arXiv Computer Science @arxiv_cs@qoto.org

MixLM: High-Throughput and Effective LLM Ranking via Text-Embedding Mix-Interaction https://arxiv.org/abs/2512.07846 #cs.IR #cs.AI #cs.CL #cs.LG

CarBench: A Comprehensive Benchmark for Neural Surrogates on High-Fidelity 3D Car Aerodynamics https://arxiv.org/abs/2512.07847 #cs.LG

RaX-Crash: A Resource Efficient and Explainable Small Model Pipeline with an Application to City Scale Injury Severity Prediction https://arxiv.org/abs/2512.07848 #cs.LG

Accelerating Urban Science Research with AI Urban Scientist https://arxiv.org/abs/2512.07849 #cs.CY #cs.CL #cs.MA

SABER: Small Actions, Big Errors - Safeguarding Mutating Steps in LLM Agents https://arxiv.org/abs/2512.07850 #cs.LG #cs.AI

Adaptive Dataset Quantization: A New Direction for Dataset Pruning https://arxiv.org/abs/2512.05987 #cs.CV #cs.AI

VG3T: Visual Geometry Grounded Gaussian Transformer https://arxiv.org/abs/2512.05988 #cs.CV #cs.AI #cs.LG

A self-driving lab for solution-processed electrochromic thin films https://arxiv.org/abs/2512.05989 #cond-mat.mtrl-sci #cs.LG

Memory-Amortized Inference: A Topological Unification of Search, Closure, and Structure https://arxiv.org/abs/2512.05990 #q-bio.NC #cs.LG

EmoDiffTalk:Emotion-aware Diffusion for Editable 3D Gaussian Talking Head https://arxiv.org/abs/2512.05991 #cs.CV

Domain-Specific Foundation Model Improves AI-Based Analysis of Neuropathology https://arxiv.org/abs/2512.05993 #cs.CV #cs.AI

RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering https://arxiv.org/abs/2512.05119 #cs.IR #cs.AI #cs.CL

Discrete Homotopy and Promise Constraint Satisfaction Problem https://arxiv.org/abs/2512.05120 #cs.CC #cs.LO

PESTalk: Speech-Driven 3D Facial Animation with Personalized Emotional Styles https://arxiv.org/abs/2512.05121 #cs.GR #cs.AI

Documenting SME Processes with Conversational AI: From Tacit Knowledge to BPMN https://arxiv.org/abs/2512.05122 #cs.AI

AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidance https://arxiv.org/abs/2512.05131 #cs.CV #cs.AI #cs.RO

Breaking Scale Anchoring: Frequency Representation Learning for Accurate High-Resolution Inference from Low-Resolution Training https://arxiv.org/abs/2512.05132 #cs.CV #cs.AI

Computing differential subresultants with Maple https://arxiv.org/abs/2512.05133 #cs.SC

InvarDiff: Cross-Scale Invariance Caching for Accelerated Diffusion Models https://arxiv.org/abs/2512.05134 #cs.CV #cs.DC #cs.LG

Analysis of Inter-Testamental References Reveal Five Groups of Books in the Christian Bible https://arxiv.org/abs/2512.05135 #cs.DL