arXiv:2604.08304v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) significantly enhances large language models (LLMs) but introduces novel security risks through external knowledge access. While existing studies cover various RAG vulnerabilities, they often conflate inherent LLM risks with those specifically introduced by RAG. In this paper, we propose that secure RAG is fundamentally about the security […]
Exploring Temporal Representation in Neural Processes for Multimodal Action Prediction
arXiv:2604.08418v1 Announce Type: cross Abstract: Inspired by the human ability to understand and predict others, we study the applicability of Conditional Neural Processes (CNP) to the task of self-supervised multimodal action prediction in robotics. Following recent results regarding the ontogeny of the Mirror Neuron System (MNS), we focus on the preliminary objective of self-actions prediction. […]
PSI: Shared State as the Missing Layer for Coherent AI-Generated Instruments in Personal AI Agents
arXiv:2604.08529v1 Announce Type: cross Abstract: Personal AI tools can now be generated from natural-language requests, but they often remain isolated after creation. We present PSI, a shared-state architecture that turns independently generated modules into coherent instruments: persistent, connected, and chat-complementary artifacts accessible through both GUIs and a generic chat agent. By publishing current state and […]
Scaling Implicit Fields via Hypernetwork-Driven Multiscale Coordinate Transformations
arXiv:2511.18387v2 Announce Type: replace Abstract: Implicit Neural Representations (INRs) have emerged as a powerful paradigm for representing signals such as images, 3D shapes, signed distance fields, and radiance fields. While significant progress has been made in architecture design (e.g., SIREN, FFC, KAN-based INRs) and optimization strategies (meta-learning, amortization, distillation), existing approaches still suffer from two […]
Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
arXiv:2604.05333v2 Announce Type: replace Abstract: Skill usage has become a core component of modern agent systems and can substantially improve agents’ ability to complete complex tasks. In real-world settings, where agents must monitor and interact with numerous personal applications, web browsers, and other environment interfaces, skill libraries can scale to thousands of reusable skills. Scaling […]
MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models
arXiv:2412.20718v2 Announce Type: replace-cross Abstract: The rapid integration of Large Vision-Language Models (LVLMs) into critical domains necessitates comprehensive moral evaluation to ensure their alignment with human values. While extensive research has addressed moral evaluation in LLMs, text-centric assessments cannot adequately capture the complex contextual nuances and ambiguities introduced by visual modalities. To bridge this gap, […]
SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models
arXiv:2506.01062v4 Announce Type: replace-cross Abstract: We introduce SealQA, a new challenge benchmark for evaluating SEarch-Augmented Language models on fact-seeking questions where web search yields conflicting, noisy, or unhelpful results. SealQA comes in three flavors: (1) Seal-0 (main) and (2) Seal-Hard, which assess factual accuracy and reasoning capabilities, with Seal-0 focusing on the most challenging questions […]
Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling
arXiv:2603.04791v3 Announce Type: replace Abstract: We introduce Timer-S1, a strong Mixture-of-Experts (MoE) time series foundation model with 8.3B total parameters, 0.75B activated parameters for each token, and a context length of 11.5K. To overcome the scalability bottleneck in existing pre-trained time series foundation models, we perform Serial Scaling in three dimensions: model architecture, dataset, and […]
NaviSlim: Adaptive Context-Aware Navigation and Sensing via Dynamic Slimmable Networks
arXiv:2407.01563v2 Announce Type: replace-cross Abstract: Small-scale autonomous airborne vehicles, such as micro-drones, are expected to be a central component of a broad spectrum of applications ranging from exploration to surveillance and delivery. This class of vehicles is characterized by severe constraints in computing power and energy reservoir, which impairs their ability to support the complex […]
Distilling Specialized Orders for Visual Generation
arXiv:2504.17069v2 Announce Type: replace-cross Abstract: Autoregressive (AR) image generators are becoming increasingly popular due to their ability to produce high-quality images and their scalability. Typical AR models are locked onto a specific generation order, often a raster-scan from top-left to bottom-right; this prohibits multi-task flexibility (inpainting, editing, outpainting) without retraining. Any-order AR models address this […]
PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning
arXiv:2508.09521v2 Announce Type: replace-cross Abstract: Emotional support conversations require more than fluent responses. Supporters need to understand the seeker’s situation and emotions, adopt an appropriate strategy, and respond in a natural, human-like manner. Despite advances in large language models, current systems often lack structured, psychology-informed reasoning. Additionally, it is challenging to enhance these systems through […]
NSTR: Neural Spectral Transport Representation for Space-Varying Frequency Fields
arXiv:2511.18384v2 Announce Type: replace-cross Abstract: Implicit Neural Representations (INRs) have emerged as a powerful paradigm for representing signals such as images, audio, and 3D scenes. However, existing INR frameworks — including MLPs with Fourier features, SIREN, and multiresolution hash grids — implicitly assume a textitglobal and stationary spectral basis. This assumption is fundamentally misaligned with […]