AI.info

Latest Research — Page 88

Browse Latest Research on AI.info.

• Approximation Algorithm for Constrained $k$-Center Clustering: A Local Search Approach
• PPTArena: A Benchmark for PowerPoint Editing
• The Minimax Lower Bound of Kernel Stein Discrepancy Estimation
• Fast PINN Eigensolvers via Biconvex Reformulation
• BCWildfire: A Long-term Multi-factor Dataset and Deep Learning Benchmark for Boreal Wildfire Risk Prediction
• Opinion: Towards Unified Expressive Policy Optimization for Robust Robot Learning
• Visuomotor Robotic Pruning in Planar Orchards Using Hybrid Reinforcement Learning
• Geometric-Photometric Event-based 3D Gaussian Ray Tracing
• When Models Defer to Wrong Answers: A Robustness Audit of Source-Attributed Cues in Multiple-Choice QA
• The Signal Rail: A Deterministic Motion Grammar for Communicating Conversational Agent State in Terminal Interfaces
• UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions
• Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning
• FOM-Nav: Frontier-Object Maps for Object Goal Navigation
• Mask-Aware Policy Gradients for Diffusion Language Models
• ShapeR: Robust Conditional 3D Shape Generation from Casual Captures
• SimScale: Learning to Drive via Real-World Simulation at Scale
• Embedding Compression via Spherical Coordinates
• Decoding Listeners Identity: Person Identification from EEG Signals Using a Lightweight Spiking Transformer
• Inference-Time Scaling of Diffusion Models for Infrared Data Generation
• LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training
• Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness
• R-AVST: Empowering Video-LLMs with Fine-Grained Spatio-Temporal Reasoning in Complex Audio-Visual Scenarios
• SANet: A Semantic-aware Agentic AI Networking Framework for Cross-layer Optimization in 6G
• Reinforcement Learning with Stochastic Reward Machines
• Toward Automatic Filling of Case Report Forms: A Case Study on Data from an Italian Emergency Department
• Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes
• Improving 2D Diffusion Models for 3D Medical Imaging with Inter-Slice Consistent Stochasticity
• M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation
• From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?
• Contamination Detection for VLMs using Multi-Modal Semantic Perturbation
• PRISM: Powerful Time Series to Image (TS2I) Representations for Multivariate Anomaly Detection
• LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?
• Astronex-World 1.0: Real-Time Interactive World Model Foundation
• How AI Models Manage Epistemic Authority: A Taxonomy and Comparative Analysis of Responses to User Disagreement
• UrbanNav: Learning Language-Guided Urban Navigation from Web-Scale Human Trajectories
• PanoNav: Mapless Zero-Shot Object Navigation with Panoramic Scene Parsing and Dynamic Memory
• Readability $\ne$ Learnability: Rethinking the Role of Simplicity in Training Small Language Models
• Chopthin-Consensus Power Sampling: A Diversity-Preserving Approach to LLM Decoding
• Be Wary of Your Time Series Preprocessing
• GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors