AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning
An AI research paper on AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning.
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.
Tree-of-Thoughts Reasoning for Text-to-Image In-Context Learning
An AI research paper on Tree-of-Thoughts Reasoning for Text-to-Image In-Context Learning.
Engineering 5.0 · Research 7.0 · Business 4.0
Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning
An AI research paper on Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning.
Engineering 5.0 · Research 7.0 · Business 4.0
From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents
An AI research paper on From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents.
Engineering 5.0 · Research 7.0 · Business 4.0
Physics-Audited Agentic Discovery in Scientific Machine Learning
An AI research paper on Physics-Audited Agentic Discovery in Scientific Machine Learning.
Engineering 5.0 · Research 7.0 · Business 4.0
SpaCellAgent: A Self-Evolving LLM-Based Multi-Agent Framework for Trajectory Analysis
An AI research paper on SpaCellAgent: A Self-Evolving LLM-Based Multi-Agent Framework for Trajectory Analysis.
Engineering 5.0 · Research 7.0 · Business 4.0
SynthAVE: Scalable Synthetic Labeling for E-Commerce with LLM-Arena Validation
An AI research paper on SynthAVE: Scalable Synthetic Labeling for E-Commerce with LLM-Arena Validation.
Engineering 5.0 · Research 7.0 · Business 4.0
HIVE: Understanding Post-Hallucination Reasoning in Vision Language Models
An AI research paper on HIVE: Understanding Post-Hallucination Reasoning in Vision Language Models.
Engineering 5.0 · Research 7.0 · Business 4.0
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
An AI research paper on Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning.
Engineering 5.0 · Research 7.0 · Business 4.0
Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation
An AI research paper on Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation.
Engineering 5.0 · Research 7.0 · Business 4.0
Asymmetric Focal Loss Improves Graph Neural Network Prediction of Drug-Drug Interactions
An AI research paper on Asymmetric Focal Loss Improves Graph Neural Network Prediction of Drug-Drug Interactions.
Engineering 5.0 · Research 7.0 · Business 4.0
Towards Agentic AI Governance: A Preliminary Assessment
An AI research paper on Towards Agentic AI Governance: A Preliminary Assessment.
Engineering 5.0 · Research 7.0 · Business 4.0
Higher-Order Geometric Updates for Levenberg-Marquardt Method via Riemann Normal Coordinates
An AI research paper on Higher-Order Geometric Updates for Levenberg-Marquardt Method via Riemann Normal Coordinates.
Engineering 5.0 · Research 7.0 · Business 4.0
Future Confidence Distillation in Large Language Models
An AI research paper on Future Confidence Distillation in Large Language Models.
Engineering 5.0 · Research 7.0 · Business 4.0
QCNN with Rough Path Signature Kernels
An AI research paper on QCNN with Rough Path Signature Kernels.
Engineering 5.0 · Research 7.0 · Business 4.0
An optimal control approach for neural network architecture adaptation with a posteriori error estimation
An AI research paper on An optimal control approach for neural network architecture adaptation with a posteriori error estimation.
Engineering 5.0 · Research 7.0 · Business 4.0
ALER-TI: Aligned Latent Embedding Retrieval for Time Series Imputation
An AI research paper on ALER-TI: Aligned Latent Embedding Retrieval for Time Series Imputation.
Engineering 5.0 · Research 7.0 · Business 4.0
RL Post-Training Builds Compositional Reasoning Strategies
An AI research paper on RL Post-Training Builds Compositional Reasoning Strategies.
Engineering 5.0 · Research 7.0 · Business 4.0
Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
An AI research paper on Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops.
Engineering 5.0 · Research 7.0 · Business 4.0
Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance
An AI research paper on Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance.
Engineering 5.0 · Research 7.0 · Business 4.0