AI.info
Latest Research — Page 75
Browse Latest Research on AI.info.
- StreamingTOM: Streaming Token Compression for Efficient Video Understanding
- Enhancing Floor Plan Recognition: A Hybrid Mix-Transformer and U-Net Approach for Precise Wall Segmentation
- Global-Aware Edge Prioritization for Pose Graph Initialization
- From Knowledge to Inference: Formalizing Specialized Public Health Reasoning on GlobalHealthAtlas
- Adaptive Consistency Graph for Long-Horizon Agents
- Learning Multiple Utterance-Level Attribute Representations with a Unified Speech Encoder
- Re-understanding Graph Unlearning through Memorization
- X-WIN: Building Chest Radiograph World Model via Predictive Sensing
- Data Whitening Improves Sparse Autoencoder Learning
- A Systematic Benchmark of Intensity Normalisation Methods for 3D Knee MRI Segmentation and Cross-Domain Generalisability
- A Comparative Evaluation of Embeddings and LLMs in a Greek Book Publisher Setting - The CUP Dataset
- Structured Residual Connectivity Matters for Diffusion Transformers
- Evidence-Decision-Feedback: Theory-Driven Adaptive Scaffolding for LLM Agents
- Learning Cell-Aware Hierarchical Multi-Modal Representations for Robust Molecular Modeling
- HYPE-EDIT-1: Benchmark for Measuring Reliability in Frontier Image Editing Models
- Integrating Virtual Reality and Large Language Models for Team-Based Non-Technical Skills Training and Evaluation in the Operating Room
- OpenEBFM: Energy-based Foundation Models Are Scalable Architecture
- Distributional Consistency Loss: Beyond Pointwise Data Terms in Inverse Problems
- DianShi-RxnDB: A Large-Scale, Fine-Grained Organic Reaction Data Platform Built via a Fully Automated Pipeline for Researchers and AI Agents
- HiRAE: Hierarchical Representation Autoencoding with Residual Budgets
- Nip Rumors in the Bud: Retrieval-Guided Topic-Level Adaptation for Test-Time Fake News Video Detection
- PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards
- Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention
- Hierarchical Graph Convolutional Network Approach for Detecting Low-Quality Documents
- Invariance before structure: two modes of emergent compression in representation learning
- LAOF: Robust Latent Action Learning with Optical Flow Constraints
- Valori: A Deterministic Memory Substrate for AI Systems
- ADVICE: Answer-Dependent Verbalized Confidence Estimation
- Multi-granularity Interactive Attention Framework for Residual Hierarchical Pronunciation Assessment
- MEGConformer: Conformer-Based MEG Decoder for Robust Speech and Phoneme Classification
- Stable and Efficient Single-Rollout RL for Multimodal Reasoning
- PhysLDM: Latent Diffusion for High-Fidelity Deformable Simulation
- NICE Toolbox: Nonverbal Interpersonal Communication Exploration Toolbox
- Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement
- VoxTell: Free-Text Promptable Universal 3D Medical Image Segmentation
- HeFS: Helper-Enhanced Feature Selection via Pareto-Optimized Genetic Search
- MedEyes: Learning Dynamic Visual Focus for Medical Progressive Diagnosis
- Running VLAs at Real-time Speed
- Semi-Supervised Regression with Heteroscedastic Pseudo-Labels
- It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning