AI.info

Latest Research — Page 84

Browse Latest Research on AI.info.

• Can LLMs Truly Embody Human Personality? Analyzing AI and Human Behavior Alignment in Dispute Resolution
• Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation
• SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning
• "What if she doesn't feel the same?" What Happens When We Ask AI for Relationship Advice
• Flow Matching for Probabilistic Monocular 3D Human Pose Estimation
• From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents
• The Epistemic Politics of AI Anthropomorphism
• Parallel Test-Time Scaling for Latent Reasoning Models
• Agent Bain vs. Agent McKinsey: A New Text-to-SQL Benchmark for the Business Domain
• Efficient Autoregressive Inference for Transformer Probabilistic Models
• Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control
• Exploring Structural Degradation in Dense Representations for Self-supervised Learning
• MIRNet: Integrating Constrained Graph-Based Reasoning with Pre-training for Diagnostic Medical Imaging
• Towards a Generalizable Fusion Architecture for Multimodal Object Detection
• Unsupervised Learning for Industrial Defect Detection: A Case Study on Shearographic Data
• CRAFT: Constrained Reward via Attention Fine-Tuning for Subject Personalization without Composed Targets
• Navigating Epistemic Monocultures in AI-Driven Science: A Simulation Study
• Affinity Contrastive Learning for Skeleton-based Human Activity Understanding
• CausalSplat: Towards Comprehensive Hierarchical Reasoning in 3D Gaussian Splatting
• HUI360: A 360° Egocentric Dataset and Baselines for Human-Robot Interaction Anticipation
• Spotlight on Token Perception for Multimodal Reinforcement Learning
• When AI Becomes Routine: A Decade of Public AI Mediation in Korean Go Commentary
• RLMEval: Evaluating Research-Level Neural Theorem Proving
• SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery
• EpiQAL: Benchmarking Large Language Models in Epidemiological Question Answering and Reasoning
• Learning Branching Policies for MILPs with Proximal Policy Optimization
• Rethinking Multimodal Point Cloud Completion: A Completion-by-Correction Perspective
• OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows
• Multi-Persona Thinking for Bias Mitigation in Large Language Models
• Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videos
• Compositional Machine Design as Program Synthesis with LLMs
• A Model with No Head and Many Thoughts
• It's Not RoPE that Creates Sinks: The Role of Self-Concentration and Value-Non-Mixing in Attention
• Planning a Shared Modular Fixture Layout Across Robotic Disassembly Stages
• Bridging Modalities via Progressive Re-alignment for Multimodal Test-Time Adaptation
• TSGDiff: Rethinking Synthetic Time Series Generation from a Pure Graph Perspective
• Is Misinformation More Open? A Study of robots.txt Gatekeeping on the Web
• KASER: Knowledge-Aligned Student Error Simulator for Open-Ended Coding Tasks
• MoRAgent: Parameter Efficient Agent Tuning with Mixture-of-Roles
• Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics