Regularization
-
Efficient Generative Image Compression with Quantized Latents Refinement
2026-10-21 13:03:09Hao Cao, Yinhuan Huang, Wenqi Guo, Zhijin Qin, Jungong HanAbstract
Generative image compression (GIC) delivers strong perceptual quality at low bitrates. However, GIC methods with strong perceptual quality often rely on pretrained diffusion models with high latency, while recent lightweight GIC methods reduce latency but deliver lower perceptual quality. We observe that, for lightweight GIC methods at low bitrates, coarse deterministic quantization can collapse nearby encoder latents corresponding to different fine details to the same point, making these details difficult to recover. Motivated by this, we propose GR-GIC, an efficient GIC that delivers competitive reconstruction performance with fast inference. For better performance, we introduce Guided Refinement (GR), which combines latent refinement guided by entropy context with adaptive perturbations for training regularization, jointly improving reconstruction at low bitrates. For fast inference, we introduce reorganized projected residual vector quantization (P-RVQ), which equivalently reorganizes residual updates into low-dimensional lookups to expose greater parallelism and reduce sequential computation. Experiments on Kodak show that for performance, compared with OneDC, GR-GIC achieves BD-rate savings of 23.19%, 37.71%, 22.30%, and 22.14% for LPIPS, DISTS, PSNR, and FID, respectively. For fast inference, the highly optimized implementation of GR-GIC encodes and decodes in 4.60 and 5.98 ms on an NVIDIA A100. Specifically, the reorganized P-RVQ implementation achieves a $3.14\times$ average speedup over the original implementation under the same FP32 setting. On an NVIDIA Jetson Orin NX, GR-GIC achieves latency comparable to lightweight GIC methods.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29691
PDF
-
Beyond Shortcut Learning: Hierarchical Spatial Prototype Regularization for Face Forgery Detection
2026-10-21 09:02:34Chao Shuai, Shaojing Fan, Kun Pan, Jinwu Hu, Weichen Lian, Ziqi Yang, Zhongjie Ba, Zhenguang LiuAbstract
Recent advances in generative models have enabled highly realistic face forgeries, yet generalizing deepfake detectors to unseen manipulation pipelines remains a major challenge. One critical yet underexplored issue is that the learned forensic representation itself may fail to remain stable across different manipulation sources. In this paper, we provide new evidence that naively fine-tuned vision models suffer from severe \textit{forensic representation collapse}: their extracted cues are often entangled with unstable, dataset-specific artifacts, resulting in structurally fragile representations and poor cross-domain generalization. Leveraging this insight, we propose \textbf{H}ierarchical \textbf{S}patial \textbf{P}rototype (\textbf{HSP}) regularization, which explicitly models the forgery manifold by learning a structured prototype subspace over spatial features. We further introduce prototype orthogonality and second-order assignment balance, which jointly preserve the geometric independence of latent forgery factors and promote high-effective-rank utilization of the forensic representation, thereby reducing reliance on dataset-specific shortcuts. Empirical results demonstrate that our method substantially improves generalizability, yielding average frame-level AUC gains of 5.6\% and 5.3\% in the cross-dataset and cross-manipulation settings, respectively. Moreover, when used as a plug-in module, HSP boosts the average video-level AUC of existing state-of-the-art detectors to 95.3\% (+1.8\%). These results demonstrate the practical value of HSP as an easy-to-adopt regularization module for enhancing deepfake detectors.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29442
PDF
-
FM-Occ: Feature-Diverse Upsampling and Memory-Aware Decoding for 3D Occupancy Prediction
2026-10-21 08:14:31Yujia Zhai (Great Bay University), Guoming Huang (Great Bay University), Zhuanghuai Wang (Great Bay University), Bangquan Xie (Great Bay University)Abstract
3D semantic occupancy prediction estimates voxel-wise occupancy and semantic labels throughout a scene. Our experiments reveal that conventional sparse transposed-convolution upsampling yields poorly differentiated voxel responses and that successive decoder layers discard previously correct semantic predictions. To address these issues, we present Feature-Diverse Upsampling and Memory-Aware Decoding for 3D Occupancy Prediction (FM-Occ), comprising two components. First, 3D Sparse Subvoxel Shuffle (3S) mitigates feature homogenization by constructing candidate child features in the channel dimension, jointly transforming and normalizing them, and then rearranging them onto a finer sparse grid with explicit feature-coordinate correspondence. Second, Entropy-Regulated Layer-wise Memory (ER-LM) retains semantic information across decoder layers by maintaining a layer-wise memory for each query through gated recurrent updates and using prediction entropy to regulate the historical information propagated to the next layer. During training, a class-weighted entropy loss Lcwe provides label-guided regularization for matched semantic queries. On SemanticKITTI, 3S increases the spatial coefficient of variation of normalized voxel-wise root-mean-square (RMS) responses from 0.41% to 4.03%, while ER-LM reduces semantic degradation and improves error correction across decoder layers. The combined FM-Occ improves mIoU from 12.16% to 12.73% with negligible memory overhead. ER-LM further improves mIoU in the BEV-based DISC framework from 16.78% to 17.17%, supporting its applicability across 3D voxel-based and BEV-based architectures.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29388
PDF
-
DepState-JEPA: Learning Depth-Grounded State Representation for Visual Perception and Manipulation
2026-10-21 05:51:06Xiujian Liang, Liuyuan Na, Zehao Du, Jiacheng Xu, Weixi Song, Mingyang Sun, Xingjun Ma, Cewu Lu, Jianhua SunAbstract
Predictive representations for robot manipulation should connect scene geometry with the state changes induced by actions. Our intuition is that understanding what an action will change starts with understanding where things are: complementary RGB and depth observations ground a common scene representation from which to infer those changes. Guided by this intuition, we introduce \textbf{DepState-JEPA}, a dual-stream RGB--Depth joint-embedding predictive architecture that connects spatial understanding with action-conditioned prediction through a shared latent state, \textbf{DepState}. Built on V-JEPA~2.1, the framework uses depth both as a complementary observation stream and to ground both modalities in metric 3D space, aggregating shared information into DepState while retaining modality-private features for decoding. Ray-conditioned readouts predict local features without target depth; after an action-conditioned transition, the same decoders predict future RGB and depth features using the predicted state and fixed initial private features. Robot-state readouts provide recursive proprioceptive inputs; object-trajectory supervision and calibrated forward kinematics shape state learning through motion targets and joint--TCP consistency. Comparisons show stronger RGB-encoder transfer after RGB-D adaptation, feature completion, conditioned visual forecasting, and manipulation success. Within-model ablations identify contributions from depth content, metric coordinates, and future-state matching, with additional control gains from FK regularization.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29246
PDF
-
DriftNeRF: Cross-Ray Density Drifting for Sparse-View Neural Radiance Fields
2026-10-21 02:49:34Juntang Wang, Yihan Wang, Sheng'en Li, Hao Wu, Dongmian Zou, Shixin XuAbstract
Neural Radiance Fields (NeRF) synthesize photorealistic novel views from dense image collections, but degrade sharply when few views are available. We attribute a specific, measurable defect to the objective itself: the rendering loss is a sum over independent rays and contains no term comparing densities that different rays assign to the same region of space, so nearby 3D points can settle on contradictory densities while every training pixel is reproduced correctly. We make this quantity explicit by measuring cross-ray density disagreement directly during training, and show that it stays high in vanilla NeRF, falls only incidentally under frequency-based regularization, and moves together with held-out quality in the sparse regime. We then close the gap with DriftNeRF, a drop-in regularizer that instantiates the drifting-field template on density samples: a masked exponential kernel aggregates densities from nearby points on other rays into a stop-gradient consensus target, and the resulting drifting field penalizes unsupported disagreement while leaving agreed-upon boundaries intact. The regularizer reads only sampled positions, ray identifiers, and predicted densities, so it requires no pretrained model, external geometry, or additional images, and transfers across field parameterizations. On NeRF-Synthetic it reduces residual disagreement by an order of magnitude, and across NeRF-Synthetic, DTU, and LLFF it improves 3-view PSNR over the strongest MLP-NeRF baseline by 0.42-0.65 dB and remains competitive with sparse-view Gaussian pipelines under a matched protocol without their depth, flow, or covisibility preprocessing.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29106
PDF
-
DualHeads: Reward-tilted few-step diffusion made simple
2026-10-20 19:31:03Yuanzhi Zhu, Eleftherios Tsonis, Simo Alami Chehboune, Xi Wang, St\'ephane Lathuili\`ere, Vicky KalogeitonAbstract
Distilled diffusion models generate high-quality images in a few sampling steps, but aligning them with task requirements and human preferences is difficult. Methods developed for multi-step diffusion models rely on differentiable rewards, or on score fields and stochastic trajectories that distilled generators may lack. We ask whether a few-step generator can be adapted using only external reward evaluations and reference samples, and show that two binary classifiers suffice. Our method, DualHeads, implements them as lightweight heads on a frozen diffusion backbone. The reward head learns which samples of the same prompt score higher, the reference head separates reference images from generated ones, and the generator maximizes a weighted sum of their logits. When the heads are optimal, this objective is KL-regularized maximization of the learned reward, and the ratio of head weights sets the regularization strength. Empirically, with both rule-based and model-based rewards, a few-step DualHeads generator reaches task rewards close to those of 40-step reinforcement learning methods while preserving image quality, at no extra inference cost. We hope that this simple and elegant dual-head formulation will help advance few-step reward-tilted generation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28858
PDF
-
CondenseVLA: Learnable History Condensation for Efficient Multi-Frame VLA
2026-10-20 15:47:30Feiyang Hong, Yujie Wei, Bo Zhao, Xiu Su, Hongxun Yao, Shuo YangAbstract
Robot manipulation often depends on short-term cues - such as brief contacts, temporary occlusions, and intermediate object states - that are ambiguous in a single frame and can only be resolved by integrating observations over time. However, injecting historical information solely by enlarging the history window is computationally costly and frequently yields limited gains due to substantial redundancy and task-agnostic, inflexible sampling of observations. We propose CondenseVLA, a multi-frame VLA policy with a learnable decoder-side history condensation module for using short-term visual context in action decoding. Given a sequence of cached per-frame features from the VLM backbone, CondenseVLA distills observation history into a fixed set of slot tokens using learnable queries and multi-head cross-attention. Simple auxiliary regularization penalizes overlap among slot attention maps and decorrelates slot embeddings, encouraging complementary attention and reducing slot redundancy. Across the evaluated tasks, CondenseVLA improves Simpler-WidowX success from 58.7% to 69.8% (+11.1 percentage points), achieves 97.2% on LIBERO, and reaches 52.8% on real-world tasks. It achieves 21.6% success on memory-dependent RMBench tasks. These results support selective condensation of bounded recent visual evidence for action decoding, while harder multi-observation tasks expose the limits of a finite history window. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.25927
PDF
-
From Generic to Dedicated: A Novel Optimizer for Online Continual Learning
Abstract
Online Continual Learning (OCL) requires models to learn from non-stationary data streams under a strict single-pass constraint, making them highly susceptible to catastrophic forgetting. While existing studies have explored various strategies from data, architecture, and optimization perspectives, the optimizer often directly uses generic approaches such as SGD and AdamW. In this work, we reveal a new link between optimization dynamics and OCL needs by recasting Polyak-Ruppert averaging as the engine of "plasticity" and Primal averaging as the anchor of "stability". This inspires our novel optimizer, SPIN (Stability-Plasticity INterpolation), which explicitly decouples plasticity and stability by interpolating between a fast-moving "plasticity" sequence and an adaptive "stability" sequence. We theoretically demonstrate that SPIN implicitly employs an inverse Hessian approximation, providing crucial Tikhonov regularization to damp noisy, single-sample Hessian estimates and mitigate forgetting. More importantly, SPIN can be seamlessly integrated into existing OCL methods by taking resulted gradients as input and replacing standard optimizers. Extensive experiments show that using SPIN instead of standard optimizers yields consistent and significant performance gains across multiple OCL approaches, including the challenging rehearsal-free setting and under strict memory constraints.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27835
PDF
-
Geometry Regularization for Vanilla NeRF via Self-Supervised Cross-Ray Consistency
2026-10-20 07:40:14Zongji WangAbstract
Neural Radiance Fields (NeRF) achieve high-quality novel-view synthesis by representing a scene as a continuous volumetric radiance field. However, the geometry encoded by the density field of vanilla NeRF can be noisy and inaccurate, since different combinations of shape and radiance may explain the same input images. To reduce this ambiguity, we augment vanilla NeRF with a geometry-optimization branch based on self-supervised cross-ray consistency. Specifically, this branch samples candidate surface points from the density field, generates virtual rays that intersect at each point from different directions, and renders their appearance using the NeRF network. Based on the visibility-weighted color consistency across these rays, we constrain the implicit geometry. We further regularize the implicit geometry by penalizing opacity at candidates with inconsistent appearance predictions and encouraging local normal smoothness. These geometric constraints are derived from the NeRF predictions and require no ground-truth depth or surface-normal supervision. Experiments on eight Replica scenes show that the proposed method reduces the mean Chamfer distance by 30.8% compared with vanilla NeRF.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27776
PDF
-
Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling
2026-10-20 03:12:50Abhijeet Sinha, Sundari Elango, Dianbo LiuAbstract
Many reinforcement learning (RL) problems admit multiple terminal solutions of comparable quality, where the goal is not to identify a single optimum but to represent a diverse set of high-quality outcomes. Nevertheless, policies trained by standard expected return maximization routinely collapse onto a small subset of outcomes, a phenomenon commonly attributed to insufficient exploration or weak regularization. We show that this explanation is incomplete: outcome level mode collapse is a structural consequence of the expected-return objective itself. Under idealized learning dynamics, the log-probability ratio between any two outcomes evolves linearly in their reward difference, implying exponential ratio divergence and inevitable collapse independent of the exploration strategy, entropy regularization, or optimization algorithm. We identify the source of this pathology as the probability multiplier inside the expectation and propose a minimal correction: inverse probability scaling, which removes outcome-frequency amplification from the learning signal, fundamentally changes the learning dynamics, and provably yields reward-proportional terminal distributions, preventing collapse in multimodal settings. We instantiate this principle in Group Relative Policy Optimization (GRPO) as a drop-in modification, IPS-GRPO, requiring no auxiliary models or architectural changes. Across different reasoning and molecular generation tasks, IPS-GRPO consistently reduces outcome-level mode collapse while matching or exceeding baseline performance, suggesting that correcting the objective rather than adding exploration heuristics is key to reliable multimodal policy optimization.
Abstract (translated)
URL
https://arxiv.org/abs/2601.21669
PDF
-
MiCLA: Mixture-to-Constituent Latent Alignment for Polyphonic Audio Representation Learning
2026-10-20 02:10:10Kohei Yamamoto, Kosuke OkusaAbstract
Real-world audio typically contains concurrent sound events, yet standard self-supervised methods treat each clip as an isolated training unit without explicitly modeling mixture--constituent relationships. We propose Mixture-to-Constituent Latent Alignment (MiCLA), a two-stage self-supervised pre-training framework that uses synthetic log-mel mixing to align mixture representations with their constituent clips. Stage 1 structures single-clip representations via masked self-distillation and contrastive regularization. Stage 2 introduces bidirectional alignment: for a synthetic mixture, MiCLA suppresses the component aligned with one constituent and aligns the residual with the other, using projective residualization on patch tokens and sample-adaptive soft residualization on the global class token. In downstream evaluations, MiCLA achieves 43.2% mean average precision (mAP) on AS-20K and 50.3% mAP on AS-2M under fine-tuning, and achieves the highest mAP among evaluated models on both AudioSet settings under frozen Convex Gated Probing (CGP). Furthermore, a Joint Semantic Retrieval diagnostic shows that MiCLA improves simultaneous retrieval of both constituent classes over target-averaging baselines. These results indicate that directional mixture-to-constituent alignment provides an effective pre-training signal for polyphonic audio representation learning.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27491
PDF
-
EDISCO: Equivariant DIScrete Diffusion for Euclidean Combinatorial Optimization
2026-10-19 18:44:19Ruogu Chen, Jie HanAbstract
