. Pulse-PPG reaches MAE = 9.28 years, beating both AI-PPG Age in linear probe mode (9.72) and HR/HRV combined with demographics (9.59). Adding demographic features brings the best result down to MAE = 8.22 years (R2 = 0.517, r = 0.725). The predicted age gap correlates with diastolic blood pressure after adjusting for chronological age (r = -0.188, p = 1.2e-8), consistent with what Apple reported for their proprietary PpgAge model. The remaining gap with Apple (MAE 2.43) appears driven by dataset size (906 vs 213,593 subjects) and population differences rather than model architecture, as our learning curve shows no plateau. Code is publicly available.

A hybrid digital twin framework is presented for bridge condition monitoring using existing traffic cameras and weather APIs, reducing reliance on dedicated sensor installations. The approach is demonstrated on the Peace Bridge (99 years in service) under high traffic demand and harsh winter exposure. The framework fuses three near-real-time streams: YOLOv8 computer vision from a bridge-deck camera estimates vehicle counts, traffic density, and load proxies; a Lighthill--Whitham--Richards (LWR) model propagates density $ρ(x,t)$ and detects deceleration-driven shockwaves linked to repetitive loading and fatigue accumulation; and weather APIs provide deterioration drivers including temperature cycling, freeze-thaw activity, precipitation-related corrosion potential, and wind effects. Monte Carlo simulation quantifies uncertainty across traffic-environment scenarios, while Random Forest models map fused features to fatigue indicators and maintenance classification. The framework demonstrates utilizing existing infrastructure for cost-effective predictive maintenance of aging, high-traffic bridges in harsh climates.

Part-level 3D generation is crucial for various downstream applications, including gaming, film production, and industrial design. However, decomposing a 3D shape into geometrically plausible and meaningful components remains a significant challenge. Previous part-based generation methods often struggle to produce well-constructed parts, exhibiting poor structural coherence, geometric implausibility, inaccuracy, or inefficiency. To address these challenges, we introduce EI-Part, a novel framework specifically designed to generate high-quality 3D shapes with components, characterized by strong structural coherence, geometric plausibility, geometric fidelity, and generation efficiency. We propose utilizing distinct representations at different stages: an Explode state for part completion and an Implode state for geometry refinement. This strategy fully leverages spatial resolution, enabling flexible part completion and fine geometric detail generation. To maintain structural coherence between parts, a self-attention mechanism is incorporated in both exploded and imploded states, facilitating effective information perception and feature fusion among components during generation. Extensive experiments on multiple benchmarks demonstrate that EI-Part efficiently produces semantically meaningful and structurally coherent parts with fine-grained geometric details, achieving state-of-the-art performance in part-level 3D generation. Project page: https://cvhadessun.github.io/EI-Part/

Domain Generalized person Re-identification (DG Re-ID) is a challenging task, where models are trained on source domains but tested on unseen target domains. Although previous pure vision-based models have achieved significant progress, the performance remains further improved. Recently, Vision-Language Models (VLMs) present outstanding generalization capabilities in various visual applications. However, directly adapting a VLM to Re-ID shows limited generalization improvement. This is because the VLM only produces with global features that are insensitive to ID nuances. To tacle this problem, we propose a CLIP-based multi-grained vision-language alignment framework in this work. Specifically, several multi-grained prompts are introduced in language modality to describe different body parts and align with their counterparts in vision modality. To obtain fine-grained visual information, an adaptively masked multi-head self-attention module is employed to precisely extract specific part features. To train the proposed module, an MLLM-based visual grounding expert is employed to automatically generate pseudo labels of body parts for supervision. Extensive experiments conducted on both single- and multi-source generalization protocols demonstrate the superior performance of our approach. The implementation code will be released at https://github.com/RikoLi/MUVA.

This work proposes a formal abductive explanation framework designed to systematically uncover rationales underlying AI predictions of mental health help-seeking within tech workplace settings. By computing rigorous justifications for model outputs, this approach enables principled selection of models tailored to distinct psychiatric profiles and underpins ethically robust recourse planning. Beyond moving past ad-hoc interpretability, we explicitly examine the influence of sensitive attributes such as gender on model decisions, a critical component for fairness assessments. In doing so, it aligns explanatory insights with the complex landscape of workplace mental health, ultimately supporting trustworthy deployment and targeted interventions.

GraphRAG is increasingly adopted for converting unstructured corpora into graph structures to enable multi-hop reasoning. However, standard graph algorithms rely heavily on static connectivity and explicit edges, often failing in real-world scenarios where knowledge graphs (KGs) are noisy, sparse, or incomplete. To address this limitation, we introduce INSES (Intelligent Navigation and Similarity Enhanced Search), a dynamic framework designed to reason beyond explicit edges. INSES couples LLM-guided navigation, which prunes noise and steers exploration, with embedding-based similarity expansion to recover hidden links and bridge semantic gaps. Recognizing the computational cost of graph reasoning, we complement INSES with a lightweight router that delegates simple queries to Naïve RAG and escalates complex cases to INSES, balancing efficiency with reasoning depth. INSES consistently outperforms SOTA RAG and GraphRAG baselines across multiple benchmarks. Notably, on the MINE benchmark, it demonstrates superior robustness across KGs constructed by varying methods (KGGEN, GraphRAG, OpenIE), improving accuracy by 5%, 10%, and 27%, respectively.

To generalize deepfake detectors to future unseen forgeries, most existing methods attempt to simulate the dynamically evolving forgery types using available source domain data. However, predicting an unbounded set of future manipulations from limited prior examples is infeasible. To overcome this limitation, we propose to exploit the invariance of \textbf{real data} from two complementary perspectives: the fixed population distribution of the entire real class and the inherent Gaussianity of individual real images. Building on these properties, we introduce the Real Distribution Bias Correction (RDBC) framework, which consists of two key components: the Real Population Distribution Estimation module and the Distribution-Sampled Feature Whitening module. The former utilizes the independent and identically distributed (\iid) property of real samples to derive the normal distribution form of their statistics, from which the distribution parameters can be estimated using limited source domain data. Based on the learned population distribution, the latter utilizes the inherent Gaussianity of real data as a discriminative prior and performs a sampling-based whitening operation to amplify the Gaussianity gap between real and fake samples. Through synergistic coupling of the two modules, our model captures the real-world properties of real samples, thereby enhancing its generalizability to unseen target domains. Extensive experiments demonstrate that RDBC achieves state-of-the-art performance in both in-domain and cross-domain deepfake detection.

Latent space-based facial attribute editing methods have gained popularity in applications such as digital entertainment, virtual avatar creation, and human-computer interaction systems due to their potential for efficient and flexible attribute manipulation, particularly for continuous edits. Among these, unsupervised latent space-based methods, which discover effective semantic vectors without relying on labeled data, have attracted considerable attention in the research community. However, existing methods still encounter difficulties in disentanglement, as manipulating a specific facial attribute may unintentionally affect other attributes, complicating fine-grained controllability. To address these challenges, we propose a novel framework designed to offer an effective and adaptable solution for unsupervised facial attribute editing, called Unsupervised Facial Attribute Controllable Editing (U-Face). The proposed method frames semantic vector learning as a subspace learning problem, where latent vectors are approximated within a lower-dimensional semantic subspace spanned by a semantic vector matrix. This formulation can also be equivalently interpreted from a projection-reconstruction perspective and further generalized into an autoencoder framework, providing a foundation that can support disentangled representation learning in a flexible manner. To improve disentanglement and controllability, we impose orthogonal non-negative constraints on the semantic vectors and incorporate attribute boundary vectors to reduce entanglement in the learned directions. Although these constraints make the optimization problem challenging, we design an alternating iterative algorithm, called Alternating Iterative Disentanglement and Controllability (AIDC), with closed-form updates and provable convergence under specific conditions.

Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated great success in modeling reflective 3D objects and their interaction with the environment via deferred rendering (DR). However, existing methods often struggle with correctly reconstructing physical attributes such as albedo and reflectance, and therefore they do not support high-fidelity relighting. Observing that this limitation stems from the lack of shape and material information in RGB images, we present PhyGaP, a physically-grounded 3DGS method that leverages polarization cues to facilitate precise reflection decomposition and visually consistent relighting of reconstructed objects. Specifically, we design a polarimetric deferred rendering (PolarDR) process to model polarization by reflection, and a self-occlusion-aware environment map building technique (GridMap) to resolve indirect lighting of non-convex objects. We validate on multiple synthetic and real-world scenes, including those featuring only partial polarization cues, that PhyGaP not only excels in reconstructing the appearance and surface normal of reflective 3D objects (~2 dB in PSNR and 45.7% in Cosine Distance better than existing RGB-based methods on average), but also achieves state-of-the-art inverse rendering and relighting capability. Our code will be released soon.

