127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “reasoning”

21,706 results

Research

Visual General Intelligence: A White Paper

DGX agent

arXiv:2608.25924v1 Announce Type: new Abstract: This paper reconsiders intelligence from a vision-centered perspective and examines whether intelligence emerging from visual experience and learning ma

researcharxiv-cs-cv

27 Aug 2026

Safety

Search: “reasoning”

Visual General Intelligence: A White Paper

What Do Medical Vision-Language Models Learn in Radiology? Transfer, Alignment, and Source-Proxy Leakage Under Distribution Shift

When agents act on their own, governance has to live in the data layer

With HuggingFace, Nvidia is also acquiring llama.cpp and the team behind it

Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization

A Judge Should Know What Changed:Construct Validity for LLM-as-a-Judge Evaluation

API is live on QwenCloud: https://www.qwencloud.com/models/qwen3.8-flash 🙌Let's build something!

AURASeg: Attention-Guided Upsampling with Residual-Assisted Boundary Refinement for Drivable-Area Segmentation

Automatic Model Card Generation Using an LLM

Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment

Beyond Accuracy: A Dual-Judge Evaluation Protocol for Vision-Language Models in Legally Grounded Tasks

Causal Modelling of Support Interventions for Student Competency Assessment

Concept-Guided Exploration: Building Persistent, Actionable Scene Graphs

Discovering Adaptive Transmission Programs for Collective Innovation

EgoErrorVQA: Assess Egocentric Comprehension Capabilities through Procedural Errors for Ego-Agentic AI

Evaluating Multiple LLM Generations with Validated Task Coverage

FedV-KGQA: Multi-Hop Question Answering over Vertically Partitioned Knowledge Graphs

FlowNeg: GFlowNet-Guided Diverse Hard Negative Sampling for Knowledge Graph Embedding

Fully quantized NVFP4 Qwen3.8-27B with QUASAR QAD

HMGCLIP: Heterogeneous Multi-Granularity Contrastive Learning for E-commerce Representation Learning

IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Agents

Learning from the Right Rollouts: Data Attribution for PPO-based LLM Post-Training

LG-GER: Language-Guided Group Emotion Recognition via Multimodal Evidence Distillation

Mahalanobis-Based Multi-Head Attention for Complex State Propagation

Matched Excess-Outranker Regularization for Candidate-Set Interference in Continual Knowledge Graph Embedding

Minima-KV: Retention-Preserving KV Cache Compression with Mixed-Format Paged Attention

Mixture of Channel Experts: Static Sparse Supports with Input-Adaptive Mixing for Pointwise Projections

Names Can Hurt: Spotting Slopsquatting Risks Caused by Package Name Hallucinations in Local Coding LLMs

Panning for Gold: Expanding Domain-Specific Knowledge Graphs with General Knowledge

QML for Quantum Sensing under Measurement-Induced Information Loss

Rules Before Oracles: Auditable, User-Configurable Argument Selection for Deliberative Polling

Scalable and Versatile Identification for Hierarchical Structural Causal Models: A New Look at Project STAR

Stack Transformer Based Spatial-Temporal Attention Model for Dynamic Sign Language and Fingerspelling Recognition

Syn2RealTrack: Bridging the Gap Between Synthetic and Real-World Datasets for Online Multi-View Multi-Target Tracking

Too much of a good thing -- when knowledge distillation promotes overfitting, and how to avoid it

Transformer Accelerator (TFA): A Macro-Op INT8 Hardware Chip for Transformer Inference and Machine Translation

TransPhy: Visual In-Context Learning for Physically Grounded Image Editing

WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report

AI University: An LLM-Powered Learning Assistant for Engineering---A Finite Element Method Case Study

CAI-DLLM: Convergence Aware Inference for Diffusion Language Models

Coarse Indexing, Fine Evidence: Decoupling Temporal Granularity in Long-Video RAG

Compositional Chain-of-Relations for Faithful Knowledge Graph Question Answering with Large Language Models

Do Large Language Models Perform Well on Comprehending Poetic Logic in Modern Chinese Poetry?

ESCRAG-R1: Retrieval-Augmented Reinforcement Learning for Emotional Support Conversation

Evaluation of Small Vision-Language Models on Qualitative Mechanical Problems

EviSafe: Evidence-Grounded Safety Evaluation for Vision-Language Models

EvoWiki: Incremental State Overwriting and Traceable Question Answering for Cross-Meeting Knowledge Evolution

HERO: Human-profile Enhanced Retrieval Optimization Framework for Long-term Agent Memory