Euclidean combinatorial optimization problems (ECOPs), such as the Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP), possess inherent symmetries under the two-dimensional Euclidean group E(2), including rotations, reflections, and translations. Existing learning-based methods, including recent diffusion-based methods, rely on data augmentation or regularization to approximate E(2)-equivariance. This paper presents EDISCO, the first discrete diffusion model for ECOPs with exact E(2)-invariant generative distributions over node-index solutions. EDISCO introduces an E(2)-equivariant edge-score network coupled with a categorical continuous-time Markov chain over discrete edge variables, and exact posterior sampling provides efficient multi-step inference. This design gives EDISCO a local geometric inductive bias: edge neighborhoods with the same relative geometry and combinatorial context are represented consistently regardless of absolute position or orientation, making learning more efficient and inference more robust than non-equivariant methods. EDISCO outperforms previous learning-based state-of-the-art solvers on synthetic TSP from 100 to 10000 nodes and CVRP from 50 to 2000 customers, while using only 33-50% of the training instances. Trained only on uniform synthetic data, EDISCO also outperforms competing learning-based baselines under spatial distribution shift and CVRP constraint-tightness shift. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.04953
PDF
-
VitronEdit: Universal Visual Editing across Images, Videos, and 3D Scenes
2026-10-19 17:59:55Jing Wang, Yanlin Li, Mong-Li Lee, Wynne Hsu, Shengqiong Wu, Hao FeiAbstract
Recent advances in unified visual editing have begun to consolidate image and video editing within a single model, while 3D scene editing remains largely separate and constrained by scarce paired training data. Given the rich image and video editing supervision now available and the common editing semantics shared across modalities, a natural question is whether this knowledge can be transferred to data-scarce 3D editing. We present VitronEdit, a universal framework for image, video, and 3D scene editing. VitronEdit adopts a shared sequence representation and progressive multimodal training to transfer editing knowledge across modalities. We further introduce geometry-aware post-training, which leverages a pretrained geometry reconstruction model to provide depth and camera-pose supervision. Surprisingly, applying geometric supervision only to 3D samples yields the best overall performance, while image and video editing also improve despite receiving no direct geometric supervision, suggesting that geometric regularization transfers through the shared backbone. Our analysis further shows that image and video training mainly transfers editing semantics to 3D, whereas 3D supervision primarily improves multi-view consistency. The project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27049
PDF
-
Channel-Level Mask Guidance for Slimmable Image Compression
2026-10-19 17:19:04Chen Chen, Chenggang Wu, Yongbiao Chen, Weidong Qiu, Zhengwei Qi, Haibing GuanAbstract
Learned image compression (LIC) has achieved promising rate-distortion performance, but most methods lack scalability for diverse platforms with varying computational and storage constraints. Existing slimmable LIC methods achieve flexible complexity via consecutive-channel activation but suffer from two limitations: forced consecutive-channel selection degrades narrow-model performance at low bitrates, and the lack of stable variable-rate control limits adaptability to varying bandwidth. We propose a channel-level mask-guided slimmable image compression method. A learnable channel-wise mask with sparsity-promoting regularization enables non-contiguous top-w channel selection, letting narrow models use the most informative channels. After training, mask merging and channel reordering convert the model into a standard slimmable network via Mask-to-Slimmable (M2S) conversion, enabling efficient inference without architectural changes. For variable-rate control, we combine lambda- and width-conditioned modulation with quantization-step scaling and a progressive training pipeline stabilized by a freeze-then-fine-tune strategy. Experiments on Kodak across E2E, Hyperprior, and Checkerboard backbones show superior rate-distortion performance across widths and bitrates, with large gains for narrow models at low bitrates. At w=48, it achieves up to 19.22%, 24.11%, and 22.76% BD-rate savings over the same-width Slimmable baseline on E2E, Hyperprior, and CKBD, respectively. A single VBR model replaces 40 independent models, reducing storage by 14.8x to 15.9x. Code: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27037
PDF
-
Embodiment-Aware Planning for Heterogeneous Bimanual Manipulation
2026-10-16 14:41:33Sukhvansh Jain, Anurag Maurya, Shivam Vats, Narendra Kumar Dhar, Ravi PrakashAbstract