While graph-derived signals are widely used in tabular learning, existing studies typically rely on limited experimental setups and average performance comparisons, leaving the statistical reliability and robustness of observed gains largely unexplored. Consequently, it remains unclear which signals provide consistent and robust improvements. This paper presents a taxonomy-driven empirical analysis of graph-derived signals for tabular machine learning. We propose a unified and reproducible evaluation protocol to systematically assess which categories of graph-derived signals yield statistically significant and robust performance improvements. The protocol provides an extensible setup for the controlled integration of diverse graph-derived signals into tabular learning pipelines. To ensure a fair and rigorous comparison, it incorporates automated hyperparameter optimization, multi-seed statistical evaluation, formal significance testing, and robustness analysis under graph perturbations. We demonstrate the protocol through an extensive case study on a large-scale, imbalanced cryptocurrency fraud detection dataset. The analysis identifies signal categories providing consistently reliable performance gains and offers interpretable insights into which graph-derived signals indicate fraud-discriminative structural patterns. Furthermore, robustness analyses reveal pronounced differences in how various signals handle missing or corrupted relational data. These findings demonstrate practical utility for fraud detection and illustrate how the proposed taxonomy-driven evaluation protocol can be applied in other application domains.

Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties. However, their alignment with human object perception remains poorly understood. Here, we introduce a behavioral benchmark in which participants make same/different object judgments for dot pairs on naturalistic scenes, scaling up a classical psychophysics paradigm to over 1000 trials. We test a diverse set of vision models using a simple readout from their representations to predict subjects' reaction times. We observe a steady improvement across model generations, with both architecture and training objective contributing to alignment, and transformer-based models trained with the DINO self-supervised objective showing the strongest performance. To investigate the source of this improvement, we propose a novel metric to quantify the object-centric component of representations by measuring patch similarity within and between objects. Across models, stronger object-centric structure predicts human segmentation behavior more accurately. We further show that matching the Gram matrix of supervised transformer models, capturing similarity structure across image patches, with that of a self-supervised model through distillation improves their alignment with human behavior, converging with the prior finding that Gram anchoring improves DINOv3's feature quality. Together, these results demonstrate that self-supervised vision models capture object structure in a behaviorally human-like manner, and that Gram matrix structure plays a role in driving perceptual alignment.

Space missions generate massive volumes of high-resolution orbital and surface imagery that far exceed the capacity for manual inspection. Detecting rare phenomena is scientifically critical, yet traditional supervised learning struggles due to scarce labeled examples and closed-world assumptions that prevent discovery of genuinely novel observations. In this work, we investigate Visual Anomaly Detection (VAD) as a framework for automated discovery in planetary exploration. We present the first empirical evaluation of state-of-the-art feature-based VAD methods on real planetary imagery, encompassing both orbital lunar data and Mars rover surface imagery. To support this evaluation, we introduce two benchmarks: (i) a lunar dataset derived from Lunar Reconnaissance Orbiter Camera Narrow Angle imagery, comprising of fresh and degraded craters as anomalies alongside normal terrain; and (ii) a Mars surface dataset designed to reflect the characteristics of rover-acquired imagery. We evaluate multiple VAD approaches with a focus on computationally efficient, edge-oriented solutions suitable for onboard deployment, applicable to both orbital platforms surveying the lunar surface and surface rovers operating on Mars. Our results demonstrate that feature-based VAD methods can effectively identify rare planetary surface phenomena while remaining feasible for resource-constrained environments. By grounding anomaly detection in planetary science, this work establishes practical benchmarks and highlights the potential of open-world perception systems to support a range of mission-critical applications, including tactical planning, landing site selection, hazard detection, bandwidth-aware data prioritization, and the discovery of unanticipated geological processes.

Agricultural robotics has emerged as a critical solution to the labor shortages and rising costs associated with manual crop harvesting. Bell pepper harvesting, in particular, is a labor-intensive task, accounting for up to 50% of total production costs. While automated solutions have shown promise in controlled greenhouse environments, harvesting in unstructured outdoor farms remains an open challenge due to environmental variability and occlusion. This paper presents VADER (Vision-guided Autonomous Dual-arm Extraction Robot), a dual-arm mobile manipulation system designed specifically for the autonomous harvesting of bell peppers in outdoor environments. The system integrates a robust perception pipeline coupled with a dual-arm planning framework that coordinates a gripping arm and a cutting arm for extraction. We validate the system through trials in various realistic conditions, demonstrating a harvest success rate exceeding 60% with a cycle time of under 100 seconds per fruit, while also featuring a teleoperation fail-safe based on the GELLO teleoperation framework to ensure robustness. To support robust perception, we contribute a hierarchically structured dataset of over 3,200 images spanning indoor and outdoor domains, pairing wide-field scene images with close-up pepper images to enable a coarse-to-fine training strategy from fruit detection to high-precision pose estimation. The code and dataset will be made publicly available upon acceptance.

Pre-trained Large Language Model (LLM) exhibits broad capabilities, yet, for specific tasks or domains their attainment of higher accuracy and more reliable reasoning generally depends on post-training through Supervised Fine-Tuning (SFT) or Reinforcement Learning (RL). Although often treated as distinct methodologies, recent theoretical and empirical developments demonstrate that SFT and RL are closely connected. This study presents a comprehensive and unified perspective on LLM post-training with SFT and RL. We first provide an in-depth overview of both techniques, examining their objectives, algorithmic structures, and data requirements. We then systematically analyze their interplay, highlighting frameworks that integrate SFT and RL, hybrid training pipelines, and methods that leverage their complementary strengths. Drawing on a representative set of recent application studies from 2023 to 2025, we identify emerging trends, characterize the rapid shift toward hybrid post-training paradigms, and distill key takeaways that clarify when and why each method is most effective. By synthesizing theoretical insights, practical methodologies, and empirical evidence, this study establishes a coherent understanding of SFT and RL within a unified framework and outlines promising directions for future research in scalable, efficient, and generalizable LLM post-training.

The emergence of Multimodal Large Language Models (MLLMs) and the widespread usage of MLLM cloud services such as GPT-4V raised great concerns about privacy leakage in visual data. As these models are typically deployed in cloud services, users are required to submit their images and videos, posing serious privacy risks. However, how to tackle such privacy concerns is an under-explored problem. Thus, in this paper, we aim to conduct a new investigation to protect visual privacy when enjoying the convenience brought by MLLM services. We address the practical case where the MLLM is a "black box", i.e., we only have access to its input and output without knowing its internal model information. To tackle such a challenging yet demanding problem, we propose a novel framework, in which we carefully design the learning objective with Pareto optimality to seek a better trade-off between visual privacy and MLLM's performance, and propose critical-history enhanced optimization to effectively optimize the framework with the black-box MLLM. Our experiments show that our method is effective on different benchmarks.

Modern large language model training is no longer limited by data availability, but by the inability of existing preprocessing pipelines to simultaneously achieve massive scale and high data quality. Current approaches are forced to sacrifice one for the other: either aggressively filtering to improve quality at the cost of severe token loss, or retaining large volumes of data while introducing substantial noise. In this work, we introduce FLUX, a preprocessing pipeline specifically designed to break this long-standing trade-off by maximizing token retention while enforcing rigorous quality control. Models trained on FLUX-curated data consistently outperform prior methods. A 3B-parameter model trained on 60B tokens with FLUX achieves 32.14% MMLU accuracy, surpassing the previous state-of-the-art pipeline DCLM (31.98%) and significantly outperforming FineWeb (29.88%). FLUX achieves the same aggregate score as a model trained on DCLM data using only 39B tokens, resulting in a 34.4% reduction in training compute. At the data level, FLUX extracts 50B usable tokens from a single dump (CC-MAIN-2025-51), compared to 40B from DCLM (+25% retention). FLUX-Base yields 192B tokens, exceeding FineWeb's 170B while still maintaining superior quality. Overall, FLUX establishes a new state of the art in web-scale data preprocessing by demonstrating that high retention, strong quality control, and computational efficiency can be achieved simultaneously, redefining the limits of scalable dataset construction for modern language models.

In offline reinforcement learning (RL), single-step temporal-difference (TD) learning can suffer from bootstrapping error accumulation over long horizons. Action-chunked TD methods mitigate this by backing up over multiple steps, but can introduce suboptimality by restricting the policy class to open-loop action sequences. To resolve this trade-off, we present Chunk-Guided Q-Learning (CGQ), a single-step TD algorithm that guides a fine-grained single-step critic by regularizing it toward a chunk-based critic trained using temporally extended backups. This reduces compounding error while preserving fine-grained value propagation. We theoretically show that CGQ attains tighter critic optimality bounds than either single-step or action-chunked TD learning alone. Empirically, CGQ achieves strong performance on challenging long-horizon OGBench tasks, often outperforming both single-step and action-chunked methods.