{"success":true,"data":[{"id":"arxiv:2607.22535","source":"arxiv","source_id":"2607.22535","title":"Robot-Factored World Models via Robot Rendering","abstract":"Action-conditioned video world models predict future observations from an initial observation and an action signal. In robotics, actions influence future observations through two distinct processes: they are first realized into robot motion by the robot body and controller, and the scene then responds through contact and object motion. Conditioning directly on action commands asks the world model to learn the realization process itself, while conditioning on logged future states leaks the interaction outcomes it is meant to predict. We propose robot-factored world models, which move two robot-specific factors outside the world model. First, action realization: each command is rolled through the robot's own controller and kinematics into a deployment-available nominal trajectory, a middle signal that avoids both action-realization learning and future-state leakage. Second, robot rendering: this nominal trajectory is rendered through the robot URDF, factoring the robot's geometry, kinematics, and appearance out of the model and into explicit rendered robot geometry. To resolve depth ambiguity, we pair end-effector depth with scene depth, giving geometric cues for contact and occlusion beyond image-plane overlap. Together, camera-aware static RGB/depth context and rendered robot geometry form a shared visual world-model interface that stays consistent across viewpoints and robot embodiments, so the model sees the action only as visible robot geometry and learns how objects respond to it. Our experiments show that the rendered interface outperforms vector-conditioned baselines and generalizes to unseen robot embodiments at inference. We further demonstrate that our model generates robot manipulation videos from human demonstrations by retargeting and rendering the hand motion as robot geometry.","authors":[{"name":"B"},{"name":"T"},{"name":"H"},{"name":"H"}],"categories":["cs.RO","cs.CV"],"primary_category":"cs.RO","published_date":"2026-07-24T17:59:57Z","updated_date":"2026-07-24T17:59:57Z","pdf_url":"https://arxiv.org/pdf/2607.22535v1","abs_url":"https://arxiv.org/abs/2607.22535v1","doi":null,"journal_ref":null,"comment":"Project Page: https://bjkim95.github.io/rofacto/","pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:00","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22534","source":"arxiv","source_id":"2607.22534","title":"SM4RT: Learning Structured Motion Geometry for 4D Reconstruction","abstract":"Geometry Foundation Models (GFMs) have substantially advanced monocular 3D reconstruction, yet extending this capability to 4D dynamic understanding remains a fundamental challenge. Most existing motion perception methods (e.g., sparse tracking, dense point-wise flow) treat motion as independent point-wise displacements, ignoring the structured nature of physical motion. However, real-world objects usually obey rigid-body kinematics, and points thus usually move collectively, not in isolation. Motion itself possesses geometric structure: physical objects undergo a set of rigid-body transformations governed by SE(3), rather than unstructured point-wise displacements. Building on this insight, we propose SM4RT, a Structured Motion 4D Reconstruction Transformer for end-to-end 3D reconstruction and structured motion perception. SM4RT introduces Structure-of-Motion to represent scene dynamics, where scene motion is decomposed into a compact set of motion bases, each represented as a temporal sequence of 6D twists in SE(3). Dense scene motion is then recovered by sparse, time-shared per-pixel assignment weights over these bases, ensuring points on the same object share a common rigid-body motion trajectory. SM4RT introduces a parallel motion geometry encoder and decoder that jointly infer 3D geometry, world-coordinate motion, and scene kinematic structure in a single forward pass from monocular RGB video. SM4RT achieves strong motion reconstruction performance while preserving the geometric structure of scene motion.","authors":[{"name":"S"},{"name":"W"},{"name":"D"},{"name":"Y"},{"name":"J"},{"name":"J"}],"categories":["cs.CV","cs.AI","cs.RO"],"primary_category":"cs.CV","published_date":"2026-07-24T17:59:51Z","updated_date":"2026-07-24T17:59:51Z","pdf_url":"https://arxiv.org/pdf/2607.22534v1","abs_url":"https://arxiv.org/abs/2607.22534v1","doi":null,"journal_ref":null,"comment":"Code is available at: https://github.com/wzzheng/SM4RT","pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:00","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22531","source":"arxiv","source_id":"2607.22531","title":"Twins: Learn to Predict Unified Representations with Focal Loss","abstract":"Unified multimodal models seek a shared visual token space that supports both multimodal understanding and image generation. Discrete methods unify the interface via a shared codebook, whereas continuous pipelines often rely on two disparate representations -- semantic features (e.g., ViT) for understanding and low-level latents (e.g., VAE) for synthesis -- resulting in mismatched latent spaces. We propose Twins, a unified continuous token space formed by channel-wise concatenating ViT and VAE features on the same token grid, so the sequence length is unchanged and attention cost does not increase. However, jointly modeling Twins in a Diffusion Transformer exposes a severe optimization imbalance: the model fits the