AI.info
Latest Research — Page 92
Browse Latest Research on AI.info.
- Where It Moves, It Matters: Referring Surgical Instrument Segmentation via Motion
- Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning
- Separating Constraint Compliance from Semantic Accuracy: A Novel Benchmark for Evaluating Instruction-Following Under Compression
- SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization
- ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge
- BIRD: Bronze Inscription Restoration and Dating
- SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation
- DFlash: Block Diffusion for Flash Speculative Decoding
- Concise Geometric Description as a Bridge: Unleashing the Potential of LLM for Plane Geometry Problem Solving
- Aggregate-then-Calibrate for Human-centered Assessment with Theoretical Guarantees
- UniHOI: Unified Human-Object Interaction Understanding via Unified Token Space
- Data Annotation as Measurement
- Bidirectional Channel-selective Semantic Interaction for Semi-Supervised Medical Segmentation
- SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentation
- Analytic Bijections for Smooth and Interpretable Normalizing Flows
- SDQM: Synthetic Data Quality Metric for Object Detection Dataset Evaluation
- Precipitation nowcasting of satellite data using physically-aligned neural networks
- REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion
- Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse
- GPEvac: GNN-Based PPO for Adaptive Evacuation Routing During Shooting Events
- Accountable and uncertainty-aware evaluation of sensor-based AI under distribution shift: devices, subjects, and nearly three years underground
- WorldWander: Bridging Egocentric and Exocentric Worlds in Video Generation
- QG-CoC: Question-Guided Chain-of-Captions for Large Multimodal Models
- AI Researchers Must Help Lead Arms Control to Mitigate Military AI Risks
- WorldSculpt: Generating Compositional Worlds from Grounded Videos
- Jokes Aside: Measuring the Semantic Distance of Double Meanings
- Sumudu Neural Operator for ODEs and PDEs
- Model to Model: Understanding the Venus Flytrap Snapping Mechanism and Transferring it to a 3D-printed Bistable Soft Robotic Demonstrator
- How Order-Sensitive Are LLMs? OrderProbe for Deterministic Structural Reconstruction
- SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards
- Instruction-Guided Lesion Segmentation for Chest X-rays with Automatically Generated Large-Scale Dataset
- OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
- Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions
- DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving
- A Cognitive Process-Inspired Architecture for Subject-Agnostic Brain Visual Decoding
- VLF-MSC: Vision-Language Feature-Based Multimodal Semantic Communication System
- Scaling, Lock-In, and Proxy Compliance: A Political Economy of Responsible AI
- PACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inference
- HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
- Formal Safety Guarantees for Autonomous Vehicles using Barrier Certificates