AI.info
Latest Research — Page 54
Browse Latest Research on AI.info.
- Splat-SAP: Feed-Forward Gaussian Splatting for Human-Centered Scene with Scale-Aware Point Map Reconstruction
- PLAN: Proactive Low-Rank Allocation for Continual Learning
- Efficient Hierarchical Any-Angle Path Planning on Multi-Resolution 3D Grids
- Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs
- Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation
- Multi-agent Coordination via Flow Matching
- SMART: A Surrogate Model for Predicting Application Runtime in Dragonfly Systems
- Ontology-Driven Structural Regularization for Document-Level Relation Extraction
- CALM-IT: Generating Realistic Long-Form Motivational Interviewing Dialogues with Dual-Actor Conversational Dynamics Tracking
- TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction
- CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
- SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation
- When benchmark inferences do not compose: Projectibility in AI evaluation
- Latent Diffusion Model without Variational Autoencoder
- Federated CLIP for Resource-Efficient Heterogeneous Medical Image Classification
- Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection
- SEGA: A Stepwise Evolution Paradigm for Content-Aware Layout Generation with Design Prior
- Degradation-Aware Metric Prompting for Hyperspectral Image Restoration
- MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators
- ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language Models
- VowelPrompt: Hearing Speech Emotions from Text via Vowel-level Prosodic Augmentation
- Activation Steering for Masked Diffusion Language Models
- Fast-SAM3D: 3Dfy Anything in Images but Faster
- 2D Gaussians Spatial Transport for Point-supervised Density Regression
- Transition Matching Distillation for Fast Video Generation
- AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations
- Balancing Centralized Learning and Distributed Self-Organization: A Hybrid Model for Embodied Morphogenesis
- PWAVEP: Purifying Imperceptible Adversarial Perturbations in 3D Point Clouds via Spectral Graph Wavelets
- Seg2Grasp: A Robust Modular Suction Grasping in Bin Picking
- Autodiscover: A reinforcement learning recommendation system for the cold-start imbalance challenge in active learning, powered by graph-aware thompson sampling
- Towards Fine-Grained Code-Switch Speech Translation with Semantic Space Alignment
- ArmnetBench v0.1: Parallel Real-World Evaluation of Manipulation Policies on a Low-Cost Arm Farm
- FlexiAvatar: Unified 3D Gaussian Human Avatars Under Arbitrary Body Visibility
- Radar-APLANC: Unsupervised Radar-based Heartbeat Sensing via Augmented Pseudo-Label and Noise Contrast
- HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics
- Task Prototype-Based Knowledge Retrieval for Multi-Task Learning from Partially Annotated Data
- Are Large Language Models Sensitive to the Motives Behind Communication?
- Physically Guided Visual Mass Estimation from a Single RGB Image
- LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?
- Hybrid-DMKG: A Hybrid Reasoning Framework over Dynamic Multimodal Knowledge Graphs for Multimodal Multihop QA with Knowledge Editing