AI.info

Latest Research — Page 21

Browse Latest Research on AI.info.

• Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers
• Competence-Gated Pooling of Language Models and Priors for Event Forecasting
• EasyPPO: Stabilizing the Critic Is Key
• TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows
• DyPSI: Dynamic Physics Sensing via Joint Field and Sensor-Trajectory Generation
• CLARA: Can AI Assess Developmental Appropriateness in Children's Stories?
• To Align or Not to Align: Strategic Multimodal Representation Alignment for Optimal Performance
• Probabilistic Textual Time Series Depression Detection
• Statistical benchmarking of transformer models in low signal-to-noise time-series forecasting
• MIMM-X: Disentangling Spurious Correlations for Medical Image Analysis
• Empathy Applicability Modeling for General Health Queries
• On the Clock: Towards Punctual and Productive Time-Budgeted AI Agents
• RoboDriveVLM: A Novel Benchmark and Baseline towards Robust Vision-Language Models for Autonomous Driving
• Ref-SAM3D: Bridging SAM3D with Text for Reference 3D Reconstruction
• Selective Rotary Position Embedding
• RoboCloth: A Large-Scale Real Cloth Material Dataset for Neural Reflectance Reconstruction
• Conviction Without Evidence: Verdict Stability Is Independent of Visual Grounding in Medical Vision--Language Models
• Dynamic Policy Learning for Legged Robot with Simplified Model Pretraining and Model-Homotopy-Inspired Transfer
• Are LLMs Good Financial User Simulators? A Preliminary Study
• SmartSplat: Feature-Smart Gaussians for Scalable Compression of Ultra-High-Resolution Images
• CUCo: An Agentic Framework for Compute and Communication Co-design
• Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface
• Detecting Experiential Intertextuality Across Migration Routes: Beyond Surface Similarity in French Narratives
• ImagebindDC: Compressing Multi-modal Data with Imagebind-based Condensation
• Skin-R1: Clinical Knowledge-Guided Dermatological Diagnosis Using Vision-Language Models
• Can LLMs Compress (and Decompress)? Evaluating Code Understanding and Execution via Invertibility
• A Few Bad Neurons: Isolating and Surgically Correcting Sycophancy
• CRAB: Cuboid-based Representation for As-built BIM from Point Clouds
• The Observer-Situation Lattice: A Unified Formal Basis for Perspective-Aware Cognition
• Diffusion differentiable resampling
• Unlocking Noisy Real-World Corpora for Foundation Model Pre-Training via Quality-Aware Tokenization
• HappyWorld-Bench
• Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach
• Sparser Block-Sparse Attention via Token Permutation
• SteerEval: Inference-time Interventions Strengthen Multilingual Generalization in Neural Summarization Metrics
• Generalist Foundation Models Are Not Clinical Enough for Hospital Operations
• The Open Ant: A Robot Platform for Reinforcement Learning Research
• Parts-of-Speech as Emergent Categories in SAE Latent Space
• PathMind: A Retrieve-Prioritize-Reason Framework for Knowledge Graph Reasoning with Large Language Models
• HEIR: Learning Graph-Based Motion Hierarchies