AI.info

Latest Research — Page 50

Browse Latest Research on AI.info.

• Context-Aware Autoregressive Image Generation for Emerging Reasoning Properties
• GIFT: Representation Geometry Matters for Single-Domain Generalized Object Detection
• Democratising Pathology Co-Pilots: An Open Pipeline and Dataset for Whole-Slide Vision-Language Modelling
• TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs
• ParetoSaddler: Pareto-Guided Optimization of Agent Harnesses for Quality and Cost
• MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting
• Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models
• Compatible Likelihoods for Flow Matching on Manifolds
• Historical Consensus: Preventing Posterior Collapse via Iterative Selection of Gaussian Mixture Priors
• OverLay++: Dense-Overlap Layout-to-Image Generation Dataset
• Plain Transformers are Surprisingly Powerful Link Predictors
• Learning-to-Memorize: Dynamic Context Management for Long-Horizon Autoregressive Video Generation
• GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification
• MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation
• AI for Green Spaces: Leveraging Autonomous Navigation and Computer Vision for Park Litter Removal
• Enhancing CLIP Robustness via Cross-Modality Alignment
• Dual Goal Representations
• RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models
• MiniFool -- Physics-Constraint-Aware Minimizer-Based Adversarial Attacks in Deep Neural Networks
• NIM: Neuro-symbolic Ideographic Metalanguage for Inclusive Communication
• LiteraryQA: Towards Effective Evaluation of Long-document Narrative QA
• JaxWildfire: A GPU-Accelerated Wildfire Simulator for Reinforcement Learning
• Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading
• PragWorld: A Benchmark Evaluating LLMs' Local World Model under Minimal Linguistic Alterations and Conversational Dynamics
• Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding
• Measuring Artifact Reliance in Machine-Generated Text Detectors
• A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies
• MOSLD-Bench: Multilingual Open-Set Learning and Discovery Benchmark for Text Categorization
• X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis
• InstructMesh: Selective Refinement of Generative 3D Models for Fabrication
• From Knowledge to Treatment: Large Language Model Assisted Biomedical Concept Representation for Drug Repurposing
• Generalization Below the Edge of Stability: The Role of Data Geometry
• The Cost of Mismatch: Noise Amplification in Zeroth-Order Reinforcement Learning
• CausalBind: Causal Modeling and Learning for Protein-Molecule Virtual Screening
• RECAP: A Resource-Efficient Method for Adversarial Prompting in Large Language Models
• Towards Efficient Evaluation of Evolutionary Transfer Optimization: Case Studies on Task-Parameterized Applications
• Robust Long-term Test-Time Adaptation for 3D Human Pose Estimation through Motion Discretization
• Empowering Medical Equipment Sustainability in Low-Resource Settings: An AI-Powered Diagnostic and Support Platform for Biomedical Technicians
• ODC: Orthogonal Drift Correction for Improved Text-to-Image Semantic Alignment at Inference
• Unified Reinforcement and Imitation Learning for Vision-Language Models