arXiv:2508.15358v2 Announce Type: replace Abstract: In many planning applications, we might be interested in finding plans that minimally modify the initial state to achieve the goals. We refer to this concept as plan disruption. In this paper, we formally introduce it, and define various planning-based compilations that aim to jointly optimize both the sum of […]
OmniTabBench: Mapping the Empirical Frontiers of GBDTs, Neural Networks, and Foundation Models for Tabular Data at Scale
arXiv:2604.06814v1 Announce Type: cross Abstract: While traditional tree-based ensemble methods have long dominated tabular tasks, deep neural networks and emerging foundation models have challenged this primacy, yet no consensus exists on a universally superior paradigm. Existing benchmarks typically contain fewer than 100 datasets, raising concerns about evaluation sufficiency and potential selection biases. To address these […]
Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline
arXiv:2412.19685v2 Announce Type: replace-cross Abstract: Existing facial forgery detection methods typically focus on binary classification or pixel-level localization, providing little semantic insight into the nature of the manipulation. To address this, we introduce Forgery Attribution Report Generation, a new multimodal task that jointly localizes forged regions (“Where”) and generates natural language explanations grounded in the […]
k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPS
arXiv:2604.03815v2 Announce Type: replace-cross Abstract: Graph transformers have shown promise in overcoming limitations of traditional graph neural networks, such as oversquashing and difficulties in modeling long-range dependencies. However, their application to large-scale graphs is hindered by the quadratic memory and computational complexity of the all-to-all attention mechanism. Although alternatives such as linearized attention and restricted […]
TREASURE: The Visa Payment Foundation Model for High-Volume Transaction Understanding
arXiv:2511.19693v3 Announce Type: replace-cross Abstract: Payment networks form the backbone of modern commerce, generating high volumes of transaction records from daily activities. Properly modeling this data can enable applications such as abnormal behavior detection and consumer-level insights for hyper-personalized experiences, ultimately improving people’s lives. In this paper, we present TREASURE, TRansformer Engine As Scalable Universal […]
SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
arXiv:2604.06811v1 Announce Type: cross Abstract: Skill-based agent systems tackle complex tasks by composing reusable skills, improving modularity and scalability while introducing a largely unexamined security attack surface. We propose SkillTrojan, a backdoor attack that targets skill implementations rather than model parameters or training data. SkillTrojan embeds malicious logic inside otherwise plausible skills and leverages standard […]
Stabilizing Unsupervised Self-Evolution of MLLMs via Continuous Softened Retracing reSampling
arXiv:2604.03647v2 Announce Type: replace-cross Abstract: In the unsupervised self-evolution of Multimodal Large Language Models, the quality of feedback signals during post-training is pivotal for stable and effective learning. However, existing self-evolution methods predominantly rely on majority voting to select the most frequent output as the pseudo-golden answer, which may stem from the model’s intrinsic biases […]
VisionClaw: Always-On AI Agents through Smart Glasses
arXiv:2604.03486v2 Announce Type: replace-cross Abstract: We present VisionClaw, an always-on wearable AI agent that integrates live egocentric perception with agentic task execution. Running on Meta Ray-Ban smart glasses, VisionClaw continuously perceives real-world context and enables in-situ, speech-driven action initiation and delegation via OpenClaw AI agents. Therefore, users can directly execute tasks through the smart glasses, […]
FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling
arXiv:2604.06916v1 Announce Type: cross Abstract: Reinforcement-Learning-based post-training has recently emerged as a promising paradigm for aligning text-to-image diffusion models with human preferences. In recent studies, increasing the rollout group size yields pronounced performance improvements, indicating substantial room for further alignment gains. However, scaling rollouts on large-scale foundational diffusion models (e.g., FLUX.1-12B) imposes a heavy computational […]
Flow Motion Policy: Manipulator Motion Planning with Flow Matching Models
arXiv:2604.07084v1 Announce Type: cross Abstract: Open-loop end-to-end neural motion planners have recently been proposed to improve motion planning for robotic manipulators. These methods enable planning directly from sensor observations without relying on a privileged collision checker during planning. However, many existing methods generate only a single path for a given workspace across different runs, and […]
Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction
arXiv:2604.01204v2 Announce Type: replace-cross Abstract: Primitive-based methods such as 3D Gaussian Splatting have recently become the state-of-the-art for novel-view synthesis and related reconstruction tasks. Compared to neural fields, these representations are more flexible, adaptive, and scale better to large scenes. However, the limited expressivity of individual primitives makes modeling high-frequency detail challenging. We introduce Neural […]
TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories
arXiv:2604.07223v1 Announce Type: cross Abstract: As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces. While safety guardrails are well-benchmarked for natural language responses, their efficacy remains largely unexplored within multi-step tool-use trajectories. To address this gap, we introduce TraceSafe-Bench, the […]