ViT component well but struggles to match the VAE latent distribution. We trace this imbalance to three sources of heterogeneity: frequency bias, intrinsic dimensionality, and condition-aligned vs condition-independent uncertainty. To address it, we adapt a focal regression objective for flow matching that upweights large-error VAE dimensions, better balancing optimization across the ViT and VAE components. On ImageNet, this yields up to 10.57 gFID gain over naive MSE loss without classifier-free guidance. Twins also performs competitively on multimodal understanding benchmarks and improves reconstruction fidelity, narrowing the gap between understanding- and generation-oriented representations.","authors":[{"name":"K"},{"name":"X"},{"name":"B"},{"name":"H"},{"name":"Y"},{"name":"M"},{"name":"B"},{"name":"J"},{"name":"M"},{"name":"Z"},{"name":"L"},{"name":"X"}],"categories":["cs.CV"],"primary_category":"cs.CV","published_date":"2026-07-24T17:59:39Z","updated_date":"2026-07-24T17:59:39Z","pdf_url":"https://arxiv.org/pdf/2607.22531v1","abs_url":"https://arxiv.org/abs/2607.22531v1","doi":null,"journal_ref":null,"comment":"ICML 2026. Code: https://github.com/Tencent-Hunyuan/Twins","pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:00","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22530","source":"arxiv","source_id":"2607.22530","title":"ViTacWorld: Scaling Visuo-Tactile World Models for Contact-Rich Robot Manipulation","abstract":"Contact-rich robot manipulation requires physical interaction cues that are often invisible to cameras, making tactile sensing essential for robust control. However, scaling visuo-tactile robot learning remains difficult because real tactile interaction data are expensive to collect, hardware-dependent, and limited in task and scene diversity. We present ViTacWorld, an action-conditioned visuo-tactile world model for scalable contact-rich robot manipulation. ViTacWorld leverages public real tactile datasets and a constructed simulation environment to scale visuo-tactile-action data, exploiting the fact that tactile signals are directly grounded in physical contact and can exhibit a smaller simulation-to-real gap than purely visual observations. The model is first pretrained with large-scale real and simulated visuo-tactile trajectories, and then finetuned with real-world policy rollouts to better match downstream manipulation behaviors. Given robot actions, ViTacWorld predicts temporally aligned visual observations and tactile feedback, enabling visuo-tactile-action rollout generation. To the best of our knowledge, ViTacWorld is the first framework that uses a world model for robot visuo-tactile-action trajectory generation and policy evaluation. It serves two roles: synthesizing rollouts to improve downstream tactile policies, and evaluating policies by predicting action-conditioned visuo-tactile outcomes under controlled action sequences. Experiments on contact-rich manipulation tasks show that ViTacWorld generates physically meaningful rollouts, improves policy performance through scalable data augmentation, and enables action-conditioned policy evaluation. Project page: https://vitacworld.github.io/","authors":[{"name":"Y"},{"name":"S"},{"name":"H"},{"name":"S"},{"name":"S"},{"name":"Z"},{"name":"Y"},{"name":"J"}],"categories":["cs.RO"],"primary_category":"cs.RO","published_date":"2026-07-24T17:59:33Z","updated_date":"2026-07-24T17:59:33Z","pdf_url":"https://arxiv.org/pdf/2607.22530v1","abs_url":"https://arxiv.org/abs/2607.22530v1","doi":null,"journal_ref":null,"comment":"18 pages, 6 figures, 5 tables. Project page: https://vitacworld.github.io/","pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:00","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22529","source":"arxiv","source_id":"2607.22529","title":"Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills","abstract":"LLM training is shifting from manual design and annotation to interaction-driven self-evolution. However, existing self-evolutionary methods face a fundamental dilemma between task diversity and verification reliability: environment-bound methods obtain precise feedback but confine learning to narrow domains, while open-ended self-generation broadens the task space but lacks reliable verification, allowing misleading rewards to pollute the training loop. We identify agent skills as a powerful middle ground to reconcile this tension: each skill ensures deep, verifiable execution in a specific scenario, while dynamic routing across skills maintains open-ended task variety. Leveraging this insight, we introduce Skill Self-Play (Skill-SP), a co-evolutionary framework comprising a proposer, a solver, and a dynamic skill controller. Orchestrated via a reinforcement learning loop, these components co-evolve in a continuous self-play loop: the proposer generates challenging tasks conditioned on dynamically sampled skills; the solver explores candidate solutions to push its capability boundaries; and the skill controller collects execution feedback to update and expand the skill library. This interactive co-evolution effectively bridges the gap between structured verification and open-ended exploration. Empirical evaluations on tool-use and reasoning benchmarks demonstrate that Skill-SP, serving as a robust evolution engine, consistently pushes the performance ceiling of competent backbones while catalyzing striking turnarounds for initially misaligned models. Our code is available at