arXiv Computer Science @arxiv_cs@qoto.org

The Biggest Risk of Embodied AI is Governance Lag https://arxiv.org/abs/2604.21938 #cs.CY #cs.AI

When Altruism Meets Autonomy: Managing Bottleneck Congestion with Strategic Autonomous Vehicles https://arxiv.org/abs/2604.21941 #eess.SY #cs.GT #cs.SY

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation https://arxiv.org/abs/2604.21950 #cs.SE #cs.AI #cs.LG

Focus Session: Hardware and Software Techniques for Accelerating Multimodal Foundation Models https://arxiv.org/abs/2604.21952 #cs.LG #cs.AI #cs.AR #cs.NE #cs.RO

The Tool-Overuse Illusion: Why Does LLM Prefer External Tools over Internal Knowledge? https://arxiv.org/abs/2604.19749 #cs.AI #cs.SE

Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging https://arxiv.org/abs/2604.19750 #cs.SE #cs.AI #cs.HC

AI to Learn 2.0: A Deliverable-Oriented Governance Framework and Maturity Rubric for Opaque AI in Learning-Intensive Domains https://arxiv.org/abs/2604.19751 #cs.AI #cs.CY

Soft-Label Governance for Distributional Safety in Multi-Agent Systems https://arxiv.org/abs/2604.19752 #cs.MA #cs.AI #cs.CY

Algorithm Selection with Zero Domain Knowledge via Text Embeddings https://arxiv.org/abs/2604.19753 #cs.AI #cs.CL #cs.LG

Exploring Data Augmentation and Resampling Strategies for Transformer-Based Models to Address Class Imbalance in AI Scoring of Scientific Explanations in NGSS Classroom https://arxiv.org/abs/2604.19754 #cs.AI #cs.LG

Explainable AML Triage with LLMs: Evidence Retrieval and Counterfactual Checks https://arxiv.org/abs/2604.19755 #cs.AI #cs.LG

WorkflowGen:an adaptive workflow generation mechanism driven by trajectory experience https://arxiv.org/abs/2604.19756 #cs.LG #cs.AI

Transparent Screening for LLM Inference and Training Impacts https://arxiv.org/abs/2604.19757 #cs.LG #cs.AI #cs.CL

ThermoQA: A Three-Tier Benchmark for Evaluating Thermodynamic Reasoning in Large Language Models https://arxiv.org/abs/2604.19758 #cs.AI #cs.CL #cs.LG

SPRITE: From Static Mockups to Engine-Ready Game UI https://arxiv.org/abs/2604.18591 #cs.HC #cs.AI

Two-dimensional early exit optimisation of LLM inference https://arxiv.org/abs/2604.18592 #cs.CL #cs.AI

HELIX: Verified compilation of cyber-physical control systems to LLVM IR https://arxiv.org/abs/2604.18593 #cs.PL

Fundamental for Delay and Reliability Guarantees for Emergency UAV https://arxiv.org/abs/2604.18595 #math.IT #cs.IT

TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution https://arxiv.org/abs/2604.18607 #cs.NE #cs.AI

GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning https://arxiv.org/abs/2604.16871 #cs.AI #cs.LG