AI.info

Latest Research — Page 91

Browse Latest Research on AI.info.

• PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation
• Contractive Diffusion Policies: Robust Action Diffusion via Contractive Score-Based Sampling with Differential Equations
• Bridging Vision and Language for Robust Context-Aware Surgical Point Tracking: The VL-SurgPT Dataset and Benchmark
• Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset
• Who Gets Heard? Rethinking Fairness in AI for Music Systems
• From Black-box to Causal-box: Towards Building More Interpretable Models
• Fixed Anchors Are Not Enough: Dynamic Retrieval and Persistent Homology for Dataset Distillation
• Learning with Preserving for Continual Multitask Learning
• Beyond Fluency: A Clinical Benchmark and Anomaly-Enhanced Baseline for Spine MRI Report Generation
• LeCoT: revisiting network architecture for two-view correspondence pruning
• ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs
• Leveraging 2D Priors and SDF Guidance for Dynamic Urban Scene Rendering
• AMVICC: A Novel Benchmark for Cross-Modal Failure Mode Profiling for VLMs and IGMs
• AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs
• Same Words, Different Judgments: Modality Effects on Preference Alignment
• CQD-SHAP: Explainable Complex Query Answering via Shapley Values
• 10 Open Challenges Steering the Future of Vision-Language-Action Models
• Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systems
• Multi-Agent Pose Uncertainty: A Differentiable Rendering Cramér-Rao Bound
• Sequential Group Composition: A Window into the Mechanics of Deep Learning
• HairWeaver: Few-Shot Photorealistic Hair Motion Synthesis with Sim-to-Real Guided Video Diffusion
• Disentangling Representation Evolution in Transformers through Directional Decomposition
• Implementation of a Metacognition Framework for Self-Awareness and Self-Regulation in Ensembles of LLMs
• OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models
• 3DID: Direct 3D Inverse Design for Aerodynamics with Physics-Aware Optimization
• The Forecast After the Forecast: A Post-Processing Shift in Time Series
• Clustered Error Correction with Grouped 4D Gaussian Splatting
• Chain of Execution Supervision Promotes General Reasoning in Large Language Models
• Performative Learning Theory
• Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
• Action-guided generation of 3D functionality segmentation data
• STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling Models
• AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite
• Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning
• PFAvatar: Pose-Fusion 3D Personalized Avatar Reconstruction from Real-World Outfit-of-the-Day Photos
• RSOD: Reliability-Guided Sonar Image Object Detection with Extremely Limited Labels
• SPACeR: Self-Play Anchoring with Centralized Reference Models
• Probably Approximately Global Robustness Certification
• LeLaR: The First In-Orbit Demonstration of an AI-Based Satellite Attitude Controller
• Boosting Monocular Metric Depth Estimation via Bokeh Rendering