AI.info
Latest Research — Page 95
Browse Latest Research on AI.info.
- Twin: Playing an Unknown Game with a Test-Time Digital Twin
- DEER: A Benchmark for Evaluating Deep Research Agents on Expert Report Generation
- How Robust Are Automated Fact-Checking Systems? A Cross-Benchmark Evaluation
- PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
- Real-Time Semantic Segmentation on FPGA for Autonomous Vehicles Using LMIINet with the CGRA4ML Framework
- PC-UNet: An Enforcing Poisson Statistics U-Net for Positron Emission Tomography Denoising
- EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models
- ECO Decoding: Entropy-Based Control for Controllability and Fluency in Controllable Dialogue Generation
- Principled Thoughts for Latent Recursive LLM Systems
- Learning-Augmented Online Bipartite Matching in the Random Arrival Order Model
- EVEREST: An Evidential, Tail-Aware Transformer for Rare-Event Time-Series Forecasting
- ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
- Layer-Wise Modality Decomposition for Interpretable Multimodal Sensor Fusion
- HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery
- Finding NeMO: A Geometry-Aware Representation of Template Views for Few-Shot Perception
- Identifying Slug Formation in Oil Well Pipelines: A Use Case from Industrial Analytics
- LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching
- Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment
- The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check
- SafeMIL: Learning Offline Safe Imitation Policy from Non-Preferred Trajectories
- Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?
- HLA-WM: Hybrid Linear Attention for Long-Horizon Video World Models
- Omni-Decision: Evidence-Ledger Planning for Omni-Modal Agents
- Synthetic Object Compositions for Scalable and Accurate Learning in Detection, Segmentation, and Grounding
- How Far Can Coding Agents Go in Visual Generation?
- Enhancing Multi-Image Understanding through Delimiter Token Scaling
- Neural Diversity Regularizes Hallucinations in Language Models
- Gap-K%: Measuring Top-1 Prediction Gap for Detecting Pretraining Data
- Interpretation as Linear Transformation: A Cognitive-Geometric Model of Concepts and Meaning
- Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
- Foundation Model Driven Optical Flow
- REXO: Indoor Multi-View Radar Object Detection via 3D Bounding Box Diffusion
- Discovering Interpretable Algorithms by Decompiling Transformers to RASP
- A class-driven hierarchical ResNet for classification of multispectral remote sensing images
- SpecAttn: Speculating Sparse Attention
- RAD: Rule-Augmented Relational Anomaly Detection
- R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation
- ShadAR: LLM-driven shader generation to transform visual perception in Augmented Reality
- Learning Discriminative Geometry for Drifting Models
- Reference Games as a Testbed for the Alignment of Model Uncertainty and Clarification Requests