AI.info

Latest Research — Page 69

Browse Latest Research on AI.info.

• RobotSeg: A Model and Dataset for Segmenting Robots in Image and Video
• Estimation of the Label-Noise Transition Matrix with Performance Guarantees via Selective Classification
• The Score Is Not the Structure: Brain Alignment and Cross-Lingual Transfer
• Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment
• StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation
• Recursive Environment Scaling for General Long-Horizon Agents
• KVzap: Fast, Adaptive, and Faithful KV Cache Pruning
• Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement
• SplatReasoner: Enhancing Embodied Reasoning and Grounding by Novel View Synthesis
• Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning
• LogSig-SSM: Time-Series Modelling with Multi-Scale Log-Signature Compression for State-Space Models
• DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learning
• Building Rome from a Single Image
• Partial VOROS: A Cost-aware Performance Metric for Binary Classifiers with Precision and Capacity Constraints
• Multi-Dataset Diagnostic Utility of Clinical Visual Concepts in AI Systems for Dermatology
• Towards Full Pipeline FP8 Reinforcement Learning for LLMs
• OR-License: Evaluating LLM Agents as Real-World Operations Research Practitioners
• Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction
• Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models
• What Is Wrong with Synthetic Data for Scene Text Recognition? A Strong Synthetic Engine with Diverse Simulations and Self-Evolution
• Universal One-third Time Scaling in Learning Peaked Distributions
• GeCo-SRT: Geometry-aware Continual Adaptation for Robotic Cross-Task Sim-to-Real Transfer
• Addressing Mark Imbalance in Integration-free Neural Marked Temporal Point Processes
• Improving CMA-ES Convergence Speed, Efficiency, and Reliability in Noisy Robot Optimization Problems
• Exploring Systems-Thinking Approaches to Loss of Control Risk
• Empirical Variational Autoencoder
• Is Hierarchical Quantization Essential for Optimal Reconstruction?
• AVC-Reward: Event-Centric Audio-Video Consistency Evaluation
• Provably Outlier-resistant Semi-parametric Regression for Transferable Calibration of Low-cost Air-quality Sensors
• TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
• Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
• Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight
• LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Services
• Variational decomposition autoencoding improves disentanglement of latent representations
• WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution
• Separating Syntax from Language: A Mechanistic Account of Translation in Multilingual LLMs
• Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Transformers
• LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis
• Rethinking Nighttime Image Deraining via Learnable Color Space Transformation
• Behavior is Not Enough: A Mechanism-Based Evaluation of Social Norm Emergence in LLM Societies