arXiv:2607.00196v1 Announce Type: new Abstract: Many scientific systems exhibit uncertainty from stochastic forcing, unresolved degrees of freedom, or imperfect observations, making reliable surrogate forecasting fundamentally distributional…
arXiv:2510.06995v2 Announce Type: replace Abstract: We study the propagation of outliers in cyclic causal graphs with linear structural equations, tracing them back to one or several…
arXiv:2607.00479v1 Announce Type: cross Abstract: Transformer-based large models have demonstrated remarkable generalization abilities across different tasks by leveraging a context-aware attention module for in-context learning. With…
arXiv:2607.00233v1 Announce Type: new Abstract: How do two agents invent a shared language from scratch? In a Lewis signaling game, a sender and receiver must coordinate…
arXiv:2607.00297v1 Announce Type: cross Abstract: When LLM agents use evaluator feedback to adapt their behavior in closed loops, evaluator biases propagate through the agent's strategy distribution…
arXiv:2607.00339v1 Announce Type: new Abstract: Conversational data is increasingly used as a persistent source of user state for long-running assistants and AI agents. However, querying this…
arXiv:2607.00060v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) show strong promise for clinical VQA and radiology report generation, yet inference-time hallucinations still undermine trustworthy…
arXiv:2604.14262v2 Announce Type: replace Abstract: GUI grounding models report over 85% accuracy on standard benchmarks, yet drop 27-56 percentage points when instructions require spatial reasoning rather…
arXiv:2602.23164v2 Announce Type: replace Abstract: Foundation models must handle multiple generative processes, yet mechanistic interpretability largely studies capabilities in isolation; it remains unclear how a single…
arXiv:2607.00149v1 Announce Type: cross Abstract: We study uniform-in-time propagation-of-chaos for continuous-time Stein Variational Gradient Descent (SVGD). Classical finite-time propagation-of-chaos estimates for mean-field systems typically deteriorate rapidly…
arXiv:2512.24152v2 Announce Type: replace-cross Abstract: Sampling based on score diffusions has led to striking empirical results, and has attracted considerable attention from various research communities. It…
arXiv:2605.26542v4 Announce Type: replace-cross Abstract: Tool-using agents increasingly operate in open-ended deployment environments, where they compose file systems, web APIs, code interpreters, and enterprise services at…
arXiv:2607.00465v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) rely extensively on Visual Instruction Tuning (VIT) to elicit their multimodal reasoning capabilities. However, we find a…
arXiv:2503.13445v3 Announce Type: replace Abstract: When asked to explain their decisions, LLMs can often give explanations which sound plausible to humans. But are these explanations faithful,…
arXiv:2606.29963v2 Announce Type: replace Abstract: The structural vulnerabilities of point cloud-based 3D object detectors remain poorly understood. Prior work has studied adversarial robustness primarily on isolated…
arXiv:2606.31043v2 Announce Type: replace Abstract: Residual reinforcement learning adapts a pretrained robot policy by learning an additive correction to its actions. While effective when adaptation amounts…
arXiv:2607.00197v1 Announce Type: new Abstract: Long-horizon multivariate time series forecasting (LTSF) remains challenging due to non-stationarity, regime shifts, and error accumulation. The Variability-Aware Recursive Neural Network…
arXiv:2607.01057v1 Announce Type: new Abstract: We study a broad class of graphical models whose independencies correspond to vertex separation in mixed graphs with directed, undirected, and…
arXiv:2507.02961v2 Announce Type: replace-cross Abstract: Modern transportation network modeling increasingly involves the integration of diverse methodologies including sensor-based forecasting, reinforcement learning, classical flow optimization, and demand…
arXiv:2607.00248v1 Announce Type: new Abstract: We present Seed2.0, a model series that takes a meaningful step toward solving complex, real-world tasks. Our approach begins with identifying…
arXiv:2607.00171v1 Announce Type: new Abstract: Text embeddings are standard for semantic similarity tasks, yet their evaluation remains an open challenge. Current benchmarks are static, cover only…
arXiv:2607.00341v1 Announce Type: new Abstract: Large language models achieve strong performance on many reasoning tasks when allowed to externalize intermediate steps as Chain-of-Thought (CoT). However, many…
arXiv:2607.00138v1 Announce Type: new Abstract: MG-SpaIR is a training-data-free framework for restoring a clean image from a single observation corrupted by a mixture of blur, downsampling,…
arXiv:2607.01223v1 Announce Type: cross Abstract: When should an AI system's answer be trusted? Formal proof assistants offer certainty but cannot reach most of the problem distribution;…