https://github.com/Qwen-Applications/skill-self-play.","authors":[{"name":"S"},{"name":"P"},{"name":"H"},{"name":"T"},{"name":"Y"},{"name":"J"},{"name":"S"},{"name":"Z"},{"name":"G"},{"name":"M"},{"name":"Y"},{"name":"X"},{"name":"G"}],"categories":["cs.CL"],"primary_category":"cs.CL","published_date":"2026-07-24T17:59:22Z","updated_date":"2026-07-24T17:59:22Z","pdf_url":"https://arxiv.org/pdf/2607.22529v1","abs_url":"https://arxiv.org/abs/2607.22529v1","doi":null,"journal_ref":null,"comment":null,"pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:00","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22525","source":"arxiv","source_id":"2607.22525","title":"Explainable Reinforcement Learning for assisting Air Traffic Controllers","abstract":"To effectively integrate AI into high-stakes, critical environments such as healthcare, autonomous driving, and aviation--and to advance toward higher levels of automation and seamless human-AI collaboration--building trust in AI-driven solutions is essential. Trust, in turn, is closely linked to the explainability of AI systems. The rapid advancements in AI across various domains have underscored the challenges of establishing trust, raising increasing interest in AI explainability even more when applied to deep learning. In this context, the present work aims to explore the application of explainability techniques to Reinforcement Learning (RL) algorithms, specifically within the safety-critical domain of Air Traffic Control (ATC). Using a simplified ATC environment as an initial testbed, an intelligent agent is trained with a reinforcement learning algorithm to make decisions on alternative flight routes that avoid no-fly zones. As a preliminary explainability approach, a saliency map is employed, providing insights into the input features that most significantly influence the agent's decision-making process.","authors":[{"name":"A"},{"name":"G"},{"name":"S"}],"categories":["cs.AI"],"primary_category":"cs.AI","published_date":"2026-07-24T17:56:38Z","updated_date":"2026-07-24T17:56:38Z","pdf_url":"https://arxiv.org/pdf/2607.22525v1","abs_url":"https://arxiv.org/abs/2607.22525v1","doi":"10.1007/978-3-031-87778-0_14","journal_ref":"In: L. Barolli (ed.), Advanced Information Networking and Applications (AINA 2025), Lecture Notes on Data Engineering and Communications Technologies, vol. 250, pp. 148-157, Springer, Cham (2025)","comment":"11 pages (10-page paper plus 1 cover/citation page), 4 figures, 1 table; published in AINA 2025","pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:00","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22520","source":"arxiv","source_id":"2607.22520","title":"The Regression Tax: Decomposing Why Skills Help and Hurt LLM Agents","abstract":"Adding procedural skills to an LLM agent is typically evaluated by average improvement in task success. However, this metric hides an important cost: skills can also make agents worse. We measure both sides by comparing agents with and without skills across nearly 6,000 runs spanning two office automation benchmarks and three model harness stacks. This allows us to distinguish two outcomes. A regression is a task solved without skills but failed after skills are added. A residual failure is a task that fails both with and without skills. We find that regressions are substantial enough that the best performing skills outperform others primarily by regressing less, not by gaining more. We identify three causes of regression: (i) skill description osmosis, a skill changes an agent's behavior simply by being present in context, even when it is never invoked; (ii) grounding displacement, a skill's prescribed procedure overrides how the agent interprets its inputs; and (iii) verification displacement, where the procedure suppresses checks the agent would otherwise perform on its outputs. Analysing persistent failures reveals the same underlying pattern. Existing skills overemphasize procedural guidance the stage least often responsible for failure while under supporting grounding and verification, the dominant sources of remaining errors. After correcting evaluation artifacts and studying traces, we find many regressions and persistent failures recoverable through better grounding and verification. Procedural skills should be evaluated by decomposing their net effect into gains and regressions, not by aggregate improvement alone. We identify three regression modes skills should avoid, and find that reliability depends more on grounding and verification than on procedural skill choice.","authors":[{"name":"D"},{"name":"B"}],"categories":["cs.AI"],"primary_category":"cs.AI","published_date":"2026-07-24T17:50:03Z","updated_date":"2026-07-24T17:50:03Z","pdf_url":"https://arxiv.org/pdf/2607.22520v1","abs_url":"https://arxiv.org/abs/2607.22520v1","doi":null,"journal_ref":null,"comment":null,"pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:00","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22518","source":"arxiv","source_id":"2607.22518","title":"PinEqualizer: Full Funnel Content Exploration and Debiasing System at Pinterest","abstract":"In this paper, we propose a new solution for addressing the content cold-start problem in industry-scale search and recommender systems. Compared to prior approaches, we have made the following new contributions: 1) our solution spans the entire multi-stage funnel and generalizes well for both search and recommendation surfaces, 2) our solution reduces bias favoring existing content, allowing more accurate model prediction across content types and reducing short-term tradeoffs associated with high volumes of explicit content exploration, 3) our solution is evaluated with a scalable measurement framework that enables fast short-term experimentation while validating long-term impact. We have iteratively built and successfully deployed this new system at Pinterest in the past two years and observed significant improvements in fresh content exploration, overall user engagement, and content ecosystem health.","authors":[{"name":"O"},{"name":"B"},{"name":"H"},{"name":"A"},{"name":"S"},{"name":"H"},{"name":"M"},{"name":"L"},{"name":"Z"},{"name":"J"},{"name":"W"},{"name":"B"},{"name":"A"},{"name":"W"},{"name":"K"},{"name":"J"},{"name":"Z"},{"name":"Z"}],"categories":["cs.IR","cs.LG"],"primary_category":"cs.IR","published_date":"2026-07-24T17:41:28Z","updated_date":"2026-07-24T17:41:28Z","pdf_url":"https://arxiv.org/pdf/2607.22518v1","abs_url":"https://arxiv.org/abs/2607.22518v1","doi":null,"journal_ref":null,"comment":"10 pages, 2 figures. Accepted at KDD 2026","pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:00","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22516","source":"arxiv","source_id":"2607.22516","title":"Quantum Spectral Model: Data Reuploading with Input-Conditioned Frequency Support","abstract":"A central design principle in modern machine learning and artificial intelligence is to align a model's inductive bias with the structure of its input data. For matrix-valued inputs, relevant matrix-level relationships can be characterised through spectral values and spectral subspaces; however, common coordinate-wise rotation-gate data-encoding unitaries used in most quantum machine learning models do not explicitly construct such a matrix-level representation. We introduce Quantum Spectral Models (QSMs), in which we construct the generator of the data-encoding unitary directly from each input matrix. We study three QSM variants based on symmetric, global block, and non-overlapping patch-local block Hamiltonians. Their outputs admit truncated Fourier representations in which input-dependent spectral gaps supply candidate phase carriers, while spectral subspaces help determine their coefficients. We evaluate the QSMs and comparison quantum models on two matrix representations of Pendigits and two controlled synthetic tasks defined by spectral statistics. At the largest evaluated circuit depth, QSM variants lead the tested quantum models in mean test accuracy across all four benchmarks. The patch-local QSM leads on Pendigits, whereas the global block-Hamiltonian QSM leads on the controlled spectral tasks. Ablations show a task-dependent reversal: subspace-preserving controls perform better on Pendigits, whereas spectral-value-only controls lead among the tested ablations on the synthetic tasks. Together, these results shed new light on quantum machine-learning model design by showing how input-conditioned spectral representations can provide an analysable inductive bias, while offering a broader perspective on structure-aware model design in machine learning and artificial intelligence.","authors":[{"name":"P"},{"name":"U"},{"name":"C"}],"categories":["quant-ph","cs.AI","cs.LG"],"primary_category":"quant-ph","published_date":"2026-07-24T17:39:14Z","updated_date":"2026-07-24T17:39:14Z","pdf_url":"https://arxiv.org/pdf/2607.22516v1","abs_url":"https://arxiv.org/abs/2607.22516v1","doi":null,"journal_ref":null,"comment":"53 pages, many figures","pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:00","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22514","source":"arxiv","source_id":"2607.22514","title":"Dysphagia Risk Stratification in Head and Neck Cancer via Two-Stage PRO-Clinical Stacking","abstract":"Dysphagia is a debilitating late effect of head and neck cancer (HNC) treatment, yet timely identification of at-risk patients remains challenging in survivorship care. Definitive assessment relies on videofluoroscopic imaging, as captured by the Dynamic Imaging Grade of Swallowing Toxicity (CTCAE-DIGEST), which, while validated, requires specialized equipment, trained personnel, and significant patient burden, limiting its routine use in surveillance. Patient-reported outcomes (PROs), by contrast, are low-cost, scalable, and easily collected at any clinical encounter, making them an attractive alternative signal for identifying patients who may warrant further evaluation. However, a clear clinical framework for translating PRO responses into actionable interventions is still evolving. In particular, uncertainty remains regarding when a patient's self-reported symptom burden should prompt escalation of care. This study addresses this gap by formulating a single-visit PRO-clinical prediction framework and introducing a clinically interpretable two-stage stacking model to predict swallowing impairment risk using PRO responses and structured clinical variables, without requiring videofluoroscopic imaging. The proposed framework quantifies the independent contributions of patient-reported symptoms and clinical factors within a unified and interpretable risk assessment model. Our findings demonstrate that individual MDADI responses contain predictive information beyond that captured by composite or global summary scores, while interpretability analyses reveal symptom patterns and clinical risk factors associated with swallowing impairment. Together, these results support the use of structured PRO-clinical integration as a practical, imaging-free approach for dysphagia risk stratification