Many manipulation tasks that are effortless for dexterous human hands remain challenging for robotic systems equipped with simple, task-specialized grippers. Industrial platforms commonly rely on end-effectors such as suction cups or parallel-jaw grippers, yet no single mode can reliably satisfy the diverse constraints encountered across different phases of complex manipulation tasks, including pickup, reorientation, insertion, and constrained placement. In this work, we investigate whether complementary simple grippers within a heterogeneous bimanual setup can collectively realize tasks that exceed the capability of any individual gripper alone. Given a single human demonstration specifying the desired object motion, we formulate embodiment-aware execution as a finite-horizon optimization over arm-trajectory assignments. At each segment, the planner determines whether single-arm manipulation or a coordinated dual arm handover is required, jointly reasoning over heterogeneous grasp feasibility, motion constraints, manipulability, and cross-gripper compatibility. Exploiting this formulation, we compute globally consistent assignments with explicit switching regularization. Experiments on a dual Franka FR3 platform equipped with suction and parallel-jaw grippers demonstrate improved feasibility and reliability in tasks that are infeasible under single-gripper execution.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23551
PDF
-
ShadowCast: On-the-Fly Context-Aware Shadow Augmentation for Remote Sensing Image Segmentation
2026-10-16 13:23:56Yechan Kim, Dongho Yoon, Jongmin Joo, JongHyun Park, Moongu JeonAbstract
Shadows cast by elevated objects alter the spectral appearance and obscure the boundaries of objects in remote sensing images, thereby degrading semantic segmentation performance. Most existing approaches handle shadows as degradations to be detected and removed, requiring additional costs from dedicated networks and shadow-specific annotations. We propose ShadowCast, which takes the opposite approach: it synthesizes shadows and injects them during training for remote sensing segmentation. It extracts masks of elevated objects, such as buildings and trees, directly from the segmentation labels and estimates an image-specific cast-shadow direction cue by probing the brightness around them. It then projects synthetic shadows along the inferred cast-shadow direction, requiring no learned network and no acquisition metadata. Experiments on three widely used remote sensing benchmarks, Vaihingen, Potsdam, and LoveDA, show that ShadowCast consistently outperforms the baseline across diverse state-of-the-art segmentation architectures. Moreover, it brings additional performance gains when combined with standard augmentation and regularization techniques, indicating that stochastic shadow injection serves as a simple and complementary augmentation strategy for remote sensing segmentation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23440
PDF
-
Audit-First VAPO: Risk-Certified Selective Updates under Imperfect Verification
2026-10-16 11:41:12Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Rui Chen, Daren ZhaAbstract
Imperfect verifiers can assign a harmful update direction even when clipping and regularization bound its magnitude. We introduce Audit-First VAPO, which separates discrete directional admission from continuous magnitude control. An observation-only accept-appeal-abstain policy uses a finite secondary-verification budget; its action trace is frozen before clean labels are joined. Simultaneous finite-sample bounds then certify selected harmful risk, coverage, and verifier-call rate over a predeclared policy family. Conditional Hoeffding-Azuma bounds account for the dependence induced by shared budgets, and rollout or verifier changes initiate a new certification stage. After admission, a bounded trust-clip-KL actuator controls magnitude. We evaluate two models on two reasoning benchmarks against static RLVR, matched-random selection, confidence thresholding, noise correction, and verifier augmentation. On Qwen3.5-0.8B and GSM8K at target risk $\rho=0.08$, RC-VAPO achieves 74.1% accuracy, selected harmful risk 0.0697, coverage 0.4125, and relative verifier cost $1.16\times$. At matched coverage and update magnitude, its selected-risk difference from matched random is -0.0260 with paired 95% interval $[-0.0364,-0.0157]$. Across asymmetric, confidence-dependent, and correlated-verifier noise, the certificate is satisfied on 57 of 60 independent runs. These comparisons isolate informative directional selection from proposal suppression, update shrinkage, and additional verifier computation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.33662
PDF
-
Rethinking GRPO for Large Reasoning Model Safety Alignment
2026-10-16 07:53:36Jiawei Chen, Yi Zhang, Jiawei Du, Zhonghou Lv, Tairan Chen, Junyuan Shang, Jinchang Hou, Xiao Yang, Yu Tian, Chenfu Bao, Chao Yu, Zhaoxia YinAbstract
Large reasoning models (LRMs) exhibit strong reasoning capabilities but remain vulnerable to unsafe outputs. While Group Relative Policy Optimization (GRPO) is widely used for safety alignment, its group-relative optimization may provide insufficient safety-directed learning signals. In this paper, we identify two failure modes: advantage collapse, where homogeneous rollout groups yield vanishing advantages, and unsafe diversification, where unsafe behaviors persist and become increasingly diverse. Our theoretical analysis reveals that behavioral consistency weakens within-group safety contrasts, while entropy regularization can diversify unsafe responses when relative signals vanish. To address these challenges, we propose Beacon, comprising Safety Signal Recovery (SSR) and Safety-Utility Decoupled Alignment (SUDA). SSR combines advantage-guided trajectory filtering and safe reference supervision to recover effective safety learning signals, while SUDA employs category-aware rewards and benign-only KL anchoring to mitigate over-refusal without compromising safety. Experiments across four Qwen3 and DeepSeek-R1-Distill variants and eight benchmarks show that our framework achieves the best average safety and reasoning performance, reducing average safety error by up to 32.83 percentage points while maintaining low over-refusal.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23085
PDF
-
A100: A Hybrid Vision Foundation Model for Agricultural Plant Image Analysis
2026-10-16 06:15:49Mayur Pratim Das, Ajai Dubey, Aksshay Mathew P, Sana Afreen, Rishi Kumar Soni, Deepak Meena, Pratibha Kumari, Mukesh SainiAbstract
The use of accurate vision models for crop monitoring, disease diagnosis, and plant phenotyping in agriculture is hindered by the lack of expertly annotated data, especially in developing countries. We propose A100, an agricultural vision foundation model that is pre-trained using self-supervised learning on 3 million unlabeled images from fields covering more than 100 crop species. A100 uses a hybrid CNN-Transformer backbone that fuses MBConv stages for local feature extraction with Transformer stages for global contextual representation. A100 uses pre-training with the integration of DINO self-distillation, iBOT masked patch reconstruction, and KoLeo uniformity regularization, resulting in features that are better than ImageNet-12K supervised representations for agricultural applications without any fine-tuning. By utilizing a frozen backbone, the accuracy for crop classification of A100 is 95.37%, which is +2.56% better than ImageNet-12K, and reduces the leaf count error by 10.4% on the GroMo25 phenotyping benchmark, proving that the same backbone can be used for classification and regression tasks. After full fine-tuning, the performance of A100 is 99.90% on 32-class crop identification and 99.02% on 44-class disease detection. On the difficult PlantDoc dataset, A100 outperforms all baselines, such as CvT-13 (64.89% against 63.56%). Remarkably, A100 obtains 98.01% accuracy on plant classification using just 1% of the labelled data (about 284 images per category), showing great label efficiency for use cases with limited labeling. Under an identical protocol, A100 also outperforms the publicly released agricultural foundation models FoMo4Wheat and LeafVision by more than 14 points at 1% labels. We plan to publicly release our pretrained model to allow agricultural professionals to adapt A100 for various plant analysis applications using limited annotations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22991
PDF
-
Hardware-as-Regularization: Enhancing Data Consistency in Imitation Learning via an Adjustable Passive Compliant Leader Arm
2026-10-16 05:56:54Hideyuki Ichiwara, Yushi Kaida, Hirokazu IshidaAbstract
Low-cost passive leader arms enable scalable data collection for imitation learning, but their lack of restoring forces leaves redundant joints unconstrained, yielding highly inconsistent joint-space trajectories. We address this with a low-cost passive joint module (an adjustable mechanical clutch and a 3D-printed spiral spring) that pulls each joint toward a user-defined neutral posture. This passive restoring force acts as a physical prior equivalent to joint-space $L_2$ regularization (``Hardware-as-Regularization''), improving kinematic consistency with shorter completion time than an unregularized arm and preserved movement smoothness. Experiments show substantial variance reduction over a naive passive arm, trajectory consistency on par with an active virtual spring of the same actuator class, and substantially higher downstream success rates (e.g., 73.3% vs. 36.7% on Block Stacking); a stiffness sweep shows consistency degrading monotonically as stiffness decreases, confirming that mechanical stiffness behaves like a regularization weight.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22977
PDF
