AI.info

Latest Research — Page 13

Browse Latest Research on AI.info.

• XInsight: Integrative Stage-Consistent Psychological Counseling Support Agents for Digital Well-Being
• It depends: Incorporating correlations for joint aleatoric and epistemic uncertainties of high-dimensional output spaces
• EpiAgent: An Agent-Centric System for Ancient Inscription Restoration
• Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch
• AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees
• MeanVoiceFlow: One-step Nonparallel Voice Conversion with Mean Flows
• Towards general embodied intelligence: integrating large language models, knowledge bases, and reasoning capabilities to build the next generation of AI agents
• Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation
• BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning
• ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
• Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization
• Breaking the Safety-Capability Tradeoff: Reinforcement Learning with Verifiable Rewards Maintains Safety Guardrails in LLMs
• A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
• InsideOut: Integrated RGB-Radiative Gaussian Splatting for Comprehensive 3D Object Representation
• Generative Classifiers Avoid Shortcut Solutions
• G3Ego: Gaze-Guided Graphs for Egocentric Action Understanding
• FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Prediction with Large Language Models
• Improving the Convergence Rate of Ray Search Optimization for Query-Efficient Hard-Label Attacks
• Trust, Usefulness, and Dependency on AI in Programming: A Hierarchical Clustering Approach
• Guided Transfer Learning for Discrete Diffusion Models
• INC: An Indirect Neural Corrector for Auto-Regressive Hybrid PDE Solvers
• MODEST: Multi-Optics Depth-of-Field Stereo Dataset
• Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
• The Biased Oracle: Assessing LLMs' Understandability and Empathy in Medical Diagnoses
• Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models
• Fluid Reasoning Representations
• ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution
• MPA: Multimodal Prototype Augmentation for Few-Shot Learning
• Learning Topology-Driven Multi-Subspace Fusion for Grassmannian Deep Network
• FormuEvo: LLM-Guided Evolution for Discovering Solver-Efficient Mixed-Integer Programming Formulations
• Aligning Agentic World Models via Knowledgeable Experience Learning
• IterResearch: Rethinking Long-Horizon Agents with Interaction Scaling
• FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs
• Associative Syntax and Maximal Repetitions reveal context-dependent complexity in fruit bat communication
• Hidden State Poisoning Attacks against Mamba-based Language Models
• ID-Crafter: VLM-Grounded Online RL for Compositional Multi-Subject Video Generation
• Conditional PED-ANOVA: Hyperparameter Importance in Hierarchical & Dynamic Search Spaces
• When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models
• When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions
• Leave It to the Experts: Detecting Knowledge Distillation via MoE Expert Signatures