AI.info
Latest Research — Page 98
Browse Latest Research on AI.info.
- A Review: PTSD in Pre-Existing Medical Condition on Social Media
- Manga2Animate: An Agentic Framework for Faithful Manga Animation with Script and Storyboard Planning
- Multi-Scale Local Speculative Decoding for Image Generation
- CADO: From Imitation to Cost Minimization for Heatmap-based Solvers in Combinatorial Optimization
- Power Ensemble Aggregation for Improved Extreme Event AI Prediction
- Approximating Shapley Explanations in Reinforcement Learning
- JMedEthicBench: A Multi-Turn Conversational Benchmark for Evaluating Medical Safety in Japanese Large Language Models
- RARF: Region-Aware Rectified Flows for 3D Brain MRI Inpainting
- DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes
- FactGuard: Event-Centric and Commonsense-Guided Fake News Detection
- MTEdit: Packed Trajectories Beat Rollouts for Multi-Turn Image Editing
- GRAFT-EEG: Gauge-Aware Physical Field Transport for Cross-Dataset Motor-Imagery EEG
- AI Should Facilitate Democratic Deliberation at Scale
- Principia: Relational Physics Tests for Video Models
- Qwen-Image-PE: Learning Visual Design for Text-to-Image Prompt Enhancement
- Low-Rank Ternary Adaptation for Fine-Tuning Transformers
- Distributionally Robust Online Markov Game with Linear Function Approximation
- SimBA: Simplifying Benchmark Analysis Using Performance Matrices Alone
- OAD-Promoter: Enhancing Zero-shot VQA using Large Language Models with Object Attribute Description
- Policy myopia as a mechanism of gradual disempowerment in Post-AGI governance, Circa 2049
- DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity
- Family Matters: A Systematic Study of Spatial vs. Frequency Masking for Continual Test-Time Adaptation
- ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents
- Dynamic Reflections: Probing Video Representations with Text Alignment
- Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience
- CHAMMI-75: Pre-training multi-channel models with heterogeneous microscopy images
- DART-ing Through the Drift: Dynamic Tracing of Knowledge Neurons for Adaptive Inference-Time Pruning
- PixPerfect: Seamless Latent Diffusion Local Editing with Discriminative Pixel-Space Refinement
- COCO-Tree: Compositional Hierarchical Concept Trees for Enhanced Reasoning in Vision Language Models
- Demonstration-Free Robotic Control via LLM Agents
- SPADE: Self-Play in Adaptive Synthetic Executable Environments
- OceanAI: A Conversational Platform for Accurate, Transparent, Near-Real-Time Oceanographic Insights
- MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping
- Reinforced Linear Genetic Programming
- Text-Only Training for Image Captioning with Retrieval Augmentation and Modality Gap Correction
- Recognizing Dialogue Ambiguity via Candidate Set Visual Grounding
- Intent2CAD: How Semantic-Parametric Supervision Shapes Text-to-CAD Generation
- SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration
- Relink: Constructing Query-Driven Evidence Graph On-the-Fly for GraphRAG
- CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems