arXiv Computer Science @arxiv_cs@qoto.org

Socrates or Smartypants: Testing Logic Reasoning Capabilities of Large Language Models with Logic Programming-based Test Oracles https://arxiv.org/abs/2504.12312 #cs.CL

Exploring the Impact of Personality Traits on Conversational Recommender Systems: A Simulation with Large Language Models https://arxiv.org/abs/2504.12313 #cs.CL #cs.HC

How to Detect and Defeat Molecular Mirage: A Metric-Driven Benchmark for Hallucination in LLM-based Molecular Comprehension https://arxiv.org/abs/2504.12314 #cs.CL #cs.AI

Capybara-OMNI: An Efficient Paradigm for Building Omni-Modal Language Models https://arxiv.org/abs/2504.12315 #cs.CL #cs.AI #cs.CV

Data Metabolism: An Efficient Data Design Schema For Vision Language Model https://arxiv.org/abs/2504.12316 #cs.CL #cs.AI #cs.CV

From Conceptual Data Models to Multimodal Representation https://arxiv.org/abs/2504.11459 #cs.AI #cs.CL #cs.IR

Semantic Matters: Multimodal Features for Affective Analysis https://arxiv.org/abs/2504.11460 #cs.CV #cs.AI #cs.CL

MultiCore+TPU Accelerated Multi-Modal TinyML for Livestock Behaviour Recognition https://arxiv.org/abs/2504.11467 #eess.IV #cs.CV

SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models https://arxiv.org/abs/2504.11468 #cs.CL

SO-DETR: Leveraging Dual-Domain Features and Knowledge Distillation for Small Object Detection https://arxiv.org/abs/2504.11470 #cs.CV #cs.AI

High Dynamic Range Modulo Imaging for Robust Object Detection in Autonomous Driving https://arxiv.org/abs/2504.11472 #eess.IV #cs.CV

Visual moral inference and communication https://arxiv.org/abs/2504.11473 #cs.CV #cs.AI

CI-RKM: A Class-Informed Approach to Robust Restricted Kernel Machines https://arxiv.org/abs/2504.11476 #cs.LG

SDIGLM: Leveraging Large Language Models and Multi-Modal Chain of Thought for Structural Damage Identification https://arxiv.org/abs/2504.11477 #cs.CV #cs.AI

Flux Already Knows - Activating Subject-Driven Image Generation without Training https://arxiv.org/abs/2504.11478 #cs.CV #cs.AI

Roamify: Designing and Evaluating an LLM Based Google Chrome Extension for Personalised Itinerary Planning https://arxiv.org/abs/2504.10489 #cs.HC #cs.AI #cs.LG

GPT Meets Graphs and KAN Splines: Testing Novel Frameworks on Multitask Fine-Tuned GPT-2 with LoRA https://arxiv.org/abs/2504.10490 #cs.LG #cs.CL

ArxivBench: Can LLMs Assist Researchers in Conducting Research? https://arxiv.org/abs/2504.10496 #cs.IR #cs.AI #cs.CL #cs.LG

Exploring Generative AI Techniques in Government: A Case Study https://arxiv.org/abs/2504.10497 #eess.SY #cs.IR #cs.AI #cs.HC #cs.MA #cs.SY

CCSK:Cognitive Convection of Self-Knowledge Based Retrieval Augmentation for Large Language Models https://arxiv.org/abs/2504.10498 #cs.IR #cs.AI