127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “framework”

42,982 results

Safety

PhysEvo: Astra Can Act, Let It

DGX agent

arXiv:2610.08995v1 Announce Type: new Abstract: Astra can act, yet reliable manipulation depends on the system through which it observes and controls the world. We introduce PhysEvo, a framework for p

safetyarxiv-cs-ro

8 Oct 2026

Model Releases

QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation

DGX agent

arXiv:2610.10497v1 Announce Type: new Abstract: We introduce QuadTok, a novel framework for visual tokenization and autoregressive image generation. Compared to traditional approaches using 2D grids o

Search: “framework”

PhysEvo: Astra Can Act, Let It

QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation

STRIKE: Learning Visual State Transitions for Physical World Modeling

Taming an End-to-End Autonomous Driving Policy for Urban Navigation of Quadruped Robots

Tetris3D: 3D Scene Generation With Objects That Fit Together

A Data-Centric Review of Plant Disease Datasets: Taxonomy, Critical Analysis, Environmental Variability, and Implications for Precision Agriculture

Attention from Above: A Multimodal Model for Drone-Based Object Localization

Beyond Corrected Memory: Execution Consistency in Multi-Agent Systems

Beyond hours saved: Building the business case for agentic automation

CuratorMAS: Automating Dataset Curation via Multi-Agent Orchestration

DecepEval: A Benchmark for Evaluating Deception in LLM Agents

DistScene: Object-to-Scene Distillation for 3D Scene Generation

DTFormer: Text-Guided Semantic Alignment for RGB-D Segmentation

EC-RAG: Event Chain Retrieval-Augmented Generation for Long Video Understanding

Embedded Bare-Metal Radar-Inertial Odometry

Event-Driven Proactive Robot Assistance through Vision-Language Reasoning

Improving Synthetic Data Generation for Argument Mining via Adversarial Reinforcement Learning

Language Unalignability: Why Some Concepts Resist Cross-Cultural Benchmark Evaluation

Magnet-Aware Control of Legged Robots

Mathematical Invariant-Enabled Topological Neural Networks for Molecular and Materials Property Prediction

Modeling Latent Disturbances for Robust Decision-Making in World Models

Mu-DisCoCat: A Variational Pipeline for Compositional Generalization on Quantum Processors

OpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception

Polar: LLM-Powered Synthesis of Real-World Cyber Evidence for Prioritization and Mitigation

RACER: Residual-Adaptive Closed-Loop Estimation for Sampling-Based Planning in Wheeled-Quadruped Racing

Random Feature Gaussian Process Attention: Linear-Time Probabilistic Attention with Calibrated Uncertainty

Rethinking Fine-Tuning: Unlocking Hidden Capabilities in Vision-Language Models

RMRRT: Riemannian Barrier Metric RRT for Inequality-Aware Steering on Equality Manifolds

Robust Nonprehensile Object Transport with Quadruped Robots

Scalable extraction and visualization of multi-attribute logical and functional dependencies in tabular data

Sensor-Language-Action Models

SkillPoison: Progressive Skill Poisoning via Successful Experiences

Task-Space Imitation Guidance for Efficient Reinforcement Learning

Toward Trustworthy Physical AI for Human Interaction

Towards Explainable Benchmarking for Data-driven Post-Wildfire Debris Flow Prediction

UltraDiff: Differentiable Ray Tracing in Ultrasound for Shape Optimization

Uncertainty in Representation Learning on Knowledge Graphs

Uniform Discrete Diffusion Models are Minimax Optimal for Estimating Distributions with Small Effective Support Size

VALSE: Vertical Adaptive Layer Skipping for Efficient Inference in Large Language Models

AdaEva: Accelerating LLM-Driven Algorithm Design with Adaptive Partial Evaluation

AFP-GIC: Controllable Generative Image Compression [R]

Anatomy-aware Fine-grained Multimodal Fusion for Laryngopharyngeal Cancer T-Staging Prediction Using CT and Radiology Report

Arithmetic Actor Heads and Training Stabilization for Out-of-Distribution Reinforcement Learning

Bilinear Flow Policy: Distributional Extrapolation for Goal-Conditioned Visuomotor Imitation

Characterizing Parallelism Strategies in LLM Inference: Fundamental Compute-Communication Trade-offs

Co-Optimizing Graph Sparsification and Approximate Computing for Energy-Efficient FPGA-Based GCN Inference

Correct Verdicts, Flawed Reasoning: Structured Auditing of LLM-based Vulnerability Reasoning

Efficient Hierarchical Transformers for Representing Log Data