AI.info

Latest Research — Page 42

Browse Latest Research on AI.info.

• Learning to Collaborate: An Orchestrated-Decentralized Framework for Peer-to-Peer LLM Federation
• ReGround: Grounding Reviewer Comments in Multimodal Evidence
• Diagnosing the Reliability of LLM-as-a-Judge via Item Response Theory
• CaMiT: A Time-Aware Car Model Dataset for Classification and Generation
• Visual Sync: Multi-Camera Synchronization via Cross-View Object Motion
• Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views
• CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks
• The Robustness of Differentiable Causal Discovery in Misspecified Scenarios
• AMaPO: Adaptive Margin-attached Preference Optimization for Language Model Alignment
• Ground Truth First: A Longitudinal Evaluation Instrument for Agent Memory, and the Tenure Crossover in Memory-Architecture Rankings
• When Refusals Fail: Unstable Safety Mechanisms in Long-Context LLM Agents
• A systematic review of relation extraction task since the emergence of Transformers
• Neural Texture Splatting: Expressive 3D Gaussian Splatting for View Synthesis, Geometry, and Dynamic Reconstruction
• Probing RLVR training instability through the lens of objective-level hacking
• SAM 3D Body: Robust Full-Body Human Mesh Recovery
• Ladders in Chaos: When, How, (and Perhaps Why) Does Test-Time Scaling Improve LLM Machine Translation
• LEVIO: Lightweight Embedded Visual Inertial Odometry for Resource-Constrained Devices
• CrossVid: A Comprehensive Benchmark for Evaluating Cross-Video Reasoning in Multimodal Large Language Models
• VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
• Tackling Resource-Constrained and Data-Heterogeneity in Federated Learning with Double-Weight Sparse Pack
• UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset
• VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation
• Socially Grounded Agentic AI: Coordinating Plural Perspectives through Social Theory
• StepShield: When, Not Whether to Intervene on Rogue Agents
• MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving
• Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axes
• Particle Monte Carlo methods for Lattice Field Theory
• Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
• InFlux: A Benchmark for Self-Calibration of Dynamic Intrinsics of Video Cameras
• Learning Pseudorandom Numbers with Transformers: Permuted Congruential Generators, Curricula, and Interpretability
• Physics-Constrained Denoising Autoencoders for Data-Scarce Wildfire UAV Sensing
• CuMPerLay: Learning Cubical Multiparameter Persistence Vectorizations
• The Shape of Time: Video-Token Contrast for Temporal Understanding in VideoLMs
• ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition Trees
• VideoLucy: Deep Memory Backtracking for Long Video Understanding
• HealthBench-Psych: A Mental Health Subset of OpenAI's HealthBench
• Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosis
• Residual Diffusion Bridge Model for Image Restoration
• SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?
• JEPA-Anything: Learning Predictive Models across Different Worlds