Skip to content

Papers 5478 stories

arXiv cs.CV Papers

MRD: Using Physically Based Differentiable Rendering to Probe Vision Models for 3D Scene Understanding

arXiv:2512.12307v5 Announce Type: replace Abstract: While deep learning methods have achieved impressive success in many vision benchmarks, it remains difficult to understand and explain the representations…

arXiv cs.LG Papers

SDO: Structure-Aware Data Organization for Efficient LLM Post-Training

arXiv:2607.27273v1 Announce Type: new Abstract: Post-training of large language models is expensive, and existing efficiency improvements mainly focus on selecting informative samples or designing training schedules.…

arXiv stat.ML Papers

Rao-Blackwellized Score Matching on Manifolds

arXiv:2605.25567v3 Announce Type: replace Abstract: We study denoising score matching (DSM) when data are drawn from an embedded manifold $M subset mathbb{R}^D$. We show that under…

arXiv stat.ML Papers

MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian

arXiv:2209.00546v5 Announce Type: replace Abstract: Signed and directed networks are ubiquitous in real-world applications. However, there has been relatively little work proposing spectral graph neural networks…

arXiv cs.AI Papers

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation

arXiv:2510.00192v3 Announce Type: replace-cross Abstract: Low-rank adaptation (LoRA) has become a widely used paradigm for parameter-efficient fine-tuning of large language models, yet its representational capacity often…

arXiv cs.AI Papers

MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoning

arXiv:2607.26465v1 Announce Type: new Abstract: Multimodal Large Language Models have sparked significant interest due to their potential for social intelligence; however, their ability to perform sequential…

arXiv cs.CL Papers

LayerRAG-Bench: A Cross-Layer Reliability Benchmark for Agentic Retrieval-Augmented Generation

arXiv:2607.27353v1 Announce Type: new Abstract: Agentic retrieval-augmented generation systems can produce answers that appear grounded while failing at the evidence, tool-contract, authorization, or session-state layer. We…

arXiv cs.CV Papers

Towards Unified Multimodal Misinformation Detection in Social Media: A Benchmark Dataset and Baseline

arXiv:2509.25991v3 Announce Type: replace-cross Abstract: Detecting deceptive multimodal content on social media has become an increasingly important problem. Two major types of deception dominate: human-crafted misinformation…

arXiv cs.CV Papers

Inference-Time Agentic Decision Rules Beat Longer Evolving Search for Multi-Image Medical Reasoning

arXiv:2607.27564v1 Announce Type: new Abstract: Multi-image medical VQA is not merely a prompt-length problem; it is a fundamental challenge of agentic decision-making. Medical vision-language agents must…

arXiv cs.LG Papers

Beyond KV Reconstruction: Functional Reconstruction for MLA Draft Models in Speculative Decoding

arXiv:2607.27269v1 Announce Type: new Abstract: Multi-head latent attention (MLA) is increasingly important for long-context LLM inference because compact latent states replace the growing key-value (KV) cache…

arXiv stat.ML Papers

Prior laundering: learned priors with inherited, undetectable overconfidence

arXiv:2607.21721v2 Announce Type: replace Abstract: Learned generative priors now supply the regularization in ill-posed imaging inverse problems, and the uncertainty read from their posterior samples is…

arXiv stat.ML Papers

Re-examining Granger Causality with Causal Bayesian Networks and Reichenbachs Principles

arXiv:2501.02672v4 Announce Type: replace Abstract: Granger causality (GC) is widely used to infer directed relationships in time-series data. However, its predictive criterion does not by itself…

arXiv cs.AI Papers

Adaptively Robust LLM Monitoring via Activation Watermarking

arXiv:2603.23171v3 Announce Type: replace-cross Abstract: Providers monitor deployed large language models (LLMs) to detect misuse that they cannot prevent. LLM monitoring is deterministic and often openly…

arXiv cs.AI Papers

On the Hybrid Nature of ABPMS Process Frames and its Implications on Automated Process Discovery

arXiv:2604.22455v2 Announce Type: replace Abstract: A core component of any AI-Augmented Business Process Management System (ABPMS) is the process frame, which gives the system process-awareness and…

arXiv cs.CL Papers

Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups

arXiv:2607.27232v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly shaping how we consume information and form our worldview. This raises concerns beyond bias in…

arXiv cs.CV Papers

Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers

arXiv:2607.28611v1 Announce Type: new Abstract: Visual generation increasingly requires high-resolution images, long videos, and multimodal context, making the quadratic cost of full attention prohibitive. We introduce…

arXiv cs.CV Papers

BeCARE: Budgeted Cache Refresh for Diffusion Transformer Acceleration

arXiv:2605.27075v2 Announce Type: replace Abstract: Training-free feature caching accelerates diffusion transformer (DiT) inference by reusing or forecasting intermediate features. However, fixed schedules make compute predictable but…

arXiv cs.LG Papers

PlatformBid: An Auto-Bidding Benchmark from a Unified Advertising Platform's Perspective

arXiv:2607.27265v1 Announce Type: new Abstract: Real-time bidding is central to computational advertising, comprising three elements: Supply Side Platform (SSP) selling ad impressions, Demand Side Platform (DSP)…

arXiv stat.ML Papers

Learning to Detect Cyber Attacks: Neural Anomaly Detection for Cybersecurity with Theoretical Insights

arXiv:2409.08521v2 Announce Type: replace Abstract: In cybersecurity practice, new forms of cyberattacks continuously emerge, deliberately designed to evade defense systems that rely on previously observed behaviors.…

arXiv stat.ML Papers

Adaptive Nystr"om for Gaussian Process Regression

arXiv:2607.27427v1 Announce Type: cross Abstract: Gaussian Process Regression (GPR) is a robust framework for uncertainty quantification, yet its $O(n^3)$ complexity limits its scalability. Low-rank Nystr"om approximations…

arXiv cs.AI Papers

Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales

arXiv:2607.25364v2 Announce Type: replace Abstract: Tool-using agents expose structured calls but commonly attach free-form rationales. Such rationales are neither authorization nor reliable introspection. We present Explanation-Bound…

arXiv cs.AI Papers

Beyond Block Boundaries: Multi-Block Editing for Diffusion Large Language Models

arXiv:2607.22663v2 Announce Type: replace Abstract: Block diffusion is the dominant approach for scaling discrete diffusion language models (dLLMs), as fixed-size blocks preserve parallel decoding while keeping…

arXiv cs.CL Papers

MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language Models

arXiv:2502.20780v2 Announce Type: replace-cross Abstract: The increasing use of vision-language models (VLMs) in healthcare applications presents great challenges related to hallucinations, in which the models may…

arXiv cs.CV Papers

Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models

arXiv:2604.08881v2 Announce Type: replace Abstract: With the widespread deployment of vision-language large models (VLLMs), their safety alignment faces dual challenges across languages and modalities. Existing methods…