arXiv Computer Science @arxiv_cs@qoto.org

Small Edits, Big Consequences: Telling Good from Bad Robustness in Large Language Models https://arxiv.org/abs/2507.15868 #cs.CL #cs.AI

An open dataset of neural networks for hypernetwork research https://arxiv.org/abs/2507.15869 #cs.LG

SpeedLLM: An FPGA Co-design of Large Language Model Inference Accelerator https://arxiv.org/abs/2507.14139 #cs.AR

The Free Will Equation: Quantum Field Analogies for AGI https://arxiv.org/abs/2507.14154 #cs.AI #cs.LG

Catalyst: a Novel Regularizer for Structured Pruning with Auxiliary Extension of Parameter Space https://arxiv.org/abs/2507.14170 #cs.LG #cs.AI

IPPRO: Importance-based Pruning with PRojective Offset for Magnitude-indifferent Structural Pruning https://arxiv.org/abs/2507.14171 #cs.LG #cs.AI

Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI https://arxiv.org/abs/2507.14172 #cs.LG #cs.AI #cs.NE

Latent Space Data Fusion Outperforms Early Fusion in Multimodal Mental Health Digital Phenotyping Data https://arxiv.org/abs/2507.14175 #stat.AP #cs.LG #cs.AI

Predictive Representativity: Uncovering Racial Bias in AI-based Skin Cancer Detection https://arxiv.org/abs/2507.14176 #stat.CO #stat.ML #cs.LG

Understanding Two-Layer Neural Networks with Smooth Activation Functions https://arxiv.org/abs/2507.14177 #math.NA #cs.LG #cs.AI #cs.NA

Feature Bank Enhancement for Distance-based Out-of-Distribution Detection https://arxiv.org/abs/2507.14178 #cs.LG #cs.AI

A Sparsity Predicting Approach for Large Language Models via Activation Pattern Clustering https://arxiv.org/abs/2507.14179 #cs.LG #cs.AI #cs.CL #cs.DC

Open-Vocabulary Object Detection in UAV Imagery: A Review and Future Perspectives https://arxiv.org/abs/2507.13359 #cs.CV

Low-Light Enhancement via Encoder-Decoder Network with Illumination Guidance https://arxiv.org/abs/2507.13360 #cs.CV

VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs https://arxiv.org/abs/2507.13361 #cs.CV #cs.AI

Enhancing Spatial Reasoning in Vision-Language Models via Chain-of-Thought Prompting and Reinforcement Learning https://arxiv.org/abs/2507.13362 #cs.CV #cs.AI #cs.CL

Just Add Geometry: Gradient-Free Open-Vocabulary 3D Detection Without Human-in-the-Loop https://arxiv.org/abs/2507.13363 #cs.CV #cs.AI

OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning https://arxiv.org/abs/2507.13364 #cs.CV #cs.AI

Leveraging the Spatial Hierarchy: Coarse-to-fine Trajectory Generation via Cascaded Hybrid Diffusion https://arxiv.org/abs/2507.13366 #cs.SI #cs.CV

Digital Twins in Industrial Applications: Concepts, Mathematical Modeling, and Use Cases https://arxiv.org/abs/2507.12468 #cs.OH