Geometry-Guided Layerwise FFN Width Allocation in Transformers
An AI research paper on Geometry-Guided Layerwise FFN Width Allocation in Transformers.
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.
Instruction-Conditioned Exploration with Asymmetric Reinforcement Learning and Self-Distillation
An AI research paper on Instruction-Conditioned Exploration with Asymmetric Reinforcement Learning and Self-Distillation.
Engineering 5.0 · Research 7.0 · Business 4.0
How Much Does a Reasoning Summary Reveal? An Observability Ladder for Large Language Models
An AI research paper on How Much Does a Reasoning Summary Reveal? An Observability Ladder for Large Language Models.
Engineering 5.0 · Research 7.0 · Business 4.0
MemArbiter: Decision-Time Memory Arbitration for Long-Horizon LLM Agents
An AI research paper on MemArbiter: Decision-Time Memory Arbitration for Long-Horizon LLM Agents.
Engineering 5.0 · Research 7.0 · Business 4.0
Self-Improving Large Language Models via Progressive Experience Evolution
An AI research paper on Self-Improving Large Language Models via Progressive Experience Evolution.
Engineering 5.0 · Research 7.0 · Business 4.0
Beyond the Mean: Multi-Moment Policy Optimization for LLM Reasoning
An AI research paper on Beyond the Mean: Multi-Moment Policy Optimization for LLM Reasoning.
Engineering 5.0 · Research 7.0 · Business 4.0
PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs
An AI research paper on PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs.
Engineering 5.0 · Research 7.0 · Business 4.0
Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints
An AI research paper on Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints.
Engineering 5.0 · Research 7.0 · Business 4.0
From Profiling to Synthesis: Benchmarking Implicit Behavioral Alignment in Personalized LLM Agents
An AI research paper on From Profiling to Synthesis: Benchmarking Implicit Behavioral Alignment in Personalized LLM Agents.
Engineering 5.0 · Research 7.0 · Business 4.0
HarMoE: Multi-Source Chest Radiograph Pretraining with Dataset-Disentangled Experts
An AI research paper on HarMoE: Multi-Source Chest Radiograph Pretraining with Dataset-Disentangled Experts.
Engineering 5.0 · Research 7.0 · Business 4.0
Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories
An AI research paper on Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories.
Engineering 5.0 · Research 7.0 · Business 4.0
SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation
An AI research paper on SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation.
Engineering 5.0 · Research 7.0 · Business 4.0
SkillTrace: Traversing a Query-Skill Graph for Composable LLM Agents
An AI research paper on SkillTrace: Traversing a Query-Skill Graph for Composable LLM Agents.
Engineering 5.0 · Research 7.0 · Business 4.0
Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training
An AI research paper on Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training.
Engineering 5.0 · Research 7.0 · Business 4.0
Antares: Foundation Models for Agentic Vulnerability Localization
An AI research paper on Antares: Foundation Models for Agentic Vulnerability Localization.
Engineering 5.0 · Research 7.0 · Business 4.0
Agentic Incident Response through Digital Twin-Enhanced Multiscale Planning
An AI research paper on Agentic Incident Response through Digital Twin-Enhanced Multiscale Planning.
Engineering 5.0 · Research 7.0 · Business 4.0
Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce
An AI research paper on Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce.
Engineering 5.0 · Research 7.0 · Business 4.0
Right Answer, Wrong Method: Shortcut Hacking Misleads the Evaluation of LLM Reasoning on Frontier Science Benchmarks
An AI research paper on Right Answer, Wrong Method: Shortcut Hacking Misleads the Evaluation of LLM Reasoning on Frontier Science Benchmarks.
Engineering 5.0 · Research 7.0 · Business 4.0
FUNDAMENTOS Y ARQUITECTURA MÓDULO 1. Arquitectura de Modelos de Lenguaje y Entornos de Ejecución
An AI research paper on FUNDAMENTOS Y ARQUITECTURA MÓDULO 1. Arquitectura de Modelos de Lenguaje y Entornos de Ejecución.
Engineering 5.0 · Research 7.0 · Business 4.0
Assessing the clinical applicability of large language models for microwave ablation guidance
An AI research paper on Assessing the clinical applicability of large language models for microwave ablation guidance.
Engineering 5.0 · Research 7.0 · Business 4.0