Artificial Intelligence

From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models ACL 2026 From Logical to Computational Sparsity: Structure-Aware Block-Sparse Attention for Long-Code Completion ACL 2026 From log 𝜋 to 𝜋: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight ACL 2026 From Manuals to Actions: A Unified VLA Model for Chain-of-Thought Manual Generation and Robotic Manipulation CVPR 2026 From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling AAAI 2026 From Measurement to Mitigation: Quantifying and Reducing Identity Leakage in Image Representation Encoders with Linear Subspace Removal CVPR 2026 From Moves to Paths: A Hierarchical Framework for Trajectory Representation Learning UAI 2026 From Narrow Unlearning to Emergent Misalignment in LLMs ACL 2026 From Naturalness to Norms: Interactional Cultural Competence for SpeechLMs ACL 2026 From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context ACL 2026 From Numbers to Narratives: Efficient Language Model-Based Detection for Safety-Critical Minority Classes EACL 2026 From Observation to Action: Latent Action-based Primitive Segmentation for VLA Pre-training in Industrial Settings CVPR 2026 From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation ACL 2026 From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection CVPR 2026 From Panel to Pixel: Zoom-In Vision-Language Pretraining from Biomedical Scientific Literature CVPR 2026 From Paper to Structured JSON: An Agentic AI Workflow for Compliant BMR Digital Transformation EACL 2026 From Pixels to Histopathology: A Graph-Based Framework for Interpretable Whole Slide Image Analysis MIDL 2026 From Pixels to Logic: A Perception-Reasoning Decomposition Framework for Open-World Referring Expression Comprehension AAAI 2026 From Pixels to Policies: Reinforcing Spatial Reasoning in Language Models for Content-Aware Layout Design ACL 2026 From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge AAAI 2026 From Prompt to Production: Automating Brand-Safe Marketing Imagery with Text-to-Image Models WACV 2026 From Proof to Program: Characterizing Tool-Induced Reasoning Hallucinations in Large Language Models ACL 2026 From Query to Counsel: Structured Reasoning with a Multi-Agent Framework and Dataset for Legal Consultation ACL 2026 From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding ACL 2026 From Regulatory Approvals to Patents: Cross-Domain Linking for Cardiovascular Device Traceability ACL 2026