in HNC survivorship.","authors":[{"name":"S"},{"name":"E"},{"name":"Z"},{"name":"Y"},{"name":"C"},{"name":"X"},{"name":"G"},{"name":"G"}],"categories":["cs.LG"],"primary_category":"cs.LG","published_date":"2026-07-24T17:34:26Z","updated_date":"2026-07-24T17:34:26Z","pdf_url":"https://arxiv.org/pdf/2607.22514v1","abs_url":"https://arxiv.org/abs/2607.22514v1","doi":null,"journal_ref":null,"comment":null,"pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:00","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22513","source":"arxiv","source_id":"2607.22513","title":"Opaque Epistemic Mediation: How LLM Deployment Configurations Shape the Validation of Pseudo-Science","abstract":"Commercial large language models are increasingly used as knowledge references, yet their stance on contested scientific claims is neither stable nor transparent. We tested how four major LLM families (Claude, Grok, GPT, Gemini) evaluate ethnonationalist pseudo-science derived from Frank Salter's biosocial framework across four temporal snapshots (October 2025-February 2026), via both API and web interfaces. Grok's Fast versions (which power the default user experience on X) consistently assigned credibility scores of 70-75, two to five times higher than all other models (which scored 15-40). This pattern was absent from control prompts testing basic evolutionary consensus and refuted Lamarckian claims, where all models performed comparably. Three additional findings emerged: (1) a silent patch reversed Grok's behaviour from chaotic to stably high validation overnight, without any public documentation; (2) the same Grok model identifier produced radically divergent outputs via API (75) and web (5.5) three months later; (3) refusal to rate the pseudo-scientific claim, the most defensible response observed, appeared in two model families through different interfaces (Claude Opus 4.1 categorically via web, GPT-5.1 Chat intermittently via API) and eroded in the successor version of each. These results indicate that the epistemic stance of a commercial LLM is not a stable property of the model but a contingent effect of deployment configuration: system prompts, safety layers, interface routing, and silent updates. This remains opaque to users and researchers alike. We argue this constitutes a matter of public concern requiring new forms of epistemic accountability.","authors":[{"name":"D"},{"name":"H"},{"name":"J"}],"categories":["cs.CY","cs.AI","cs.CL"],"primary_category":"cs.CY","published_date":"2026-07-24T17:32:43Z","updated_date":"2026-07-24T17:32:43Z","pdf_url":"https://arxiv.org/pdf/2607.22513v1","abs_url":"https://arxiv.org/abs/2607.22513v1","doi":null,"journal_ref":null,"comment":"16 pages, 2 tables","pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:00","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22511","source":"arxiv","source_id":"2607.22511","title":"CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference","abstract":"Automating theoretical research is constrained not only by the generation of candidate results, but also by their reliable evaluation. A common approach is to close the research loop with a large language model (LLM) reviewer. However, such reviewers remain empirically unreliable: they may accept fabricated papers and detect them at rates close to chance (Bad Scientist, 2025). We present CausalForge, a framework for automated theoretical research in causal inference grounded in the Lean proof assistant. CausalForge combines Causalean, a foundational Lean library for causal inference containing 7,035 machine-checked declarations developed with language-model assistance under human design and review, with CausalSmith, a self-improving agentic pipeline that selects research topics, proposes results, formalizes statements, constructs proofs, and presents the resulting artifacts for human inspection. Because a machine-checked proof establishes only that a formal statement follows from its assumptions, not that the statement faithfully captures the intended scientific claim, the pipeline augments kernel verification with a statement audit that compares each formal theorem against the informal claim it is intended to express. We evaluate the system using artifacts produced by completed autonomous research runs. The source code, formal library, and run records are available at https://github.com/Jiyuan-Tan/CausalForge.","authors":[{"name":"J"},{"name":"V"}],"categories":["stat.ML","cs.AI","cs.LG","econ.EM"],"primary_category":"stat.ML","published_date":"2026-07-24T17:32:35Z","updated_date":"2026-07-24T17:32:35Z","pdf_url":"https://arxiv.org/pdf/2607.22511v1","abs_url":"https://arxiv.org/abs/2607.22511v1","doi":null,"journal_ref":null,"comment":null,"pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:00","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22508","source":"arxiv","source_id":"2607.22508","title":"Interpretable EEG biomarkers with bag-of-waves: Spatial and temporal waveform dictionaries for low-data regimes","abstract":"Electroencephalography (EEG) is widely used to diagnose neurological conditions, but its analysis usually relies on either predefined spectral features or deep neural networks. Predefined features carry a strong bias, since they fix in advance what counts as informative, while deep neural networks and foundation models are hard to interpret and need large amounts of data and compute. We present bag-of-waves, an interpretable framework that learns a small dictionary of recurring EEG waveform