127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “inference”

17,838 results

Safety

VGR: Visual Grounded Reasoning

DGX agent

arXiv:2506.11991v3 Announce Type: replace-cross Abstract: In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which

safetyarxiv-cs-cl

4 May 2026

Model Releases

VLAs are Confined yet Capable of Generalizing to Novel Instructions

DGX agent

arXiv:2505.03500v5 Announce Type: replace Abstract: Vision-language-action models (VLAs) often achieve high performance on demonstrated tasks but struggle significantly when required to extrapolate, c

Search: “inference”

VGR: Visual Grounded Reasoning

VLAs are Confined yet Capable of Generalizing to Novel Instructions

A Real-time Scale-robust Network for Glottis Segmentation in Nasal Transnasal Intubation

ANCORA: Learning to Question via Manifold-Anchored Self-Play for Verifiable Reasoning

BoostLoRA: Growing Effective Rank by Boosting Adapters

Contextual Online Uncertainty-Aware Preference Learning for Human Feedback

Continuous-tone Simple Points: An ell_0-Norm of Cyclic Gradient for Topology-Preserving Data-Driven Image Segmentation

Decoding Scientific Experimental Images: The SPUR Benchmark for Perception, Understanding, and Reasoning

Differentiable latent structure discovery for interpretable forecasting in clinical time series

DPN-LE: Dual Personality Neuron Localization and Editing for Large Language Models

Echo-{alpha}: Large Agentic Multimodal Reasoning Model for Ultrasound Interpretation

Epistemic reflections on AI answering our questions: overwatch, erudite, logician, interlocutor

Exploring the Limits of Pruning: Task-Specific Neurons, Model Collapse, and Recovery in Task-Specific Large Language Models

Exponential families from a single KL identity

FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering

Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs

From Context to Skills: Can Language Models Learn from Context Skillfully?

From surveillance to signalling: escalation channels as environmental controls for agentic AI

Generalizable Sparse-View 3D Reconstruction from Unconstrained Images

Generate Your Talking Avatar from Video Reference

Gradient-Based Optimization on Godel Logic as Discrete Local Search

Grounding Agent Memory in Contextual Intent

Heterogeneous Scientific Foundation Model Collaboration

How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance

In-Context Examples Suppress Scientific Knowledge Recall in LLMs

Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists

Knowledge Graph Representations for LLM-Based Policy Compliance Reasoning

Learning Generalizable Multimodal Representations for Software Vulnerability Detection

Learning to Reason: Targeted Knowledge Discovery and Fuzzy Logic Update for Robust Image Recognition

Lightweight Distillation of SAM 3 and DINOv3 for Edge-Deployable Individual-Level Livestock Monitoring and Longitudinal Visual Analytics

Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction

LLMs Capture Emotion Labels, Not Emotion Uncertainty: Distributional Analysis and Calibration of Human--LLM Judgment Gaps

Machine Collective Intelligence for Explainable Scientific Discovery

Mapping the Phase Diagram of the Vicsek Model with Machine Learning

METASYMBO: Multi-Agent Language-Guided Metamaterial Discovery via Symbolic Latent Evolution

MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction

Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPO

MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons

Neural Aided Kalman Filtering for UAV State Estimation in Degraded Sensing Environments

Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation

PhyCo: Learning Controllable Physical Priors for Generative Motion

Predicting Covariate-Driven Spatial Deformation for Nonstationary Gaussian Processes

Proactive Dialogue Model with Intent Prediction

REBENCH: A Procedural, Fair-by-Construction Benchmark for LLMs on Stripped-Binary Types and Names (Extended Version)

Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding

Revealing the Impact of Visual Text Style on Attribute-based Descriptions Produced by Large Visual Language Models

Robust Lightweight Crack Classification for Real-Time UAV Bridge Inspection

RopeDreamer: A Kinematic Recurrent State Space Model for Dynamics of Flexible Deformable Linear Objects