AI.info

Latest Research — Page 5

Browse Latest Research on AI.info.

• BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping
• Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate
• SurveyGraph: Generating Academic Surveys via Methods-Entity Knowledge Graphs
• FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline
• HLPD: Aligning LLMs to Human Language Preference for Machine-Revised Text Detection
• Debias-SparseGPT: Bias-Aware Pruning for Large Language Models
• SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation
• Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference
• Spherical Steering: Geometry-Aware Activation Rotation for Language Models
• HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference
• Readability Reconsidered: A Cross-Dataset Analysis of Reference-Free Metrics
• SPOT: An Annotated French Corpus and Benchmark for Detecting Critical Interventions in Online Conversations
• Optimized Learned Count-Min Sketch
• HiligayNER: A Baseline Named Entity Recognition Model for Hiligaynon
• Found-RL: foundation model-enhanced reinforcement learning for autonomous driving
• Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding
• VAMOS-OCTA: Vessel-Aware Multi-Axis Orthogonal Supervision for Inpainting Motion-Corrupted OCT Angiography Volumes
• Analytic Planning under Uncertainty with Moment Closure
• EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?
• Enhancing Binary Encoded Crime Linkage Analysis Using Siamese Network
• Vector Arithmetic in Concept and Token Subspaces
• Reading, Writing, Sharing, and Interacting with the World through Video
• MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimization
• Mining Frames: Association Rule Mining as an Unsupervised Framework for News Framing Detection
• Can Computation from Earlier Problems Help LLMs Solve New Ones?
• MS-BART: Unified Modeling of Mass Spectra and Molecules for Structure Elucidation
• InertialAR: Autoregressive 3D Molecule Generation with Inertial Frames
• Direct Conditional Parameterization for N-Dimensional Splatting
• Rethinking Search: A Study of University Students' Perspectives on Using LLMs and Traditional Search Engines in Academic Problem Solving
• Computational Foundations for Strategic Coopetition: Formalizing Trust and Reputation Dynamics
• BAID: A Benchmark for Bias Assessment of AI Detectors
• Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents
• Real-Time 3D Object Detection with Inference-Aligned Learning
• CytoCrowd: A Multi-Annotator Benchmark Dataset for Cytology Image Analysis
• Auto-Regressive Masked Diffusion Models
• Gaussian-Augmented Physics Simulation and System Identification with Complex Colliders
• Why Prototypes Collapse: Diagnosing and Preventing Partial Collapse in Prototypical Self-Supervised Learning
• MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation
• Seg-VAR: Image Segmentation with Visual Autoregressive Modeling
• Automated Plant Disease and Pest Detection System Using Hybrid Lightweight CNN-MobileViT Models for Diagnosis of Indigenous Crops