templates, called atoms, using shift-invariant k-means without labels. The continuous EEG is then turned into a sequence of atom tokens, whose counts feed a simple downstream classifier or clustering step. We extend this representation in two ways: we add atom-to-atom transitions, which we call n- grams, to capture temporal structure, and we move from single-channel atoms to regional and cross-channel spatial atoms for the multichannel case. We test the method on three complementary datasets, each probing a different aspect: single-channel mouse genotype clustering with only sixteen animals (the low-data and temporal case), resting-state dementia classification (the spatial case), and the TUEV benchmark, a six-way classification of clinical EEG events (a high-data comparison against strong deep and foundation baselines). Across all three datasets, bag-of-waves achieves performance competitive with state-of-the-art deep and foundation models. Yet, it operates with a fraction of the parameter count and provides full interpretability: because every atom corresponds to an inspectable waveform, the method explicitly recovers known clinical morphologies that a neurophysiologist can directly validate. Its main advantage is that it works in the low-data regime where heavier models are a poor fit.","authors":[{"name":"A"},{"name":"S"},{"name":"L"},{"name":"A"},{"name":"J"},{"name":"M"},{"name":"Z"}],"categories":["cs.LG","eess.SP"],"primary_category":"cs.LG","published_date":"2026-07-24T17:27:43Z","updated_date":"2026-07-24T17:27:43Z","pdf_url":"https://arxiv.org/pdf/2607.22508v1","abs_url":"https://arxiv.org/abs/2607.22508v1","doi":null,"journal_ref":null,"comment":"In Review","pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:00","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22494","source":"arxiv","source_id":"2607.22494","title":"CARA: Concept-Aware Risk Attention for Interpretable Collision Anticipation","abstract":"Collision anticipation in autonomous driving requires not only accurate early warnings but also interpretable reasoning about what risk factors are being tracked and how risk evolves over time. Existing methods fall short in this regard: feature-driven models are opaque, post-hoc explanations often lack fidelity, and concept-based methods are mostly designed for static recognition rather than dynamic driving scenes. We propose CARA (Concept-Aware Risk Attention), an intrinsically interpretable spatio-temporal framework for collision anticipation. CARA derives domain-grounded risk concepts from accident narratives, aligns them with video frames via vision-language similarity, and organizes them into evolving concept trajectories. These trajectories provide explicit risk evidence that guides spatial attention, temporal attention, and anticipation, allowing semantic concepts to directly influence both where the model attends and how it predicts risk over time. By treating semantic risk factors as dynamic intermediate evidence rather than auxiliary post-hoc explanations, CARA tightly couples interpretability with the predictive process. Extensive experiments on three benchmarks show that CARA consistently improves anticipation accuracy and warning earliness over strong baselines, while providing sparse and semantically grounded concept evidence.","authors":[{"name":"Z"},{"name":"R"},{"name":"Y"},{"name":"E"},{"name":"Y"},{"name":"S"},{"name":"Y"},{"name":"J"},{"name":"Y"}],"categories":["cs.MM","cs.CV"],"primary_category":"cs.MM","published_date":"2026-07-24T17:06:05Z","updated_date":"2026-07-24T17:06:05Z","pdf_url":"https://arxiv.org/pdf/2607.22494v1","abs_url":"https://arxiv.org/abs/2607.22494v1","doi":null,"journal_ref":null,"comment":"Accepted to ACM Multimedia 2026(Oral)","pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:00","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22493","source":"arxiv","source_id":"2607.22493","title":"The V-fold jackknife for semiparametric inference: variance estimation, confidence intervals, and simultaneous confidence bands","abstract":"For decades, the bootstrap has been a default tool for statistical inference because of its broad applicability and minimal analytic requirements. Although its validity is well understood for smooth parametric estimators, its theoretical properties for many modern semiparametric and machine-learning estimators remain largely unstudied. Nevertheless, bootstrap procedures are often used routinely in such settings, even when their validity is unknown and their computational cost is substantial. We develop the $V$-fold jackknife as a computationally efficient and theoretically justified alternative for semiparametric inference. It requires only $V$ leave-fold-out refits and uses the empirical dispersion of jackknife pseudo-values to quantify uncertainty, without deriving or evaluating an influence function. For regular asymptotically linear estimators of pathwise differentiable parameters, we show that, for fixed $V$, the Studentized $V$-fold jackknife statistic converges to a $t$-distribution with $V-1$ degrees of freedom, giving valid confidence intervals even though the jackknife variance estimator does not converge in probability. When $V\\to\\infty$, we establish consistency of the variance estimator at rate $V^{-1/2}$, allowing $V$ to diverge slowly, for example at rate $\\log n$. We also develop simultaneous confidence bands based on the correct componentwise-Studentized limiting distribution. Finally, we extend the theory to generalized asymptotically linear estimators with diverging influence-function variance and slower-than-$\\sqrt n$ convergence; scale invariance of Studentization eliminates the need to know the effective convergence rate. Simulations on the average treatment effect, Kaplan--Meier survival curve, and highly adaptive lasso dose-response curves confirm reliable inference, including where influence-function-based standard errors are anti-conservative or unstable.","authors":[{"name":"Y"},{"name":"A"},{"name":"M"}],"categories":["stat.ME","math.ST","stat.CO","stat.ML"],"primary_category":"stat.ME","published_date":"2026-07-24T17:05:54Z","updated_date":"2026-07-24T17:05:54Z","pdf_url":"https://arxiv.org/pdf/2607.22493v1","abs_url":"https://arxiv.org/abs/2607.22493v1","doi":null,"journal_ref":null,"comment":null,"pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:00","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22491","source":"arxiv","source_id":"2607.22491","title":"Susceptible Reservoir Architectures for Regime-Conditional Volatility Forecasting","abstract":"Volatility forecasting is dominated by persistence and measurement noise, leaving limited residual structure for nonlinear models to exploit. We introduce Susceptible Architectures (SUSA), a reservoir-design principle for volatility forecasting, and its two concrete implementations, based on complex-valued open-chain and periodic reservoirs and regime-conditioned experts to interpret reservoir features across calm, onset, recovery, and persistent-stress states. We also implement open-system $q$-qubit counterparts in Qiskit while retaining a common AR-Ridge anchor and a bounded residual correction trained under QLIKE. We evaluate models on 16 U.S. equity and exchange-traded-fund series using three disjoint chronological training, validation, and test folds, a 12-observation input window, and a five-observation forecast horizon. The proposed models perform competitively with GARCH, achieving statistically significant QLIKE improvements for specific assets (IWM, XLP). Also models' forecasts complement HARQ-style predictions: a stacked ensemble improves mean QLIKE by 0.0116 over its strongest constituent and wins in 75% of test scenarios.","authors":[{"name":"A"}],"categories":["cs.LG"],"primary_category":"cs.LG","published_date":"2026-07-24T17:03:08Z","updated_date":"2026-07-24T17:03:08Z","pdf_url":"https://arxiv.org/pdf/2607.22491v1","abs_url":"https://arxiv.org/abs/2607.22491v1","doi":null,"journal_ref":null,"comment":null,"pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:00","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22489","source":"arxiv","source_id":"2607.22489","title":"\\k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating","abstract":"Low-Rank Adaptation (LoRA) has become a widely adopted technique for efficient neural network fine-tuning, decomposing model updates into low-rank matrices. However, LoRA remains computationally costly because it updates all matrices uniformly, regardless of their actual contribution to adaptation. This cost is especially prohibitive for large-scale models with billions of parameters and for resource-constrained settings such as edge deployment and on-device fine-tuning. We show for the first time that not all LoRA matrices are equally worth tuning: matrices with smaller condition numbers (the ratio of largest to smallest singular value) are already well-balanced across directions and contribute only marginally to adaptation, whereas matrices with larger condition numbers contain underdeveloped directions that span richer subspaces and drive most of the performance gains. This observation itself is a key contribution of our work, and it motivates a more selective approach to fine-tuning. Building on this insight, we propose \\k{appa}-LoRA, a method that optimizes LoRA by focusing updates on the matrices with the largest condition numbers, which capture the most informative directions of change. By restricting LoRA updates to the top 50% of weight matrices ranked by condition number, \\k{appa}-LoRA halves the trainable parameter count and correspondingly reduces compute and memory cost. Extensive experiments across multiple benchmarks show that this design cuts fine-tuning time by 16.2% on average while matching the accuracy of standard LoRA and reducing memory cost by 4.5%. Further analysis reveals that the condition numbers of the selected matrices consistently decrease over training, suggesting that \\k{appa}-LoRA's effectiveness stems from targeted spectral rebalancing rather than parameter selection alone.","authors":[{"name":"J"},{"name":"S"},{"name":"F"},{"name":"M"},{"name":"K"},{"name":"Y"}],"categories":["cs.LG","cs.AI"],"primary_category":"cs.LG","published_date":"2026-07-24T17:00:40Z","updated_date":"2026-07-24T17:00:40Z","pdf_url":"https://arxiv.org/pdf/2607.22489v1","abs_url":"https://arxiv.org/abs/2607.22489v1","doi":null,"journal_ref":null,"comment":null,"pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:01","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22486","source":"arxiv","source_id":"2607.22486","title":"Optimal Transport Image Representation and Deep Covariance Alignment (CORAL) for Control Valve Stiction Detection","abstract":"Control valve stiction is a common cause of unwanted oscillations and poor control-loop performance in industrial processes. Data-driven methods can automatically detect stiction, but models trained purely on simulated data often struggle to generalize to real industrial control loops due to domain