arXiv:2603.00492v2 Announce Type: replace-cross Abstract: Per-scene optimization methods such as 3D Gaussian Splatting provide state-of-the-art novel view synthesis quality but extrapolate poorly to under-observed areas. Methods that leverage generative priors to correct artifacts in these areas hold promise but currently suffer from two shortcomings. The first is scalability, as existing methods use image diffusion models […]
The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment
arXiv:2604.06377v3 Announce Type: replace-cross Abstract: We investigate whether post-trained capabilities can be transferred across models without retraining, with a focus on transfer across different model scales. We propose the Master Key Hypothesis, which states that model capabilities correspond to directions in a low-dimensional latent subspace that induce specific behaviors and are transferable across models through […]
Scale-Parameter Selection in Gaussian Kolmogorov-Arnold Networks
arXiv:2604.21174v2 Announce Type: replace-cross Abstract: Kolmogorov–Arnold Networks (KANs) have recently attracted attention as edge-based neural architectures in which learnable univariate functions replace conventional fixed activation functions. A key source of flexibility in KANs is the choice of basis functions used to parameterize the learnable edge functions. In this context, Gaussian basis functions provide a simple […]
Pro$^2$Assist: Continuous Step-Aware Proactive Assistance with Multimodal Egocentric Perception for Long-Horizon Procedural Tasks
arXiv:2605.04227v1 Announce Type: new Abstract: Procedural tasks with multiple ordered steps are ubiquitous in daily life. Recent advances in multimodal large language models (MLLMs) have enabled personal assistants that support daily activities. However, existing systems primarily provide reactive guidance triggered by user queries, or limited proactive assistance for isolated short-term events rather than long-horizon procedural […]
Manifold-Aligned Guided Integrated Gradients for Reliable Feature Attribution
arXiv:2605.02167v2 Announce Type: replace-cross Abstract: Feature attribution is central to diagnosing and trusting deep neural networks, and Integrated Gradients (IG) is widely used due to its axiomatic properties. However, IG can yield unreliable explanations when the integration path between a baseline and the input passes through regions with noisy gradients. While Guided Integrated Gradients reduces […]
Noise-Accelerated Kramers Escape and Coherence Resonance in a 5D Neural Manifold
arXiv:2605.04088v1 Announce Type: new Abstract: Intrinsic channel noise is fundamental to neural processing, yet its state-dependent nature, when constrained by strict Feller boundary conditions, is often overlooked. Here, we demonstrate that this bounded multiplicative noise is not merely a source of jitter but an active dynamical force that fundamentally reshapes neural excitability. Investigating a 5D […]
Architectural Constraints Alignment in AI-assisted, Platform-based Service Development
arXiv:2605.04973v1 Announce Type: cross Abstract: AI-assisted development tools enable rapid prototyping of services but often lack awareness of architectural constraints, infrastructure dependencies, and organizational standards required in production environments. Consequently, generated artifacts may exhibit brittle behavior and limited deployability. We propose a retrieval-augmented scaffolding approach that combines platform-based code generation with agentic clarification loops to […]
Temporal Reasoning Is Not the Bottleneck: A Probabilistic Inconsistency Framework for Neuro-Symbolic QA
arXiv:2605.04243v1 Announce Type: new Abstract: Despite significant advances, large language models (LLMs) continue to exhibit brittle performance on complex temporal reasoning tasks. This failure mode is widely attributed to inherent deficits in autoregressive logical deduction. In this paper, we challenge this prevailing narrative, demonstrating that temporal reasoning is not the fundamental bottleneck; rather, the locus […]
SoK: Robustness in Large Language Models against Jailbreak Attacks
arXiv:2605.05058v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved remarkable success but remain highly susceptible to jailbreak attacks, in which adversarial prompts coerce models into generating harmful, unethical, or policy-violating outputs. Such attacks pose real-world risks, eroding safety, trust, and regulatory compliance in high-stakes applications. Although a variety of attack and defense methods […]
ROZA Graphs: Self-Improving Near-Deterministic RAG through Evidence-Centric Feedback
arXiv:2604.07595v3 Announce Type: replace Abstract: Language model agents reason from scratch on every query, discarding their chain of thought after each run. The result is lower accuracy and high run-to-run variance. We introduce reasoning graphs, which persist the per-evidence chain of thought as structured edges. Unlike prior memory that retrieves distilled strategies by query similarity, […]
Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims
arXiv:2605.02740v2 Announce Type: replace Abstract: Evidence derived from large-scale real-world data (RWD) is increasingly informing regulatory evaluation and healthcare decision-making. Administrative claims provide population-scale, longitudinal records of healthcare utilization, expenditure, and detailed coding of diagnoses, procedures, and medications, yet their potential as a substrate for healthcare foundation models remains largely unexplored. Here we present ReClaim, […]
Aes3D: Aesthetic Assessment in 3D Gaussian Splatting
arXiv:2605.05155v1 Announce Type: cross Abstract: As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important in helping creators build more visually compelling 3D content. However, existing evaluation methods for 3D scenes primarily emphasize reconstruction fidelity and perceptual realism, largely overlooking higher-level aesthetic attributes […]