AI.info

Latest Research — Page 128

Browse Latest Research on AI.info.

• CleverBirds: A Multiple-Choice Benchmark for Fine-grained Human Knowledge Tracing
• Tri-Bench: Stress-Testing VLM Reliability on Spatial Reasoning under Camera Tilt and Object Interference
• DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
• Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation
• Thermodynamic Limits of Physical Intelligence
• GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation
• GateRA: Token-Aware Modulation for Parameter-Efficient Fine-Tuning
• Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance
• FaST: Efficient and Effective Long-Horizon Forecasting for Large-Scale Spatial-Temporal Graphs via Mixture-of-Experts
• RegionReasoner: Region-Grounded Multi-Round Visual Reasoning
• VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion
• FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning
• Cultural Awareness is Represented but Not Decoded: Tracing Mythological Knowledge across 18 Open-Source LLMs
• Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment
• Identifying the Supply Chain of AI for Trustworthiness and Risk Management in Critical Applications
• LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systems
• LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training
• LSP-DETR: Efficient and Scalable Nuclei Segmentation in Whole-Slide Images
• MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation
• Anka: A Domain-Specific Language for Reliable LLM Code Generation
• Large Multimodal Models as General In-Context Classifiers
• A Pragmatic VLA Foundation Model
• Same Formulas, Different Semantics: Do Language Models Follow Modal Logic Specifications?
• SlidesGen-Bench: Evaluating Slides Generation via Computational and Quantitative Metrics
• DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas
• Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching
• GTR-Bench: Evaluating Geo-Temporal Reasoning in Vision-Language Models
• MedPixel: A Unified Pixel-Language Model for Medical Reasoning and Segmentation
• SPWOOD: Sparse Partial Weakly-Supervised Oriented Object Detection
• Commonality in Few: Few-Shot Multimodal Anomaly Detection via Hypergraph-Enhanced Memory
• P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling
• LoRA on the Go: Instance-level Dynamic LoRA Selection and Merging
• Trust in One Round: Confidence Estimation for Large Language Models via Structural Signals
• Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints
• Designing Incident Reporting Systems for Harms from General-Purpose AI
• Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Search
• WhAM: Towards A Translative Model of Sperm Whale Vocalization
• Predictive Scheduling for Efficient Inference-Time Reasoning in Large Language Models
• Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations
• Membership and Dataset Inference Attacks on Large Audio Generative Models