AI.info

Latest Research — Page 41

Browse Latest Research on AI.info.

• Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules
• Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games
• Kleinkram: Open Robotic Data Management
• Elastic ViTs from Pretrained Models without Retraining
• "Jutters"
• ORCH: Organizational Principles Enable Collective Intelligence in Embodied AI
• SV-TAD: Native Sparse Convs for Efficient Temporal Action Detection
• Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety
• Müntz-Szász Networks: Neural Architectures with Learnable Power-Law Bases
• Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness
• Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games
• Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs
• CRONOS: Continuous Time Reconstruction for 4D Medical Longitudinal Series
• Vroom-Vroom at SHROOM-Visions: A Multi-Judge Committee for Detecting Hallucinated Spans in Vision-Language Outputs
• On the Regulatory Potential of User Interfaces for AI Agent Governance
• Representation-driven Endoscopic Visual Embedding Alignment for Latent Generation
• One Size, Many Fits: Aligning Diverse Group-Wise Click Preferences in Large-Scale Advertising Image Generation
• UltraBERT: Beyond the Limit of BERT Pre-Training
• IPCV: Information-Preserving Compression for MLLM Visual Encoders
• Bridging Academia and Industry: A Comprehensive Benchmark for Attributed Graph Clustering
• SemGeo-Gen: Unsupervised Generation of Approximate Cross-Instance Semantic-Geometric Correspondences
• PropUQ-MAS: Propagation-Aware Uncertainty Quantification for LLM Multi-Agent Systems
• RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model
• AViTS: Adaptive Spatiotemporal Token Selection for Efficient Dynamic-Resolution Generation
• AI Progress Should Be Measured by Capability-Per-Resource, Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLMs
• On topological descriptors for graph products
• Confidence-Based Response Abstinence: Improving LLM Trustworthiness via Activation-Based Uncertainty Estimation
• Embodied Cognition Augmented End2End Autonomous Driving
• From Reachability to Learnability: Geometric Design Principles for Quantum Neural Networks
• Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum
• Formalized Hopfield Networks and Boltzmann Machines
• PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation
• Minimum-Cost Network Flow with Dual Predictions
• Clarify Before Executing: A Self-Evolving Agent for Resolving Intent Asymmetry in 3D Tool Orchestration
• Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection
• Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents
• CageDroneRF: A Large-Scale RF Benchmark and Toolkit for Drone Perception
• MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery
• CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates
• Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses