AI.info

Latest Research — Page 89

Browse Latest Research on AI.info.

• Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment
• You Only Train Once: Differentiable Subset Selection for Omics Data
• Compact Memory for Continual Logistic Regression
• DiffuSearch: How Hybrid Trajectory Planning Benefits from Aligned Objectives in Diffusion and Action Space
• DynamicGTR: Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities on Graph QAs
• AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models
• Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions
• Grounding Agent Memory in Contextual Intent
• One4Many-StablePacker: An Efficient Deep Reinforcement Learning Framework for the 3D Bin Packing Problem
• What You Can't See Is What You Learn: Restricted Evidence Visibility Favors Compositional Generalization in Shared-Genome Language-Model Societies
• The Configuration of Space: Probing the Way Social Interaction and Perception are Affected by Task-Specific Spatial Representations in Online Video Communication
• Can Large Language Models Anticipate Behavioral Responses to Social Policies? A Case of Pension Enrollment Prediction among China's Flexible Workers
• Efficient and Reliable Estimation of Named Entity Linking Quality: A Case Study on GutBrainIE
• GEWDiff: Geometric Enhanced Wavelet-based Diffusion Model for Hyperspectral Image Super-resolution
• PROPER Agents: Proactivity Driven Personalized Agents for Advancing Knowledge Gap Navigation
• ReGal: A First Look at PPO-based Legal AI for Judgment Prediction and Summarization in India
• MemUse: Moving Memory Evaluation from Direct QA to Natural Integration in Long-Term Human-AI Conversation
• Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task
• LaVPR: Benchmarking Language and Vision for Place Recognition
• Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
• Trapped by simplicity: When Transformers fail to learn from noisy features
• Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception
• Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification
• Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation
• FlyCo: Foundation Model-Empowered Drones for Autonomous 3D Structure Scanning in Open-World Environments
• Structured Memory for Edge Language Models: Persistent Context and Corpus Retrieval via O(1) SSM State Injection
• Mitigating Semantic Collapse in Partially Relevant Video Retrieval
• Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall
• Articulated Object Reconstruction from Rest-State Observation
• Robust and Efficient Motion Reasoning for Privacy-Aware Classroom Incident Recognition
• Gated Uncertainty-Aware Runtime Dual Invariants for Neural Signal-Controlled Robotics
• GraphKeeper: Graph Domain-Incremental Learning via Knowledge Disentanglement and Preservation
• Realizing Immersive Volumetric Video: A Multimodal Framework for 6-DoF VR Engagement
• Vis2Reg: Visibility-Aware Landmark-Free Geometric 3D--2D Registration for Liver Laparoscopy
• Beyond One-Size-Fits-All: Neural Networks for Differentially Private Tabular Data Synthesis
• Cross-Domain Generalization in Machine Unlearning via Label-Conditioned Energy Magnitude Regularization
• Causal World Modeling for Robot Control
• Schema-Guided Hierarchical Information Extraction and Semantic Evaluation Using Generative AI
• Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts
• AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness