Large Language Models Are Overconfident in Their Own Responses
An AI research paper on Large Language Models Are Overconfident in Their Own Responses.
Engineering 5.0 · Research 7.0 · Business 4.0
aipentium - AI Papers with Code, Datasets and Engineering Notes
aipentium: browse curated AI and robotics papers about humanoid robots, embodied AI, robot manipulation, VLA models, Diffusion Policy, Sim2Real and robot foundation models.
Beyond the Literal: Decomposing Pragmatic Intent in Multimodal Meme Understanding
An AI research paper on Beyond the Literal: Decomposing Pragmatic Intent in Multimodal Meme Understanding.
Engineering 5.0 · Research 7.0 · Business 4.0
Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models
An AI research paper on Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models.
Engineering 5.0 · Research 7.0 · Business 4.0
Visual Instruction Tuning Aligns Modalities through Abstraction
An AI research paper on Visual Instruction Tuning Aligns Modalities through Abstraction.
Engineering 5.0 · Research 7.0 · Business 4.0
When Retrieval Doesn't Help: A Large-Scale Study of Biomedical RAG
An AI research paper on When Retrieval Doesn't Help: A Large-Scale Study of Biomedical RAG.
Engineering 5.0 · Research 7.0 · Business 4.0
Expert-Aware Refusal Steering
An AI research paper on Expert-Aware Refusal Steering.
Engineering 5.0 · Research 7.0 · Business 4.0
UniCanvas: A Diffusion-base Unified Model for Text-in-Image Joint Generation
An AI research paper on UniCanvas: A Diffusion-base Unified Model for Text-in-Image Joint Generation.
Engineering 5.0 · Research 7.0 · Business 4.0
Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models
An AI research paper on Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models.
Engineering 5.0 · Research 7.0 · Business 4.0
Toward Pre-Deployment Assurance for Enterprise AI Agents: Ontology-Grounded Simulation and Trust Certification
An AI research paper on Toward Pre-Deployment Assurance for Enterprise AI Agents: Ontology-Grounded Simulation and Trust Certification.
Engineering 5.0 · Research 7.0 · Business 4.0
NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
An AI research paper on NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation.
Engineering 5.0 · Research 7.0 · Business 4.0
Solipsistic Superintelligence is Unlikely to be Cooperative
An AI research paper on Solipsistic Superintelligence is Unlikely to be Cooperative.
Engineering 5.0 · Research 7.0 · Business 4.0
DMF: A Deterministic Memory Framework for Conversational AI Agents
An AI research paper on DMF: A Deterministic Memory Framework for Conversational AI Agents.
Engineering 5.0 · Research 7.0 · Business 4.0
Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI
An AI research paper on Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI.
Engineering 5.0 · Research 7.0 · Business 4.0
From Prompt to Service: An SLM-Based Agent Orchestration Gateway for AI-Driven Virtual Worlds
An AI research paper on From Prompt to Service: An SLM-Based Agent Orchestration Gateway for AI-Driven Virtual Worlds.
Engineering 5.0 · Research 7.0 · Business 4.0
Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing
An AI research paper on Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing.
Engineering 5.0 · Research 7.0 · Business 4.0
The DeepSpeak-Agentic Dataset
An AI research paper on The DeepSpeak-Agentic Dataset.
Engineering 5.0 · Research 7.0 · Business 4.0
SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents
An AI research paper on SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents.
Engineering 5.0 · Research 7.0 · Business 4.0
From Control Boundary to Insurance Claim: Reconstructing AI-Mediated Losses Through the CER Framework
An AI research paper on From Control Boundary to Insurance Claim: Reconstructing AI-Mediated Losses Through the CER Framework.
Engineering 5.0 · Research 7.0 · Business 4.0
AI Agents Enable Adaptive Computer Worms
An AI research paper on AI Agents Enable Adaptive Computer Worms.
Engineering 5.0 · Research 7.0 · Business 4.0
Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis
An AI research paper on Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis.
Engineering 5.0 · Research 7.0 · Business 4.0