shift. To bridge this gap, this work propose a novel stiction detection methodology that combines optimal transport (OT) imaging technique with deep correlation alignment (Deep CORAL) algorithm. Closed loop signals: controller output and process variable are converted into two-dimensional OT images. These images capture the dynamic behaviour of control loops. The proposed methodology includes a convolutional neural network (CNN) encoder (or feature extractor) trained to learn domain-invariant representations by optimizing a combined objective: a cross-entropy loss on labeled simulation data and a Deep CORAL (covariance-alignment) loss between simulation data and unlabeled target-domain industrial data. Downstream classifiers trained on the domain-invariant target features were evaluated on an independent test set of 20 benchmark loops from industrial stiction data benchmark. The proposed methodology successfully diagnosed 18 out of the 20 loops and achieved100% recall across all 13 stiction cases, an accuracy of 90.00% and an F1-score of 92.86%. Compared to standard baseline approach (hand-crafted features-based method), the proposed methodology significantly mitigates domain shift, providing robust, highly reliable stiction detection for real-world industrial control loops.","authors":[{"name":"S"}],"categories":["cs.CV"],"primary_category":"cs.CV","published_date":"2026-07-24T16:56:33Z","updated_date":"2026-07-24T16:56:33Z","pdf_url":"https://arxiv.org/pdf/2607.22486v1","abs_url":"https://arxiv.org/abs/2607.22486v1","doi":null,"journal_ref":null,"comment":"7 pages, 6 figures, 6 tables","pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:01","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22484","source":"arxiv","source_id":"2607.22484","title":"Singular value soft-thresholding via the polar decomposition","abstract":"Singular value soft-thresholding can be computed via a reduction to the matrix polar decomposition, which allows one to exploit GPU-friendly algorithms for computing the polar decomposition. Empirically, there is a significant speed-up on GPUs compared to the standard approach using the SVD. We leave the investigation of robustness to future work, but note that due to the discontinuous nature of the sign function, the reduction to the polar decomposition is likely only suitable for low-accuracy applications.","authors":[{"name":"S"}],"categories":["math.NA","cs.LG","math.OC"],"primary_category":"math.NA","published_date":"2026-07-24T16:55:09Z","updated_date":"2026-07-24T16:55:09Z","pdf_url":"https://arxiv.org/pdf/2607.22484v1","abs_url":"https://arxiv.org/abs/2607.22484v1","doi":null,"journal_ref":null,"comment":"3 pages, 2 figures, technical report","pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:01","updated_at":"2026-07-27 18:28:00"},{"id":"arxiv:2607.22483","source":"arxiv","source_id":"2607.22483","title":"Plug, Play, and Comply: A Modular Framework for Online Variable Impedance with Arbitrarily Oriented Compliance Axes","abstract":"The paper proposes a robot-agnostic compliant-control framework that extends the ROS control ecosystem with standardized joint and Cartesian command interfaces. It addresses a key limitation of existing control software: no reusable infrastructure for implementing compliant-control algorithms across different manipulators while preserving a common interface to higher-level applications. A plugin-based architecture separates controller infrastructure from control-law implementation. Generic wrappers use existing hardware abstractions to interface with different manipulators, while runtime-loaded plugins implement only the control law. Command interfaces support joint- and Cartesian-space references, stiffness and damping gains, nullspace targets, and feedforward terms, enabling variable impedance and diverse compliant-control formulations. Robot kinematics and dynamics are computed from URDF models using Pinocchio. The architecture facilitates the development of compliant-control strategies and enables the same implementation to be deployed across platforms unchanged. The complete framework, including reference controllers, high-level task interfaces, and example configurations for various manipulators, is open-sourced. The reference Cartesian impedance controller supports task-dependent compliance by rotating translational and rotational stiffness and damping, allowing the principal compliance directions to be updated online according to local task geometry rather than remaining fixed in the robot base or TCP frame. This is particularly important in contact-rich manipulation, where the desired directions of motion, constraints, and compliance directions may vary throughout task execution. Real-robot experiments demonstrate task-dependent compliance in contact-rich manipulation, while simulations show portability across manipulators with distinct kinematic and dynamic characteristics.","authors":[{"name":"M"},{"name":"X"}],"categories":["cs.RO"],"primary_category":"cs.RO","published_date":"2026-07-24T16:53:51Z","updated_date":"2026-07-24T16:53:51Z","pdf_url":"https://arxiv.org/pdf/2607.22483v1","abs_url":"https://arxiv.org/abs/2607.22483v1","doi":null,"journal_ref":null,"comment":"8 pages, 7 figures, 2 tables. Paper page: https://smihael.github.io/plug-play-comply/","pdf_downloaded":false,"pdf_path":null,"trending_score":0,"citation_count":0,"github_stars":0,"created_at":"2026-07-27 18:15:01","updated_at":"2026-07-27 18:28:00"}],"meta":{"page":1,"per_page":20,"total":200,"total_pages":10}}