GuardianAgentBench: Where Agents Fail and How to Guard Them
An AI research paper on GuardianAgentBench: Where Agents Fail and How to Guard Them.
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.
Sparse Concept Channels in Frozen 3D CT Vision Encoders
An AI research paper on Sparse Concept Channels in Frozen 3D CT Vision Encoders.
Engineering 5.0 · Research 7.0 · Business 4.0
Reexamining zero-shot summarization: Empirical investigation of trustworthiness of LLM-summarizers
An AI research paper on Reexamining zero-shot summarization: Empirical investigation of trustworthiness of LLM-summarizers.
Engineering 5.0 · Research 7.0 · Business 4.0
EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent Specialization
An AI research paper on EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent Specialization.
Engineering 5.0 · Research 7.0 · Business 4.0
V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure
An AI research paper on V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure.
Engineering 5.0 · Research 7.0 · Business 4.0
Case study: proving sqrt(2) irrational with LPTP and an LLM
An AI research paper on Case study: proving sqrt(2) irrational with LPTP and an LLM.
Engineering 5.0 · Research 7.0 · Business 4.0
Case study: solving P-99 with LPTP and an LLM
An AI research paper on Case study: solving P-99 with LPTP and an LLM.
Engineering 5.0 · Research 7.0 · Business 4.0
slang.gr as a Large-Scale Crowdsourced Resource for Non-Standard Greek
An AI research paper on slang.gr as a Large-Scale Crowdsourced Resource for Non-Standard Greek.
Engineering 5.0 · Research 7.0 · Business 4.0
An LLM-Driven Workflow for Automated Process Control Strategy Generation and Tuning from Dynamic Process Models
An AI research paper on An LLM-Driven Workflow for Automated Process Control Strategy Generation and Tuning from Dynamic Process Models.
Engineering 5.0 · Research 7.0 · Business 4.0
Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning
An AI research paper on Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning.
Engineering 5.0 · Research 7.0 · Business 4.0
AI Assistants Overassist
An AI research paper on AI Assistants Overassist.
Engineering 5.0 · Research 7.0 · Business 4.0
Scaling Up Formal Representation of Clinical Trial Protocols in Ensemble Logic Using LLMs: A Preliminary Study
An AI research paper on Scaling Up Formal Representation of Clinical Trial Protocols in Ensemble Logic Using LLMs: A Preliminary Study.
Engineering 5.0 · Research 7.0 · Business 4.0
From Static Bibliometrics to Dynamic Knowledge Graphs: An LLM-Powered Framework for Modernizing Science, Technology, and Innovation (STI) Analytics
An AI research paper on From Static Bibliometrics to Dynamic Knowledge Graphs: An LLM-Powered Framework for Modernizing Science, Technology, and Innovation (STI) Analytics.
Engineering 5.0 · Research 7.0 · Business 4.0
Euclid-MCP: A Model Context Protocol Server for Deterministic Logical Reasoning via Prolog
An AI research paper on Euclid-MCP: A Model Context Protocol Server for Deterministic Logical Reasoning via Prolog.
Engineering 5.0 · Research 7.0 · Business 4.0
Thinkink: 2D Spatial Ink-native Interaction with LLMs
An AI research paper on Thinkink: 2D Spatial Ink-native Interaction with LLMs.
Engineering 5.0 · Research 7.0 · Business 4.0
Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks
An AI research paper on Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks.
Engineering 5.0 · Research 7.0 · Business 4.0
Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate it
An AI research paper on Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate it.
Engineering 5.0 · Research 7.0 · Business 4.0
Improved lower bounds for the Shannon capacity of odd cycles
An AI research paper on Improved lower bounds for the Shannon capacity of odd cycles.
Engineering 5.0 · Research 7.0 · Business 4.0
GS-Agent: Creating 4D Physical Worlds With Generative Simulation
An AI research paper on GS-Agent: Creating 4D Physical Worlds With Generative Simulation.
Engineering 5.0 · Research 7.0 · Business 4.0
From Resource Flow to Executable Tests: Petri-Net-Guided LLM Test Generation for Concurrent Stateful Rust APIs
An AI research paper on From Resource Flow to Executable Tests: Petri-Net-Guided LLM Test Generation for Concurrent Stateful Rust APIs.
Engineering 5.0 · Research 7.0 · Business 4.0