CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning
arXiv:2512.02551v3 Announce Type: replace-cross Abstract: In this paper, we propose CUDA-L2, a system that combines large language models (LLMs) and…
Technical Report on the CVPR 2026@AdvML Workshop Challenge
arXiv:2607.11560v1 Announce Type: cross Abstract: Vision-language agents (VLAs) are increasingly used to interpret complex driving scenes and support safety-critical reasoning.…
BizFinBench.v2: Towards Reliable LLMs in Finance via Real-User Data and Offline/Online Bilingual Evaluation
arXiv:2601.06401v2 Announce Type: replace Abstract: Large language models are becoming increasingly significant in financial applications. Nevertheless, prevailing benchmarks are largely…
Abstractiveness Metrics for Evaluating Text Summarization: A Refined Formulation with Empirical Validation
arXiv:2607.10806v1 Announce Type: cross Abstract: Quantifying abstractiveness in generated summaries is essential for evaluating summarization models beyond surface-level metrics like…
4DR360: State Reasoning for Joint 3D Detection and Occupancy Prediction in 4D Radar-Camera Full-Scene Perception
arXiv:2607.09629v2 Announce Type: replace-cross Abstract: Reliable autonomous driving requires full-scene perception that couples foreground objects with dense semantic layout. Recently,…
From ML Predictions to Informed Diagnostic Assistance Using the Toulmin Model of Argumentation
arXiv:2607.09664v1 Announce Type: new Abstract: To provide a structured and interpretable assessment, we decompose the image-based diagnosis into components following…
The Ebb and Flow of Multimodal Focus: Scheduling Visual Relay Windows for Grounded VLM Reasoning
arXiv:2607.11436v1 Announce Type: new Abstract: Vision-language models increasingly succeed on multimodal reasoning benchmarks, yet their visual evidence often becomes unstable…
Prompt Compression in Diffusion Large Language Models: Evaluating LLMLingua-2 on LLaDA
arXiv:2605.17932v2 Announce Type: replace-cross Abstract: Prompt compression reduces inference cost and context length in large language models, but prior evaluations…
A Sovereign, Open-Source Foundation Model for German and English
arXiv:2607.09424v2 Announce Type: replace-cross Abstract: We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation model…
Lightning Fast Matching Dependency Discovery with Desbordante
arXiv:2607.10771v1 Announce Type: cross Abstract: Matching dependency is a generalization of the functional dependency concept, which allows users to apply…