arXiv:2603.17538v1 Announce Type: cross Abstract: A symmetry on rigid motion is one of the salient factors in efficient learning of 3D point cloud problems. Group convolution has been a representative method to extract equivariant features, but its realizations have struggled to retain both rigorous symmetry and scalability simultaneously. We advocate utilizing the intertwiner framework to […]
Stepwise Think-Critique: A Unified Framework for Robust and Interpretable LLM Reasoning
arXiv:2512.15662v3 Announce Type: replace Abstract: Human beings solve complex problems through critical thinking, where reasoning and evaluation are intertwined to converge toward correct solutions. However, most existing large language models (LLMs) treat the reasoning and verification as separate processes: they either generate reasoning without explicit self-checking or rely on external verifiers to detect errors post […]
Chain of Mindset: Reasoning with Adaptive Cognitive Modes
arXiv:2602.10063v2 Announce Type: replace Abstract: Human problem-solving is never the repetition of a single mindset, by which we mean a distinct mode of cognitive processing. When tackling a specific task, we do not rely on a single mindset; instead, we integrate multiple mindsets within the single solution process. However, existing LLM reasoning methods fall into […]
I Know What I Don’t Know: Latent Posterior Factor Models for Multi-Evidence Probabilistic Reasoning
arXiv:2603.15670v2 Announce Type: replace Abstract: Real-world decision-making, from tax compliance assessment to medical diagnosis, requires aggregating multiple noisy and potentially contradictory evidence sources. Existing approaches either lack explicit uncertainty quantification (neural aggregation methods) or rely on manually engineered discrete predicates (probabilistic logic frameworks), limiting scalability to unstructured data. We introduce Latent Posterior Factors (LPF), a […]
Physics-Informed Evolution: An Evolutionary Framework for Solving Quantum Control Problems Involving the Schr”odinger Equation
arXiv:2502.05228v2 Announce Type: replace-cross Abstract: Physics-Informed Neural Networks (PINNs) have demonstrated that embedding physical laws directly into the learning objective can significantly enhance the efficiency and physical consistency of neural network solutions. Inspired by this principle, we ask a natural question: can physical information be similarly embedded into the fitness function of evolutionary algorithms? In […]
Efficient Diffusion as Low Light Enhancer
arXiv:2410.12346v3 Announce Type: replace-cross Abstract: The computational burden of the iterative sampling process remains a major challenge in diffusion-based Low-Light Image Enhancement (LLIE). Current acceleration methods, whether training-based or training-free, often lead to significant performance degradation, highlighting the trade-off between performance and efficiency. In this paper, we identify two primary factors contributing to performance degradation: […]
Mitigating LLM Hallucinations through Domain-Grounded Tiered Retrieval
arXiv:2603.17872v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved unprecedented fluency but remain susceptible to “hallucinations” – the generation of factually incorrect or ungrounded content. This limitation is particularly critical in high-stakes domains where reliability is paramount. We propose a domain-grounded tiered retrieval and verification architecture designed to systematically intercept factual inaccuracies by […]
Learning Over Dirty Data with Minimal Repairs
arXiv:2503.13921v2 Announce Type: replace-cross Abstract: Missing data often exists in real-world datasets, requiring significant time and effort for data repair to learn accurate models. In this paper, we show that imputing all missing values is not always necessary to achieve an accurate ML model. We introduce concepts of minimal and almost minimal repair, which are […]
Low-dimensional model for adaptive networks of spiking neurons
arXiv:2410.03657v3 Announce Type: replace Abstract: We investigate a large ensemble of Quadratic Integrate-and-Fire (QIF) neurons with heterogeneous input currents and adaptation variables. Our analysis reveals that for a specific class of adaptation, termed quadratic spike-frequency adaptation (QSFA), the high-dimensional system can be exactly reduced to a low-dimensional system of ordinary differential equations, which describes the […]
RAGXplain: From Explainable Evaluation to Actionable Guidance of RAG Pipelines
arXiv:2505.13538v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) systems couple large language models with external knowledge, yet most evaluation methods report aggregate scores that reveal whether a pipeline underperforms but not where or why. We introduce RAGXplain, an evaluation framework that translates performance metrics into actionable guidance. RAGXplain structures evaluation around a ‘Metric Diamond’ connecting […]
Spatial Transcriptomics as Images for Large-Scale Pretraining
arXiv:2603.13432v2 Announce Type: replace-cross Abstract: Spatial Transcriptomics (ST) profiles thousands of gene expression values at discrete spots with precise coordinates on tissue sections, preserving spatial context essential for clinical and pathological studies. With rising sequencing throughput and advancing platforms, the expanding data volumes motivate large-scale ST pretraining. However, the fundamental unit for pretraining, i.e., what […]
ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs
arXiv:2507.10593v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) applications are increasingly relying on external tools to extend their capabilities beyond text generation. However, current tool integration approaches suffer from fragmentation, protocol limitations, and implementation complexity, leading to substantial development overhead. This paper presents ToolRegistry, a protocol-agnostic tool management system that has evolved from a […]