AI.info
Latest Research — Page 106
Browse Latest Research on AI.info.
- Auditing Google's AI Overviews and Featured Snippets: A Case Study on Baby Care and Pregnancy
- More Than Irrational: Modeling Belief-Biased Agents
- HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images
- Maximum Likelihood Reinforcement Learning
- LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation
- PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving
- Demeter: A Parametric Model of Crop Plant Morphology from the Real World
- MTBBench: A Multimodal Sequential Clinical Decision-Making Benchmark in Oncology
- SUMMPILOT: Bridging Efficiency and Customization for Interactive Summarization System
- FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain
- MATA: A Trainable Hierarchical Automaton System for Multi-Agent Visual Reasoning
- Posterior Sampling by Combining Diffusion Models with Annealed Langevin Dynamics
- Rig-Aware 3D Reconstruction of Vehicle Undercarriages using Gaussian Splatting
- MixTTE: Multi-Level Mixture-of-Experts for Scalable and Adaptive Travel Time Estimation
- Investigating self-supervised representations for audio-visual deepfake detection
- A Standardized Framework for Machine Learning in Power System Protection
- Towards Syn-to-Real IQA: A Novel Perspective on Reshaping Synthetic Data Distributions
- Spheriverse: 3D Scene Understanding from Spherical Observations in the Wild
- Disco: Densely-overlapping Cell Instance Segmentation via Adjacency-aware Collaborative Coloring
- CORDS: Continuous Representations of Discrete Structures
- From Detection to Diagnosis: Advancing Hallucination Analysis with Automated Data Synthesis
- Simultaneous Speech-to-Speech Translation Without Aligned Data
- Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models
- Motus2: A Self-Evolving General World Model for Dexterous Manipulation
- Alignment Risks from Capability-Seeking RL Training
- SARA: Stress Test Reasoning in Audio Deepfake Detection
- Registration-Free Monitoring of Unstructured Point Cloud Data via Intrinsic Geometrical Properties
- Angular Steering: Behavior Control via Rotation in Activation Space
- PRISM: A 3D Probabilistic Neural Representation for Interpretable Shape Modeling
- Open-Set Domain Adaptation Under Background Distribution Shift: Challenges and A Provably Efficient Solution
- CLewR: Curriculum Learning with Restarts for Machine Translation Preference Learning
- DistillPath: An Efficient 22M Distilled Pathology Encoder Approaching Large Foundation Model Performance
- VitalDiagnosis: AI-Driven Ecosystem for 24/7 Vital Monitoring and Chronic Disease Management
- Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best
- FALCON: Few-step Accurate Likelihoods for Continuous Flows
- Redistribution-based Cost Inference Improves Sparse Safe Offline RL
- HNDiff: Haze-Noise Diffusion for Image Dehazing
- Are Foundation Models Useful for Bankruptcy Prediction?
- Your LLM, Your Style: Behavioral Mode Axes for LLM Behavioral Control
- CVSS-X: A Multilingual Speech-to-Speech Translation Corpus for 28 Languages