AMTFV: Agentic Mathematical Tool-Flow Verification for LLM Self-Correction
An AI research paper on AMTFV: Agentic Mathematical Tool-Flow Verification for LLM Self-Correction.
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.
MOT-SR: Multi-Objective Tool-Augmented Scientific Equation Discovery with Large Language Models
An AI research paper on MOT-SR: Multi-Objective Tool-Augmented Scientific Equation Discovery with Large Language Models.
Engineering 5.0 · Research 7.0 · Business 4.0
TraceViT: Grounded Trace Supervision for Visual Abstract Reasoning
An AI research paper on TraceViT: Grounded Trace Supervision for Visual Abstract Reasoning.
Engineering 5.0 · Research 7.0 · Business 4.0
ResKV: Reconstructing Omitted Attention Contributions for Fixed-Budget KV Cache Compression
An AI research paper on ResKV: Reconstructing Omitted Attention Contributions for Fixed-Budget KV Cache Compression.
Engineering 5.0 · Research 7.0 · Business 4.0
TOOD: Task-Aware Out-of-Distribution Score Calibration for Continual Learners
An AI research paper on TOOD: Task-Aware Out-of-Distribution Score Calibration for Continual Learners.
Engineering 5.0 · Research 7.0 · Business 4.0
Convergence and Regret of the Policy Gradient for Multi-Armed Bandits in Diffusion Environment
An AI research paper on Convergence and Regret of the Policy Gradient for Multi-Armed Bandits in Diffusion Environment.
Engineering 5.0 · Research 7.0 · Business 4.0
CoDe-SSM: Context-Detail Decoupled State Space Model for Efficient UHD Image Restoration
An AI research paper on CoDe-SSM: Context-Detail Decoupled State Space Model for Efficient UHD Image Restoration.
Engineering 5.0 · Research 7.0 · Business 4.0
FibVLA: An Efficient Temporal Vision-Language-Action Model with Fibonacci Sampling
An AI research paper on FibVLA: An Efficient Temporal Vision-Language-Action Model with Fibonacci Sampling.
Engineering 5.0 · Research 7.0 · Business 4.0
The Parts Are Greater Than the Sum: Automated Task Sequencing for Efficient Training of Multi-Policy LLMs
An AI research paper on The Parts Are Greater Than the Sum: Automated Task Sequencing for Efficient Training of Multi-Policy LLMs.
Engineering 5.0 · Research 7.0 · Business 4.0
FriendBench: Benchmarking Dyadic Familiarity Inference in Humans and Multimodal Large Language Models
An AI research paper on FriendBench: Benchmarking Dyadic Familiarity Inference in Humans and Multimodal Large Language Models.
Engineering 5.0 · Research 7.0 · Business 4.0
QASP: Query-Adaptive Robust Vector Search Policy
An AI research paper on QASP: Query-Adaptive Robust Vector Search Policy.
Engineering 5.0 · Research 7.0 · Business 4.0
WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning
An AI research paper on WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning.
Engineering 5.0 · Research 7.0 · Business 4.0
A Human-Centered Validation of the Explainability-Performance Coefficient
An AI research paper on A Human-Centered Validation of the Explainability-Performance Coefficient.
Engineering 5.0 · Research 7.0 · Business 4.0
When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning
An AI research paper on When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning.
Engineering 5.0 · Research 7.0 · Business 4.0
CENDRe: Concept Extraction with Natural Domain Representations
An AI research paper on CENDRe: Concept Extraction with Natural Domain Representations.
Engineering 5.0 · Research 7.0 · Business 4.0
RayViT: Ray-Conditioned Visual Representations for Viewpoint-Robust Imitation Learning
An AI research paper on RayViT: Ray-Conditioned Visual Representations for Viewpoint-Robust Imitation Learning.
Engineering 5.0 · Research 7.0 · Business 4.0
The Theoretical Foundation of Socratic Tests: Dynamic, Multimodal, Conversational Examinations
An AI research paper on The Theoretical Foundation of Socratic Tests: Dynamic, Multimodal, Conversational Examinations.
Engineering 5.0 · Research 7.0 · Business 4.0
AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers
An AI research paper on AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers.
Engineering 5.0 · Research 7.0 · Business 4.0
FlexComposer: Unified Video Compositing from Images to Dynamic Footage with Flexible Trajectory Control
An AI research paper on FlexComposer: Unified Video Compositing from Images to Dynamic Footage with Flexible Trajectory Control.
Engineering 5.0 · Research 7.0 · Business 4.0
OASIS: Occlusion-aware Single-image Hand Avatar Reconstruction via 3D Gaussian Splatting
An AI research paper on OASIS: Occlusion-aware Single-image Hand Avatar Reconstruction via 3D Gaussian Splatting.
Engineering 5.0 · Research 7.0 · Business 4.0