127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

All entries

94,811 results

Research

The persistence of painting styles

DGX agent

arXiv:2511.16695v2 Announce Type: replace Abstract: Art is a deeply personal and expressive medium, where each artist brings their own style, technique, and cultural background into their work. Tradit

researcharxiv-cs-cv

31 Aug 2026

Model Releases

The Telephone Game: Evaluating Semantic Drift in Unified Models

DGX agent

arXiv:2509.04438v3 Announce Type: replace-cross Abstract: Unified models (UMs) combine visual understanding (I2T) and generation (T2I) in a single framework. We focus on T2I and I2T, where cross-consi

All entries

The persistence of painting styles

The Telephone Game: Evaluating Semantic Drift in Unified Models

There and Back Again: Bidirectional Diffusion Bridges for Multimodality Translation

Thread-Efficient Decoding for Neural Texture Compression

TI^2PS: A Topology-Informed Inverse Design Framework for Stochastic Multicellular Pattern Formation

Timing-Aware Repurchase Prediction for Web-Scale E-Commerce: Survival Models for Multi-Surface Grocery Recommendation

Token-Budget Distillation: Transferring Full-Token Semantics to Compressed Video Vision-Language Models

TokenPilot: Cache-Efficient Context Management for LLM Agents

ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMs

Towards a mathematical theory of superposition

Towards Large-Scale Heterogeneous Data Organization for Scientific Foundation Models: A Nuclear Fusion Case Study

TQD-Track: Temporal Query Denoising for 3D Multi-Object Tracking

Training-free Suction Grasp Detection for Deformed Aseptic Cartons Using Vision-Language Models and Geometric Surface Scoring

Training-Free Temporal Abstraction for General Video Understanding

Trajectory balance: Improved credit assignment in GFlowNets

Trajectory-Level Speculative Decoding for Diffusion Language Models

Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning

UIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering

Under-Mattress Temporal Sensing for Next-Day Agitation Risk Scoring in Dementia Wards

UniLipi: A Unified Multi-Script OCR for Historical Indic Manuscripts

Unsupervised Continual Learning with Growing Self-Organizing Maps and Synthetic Replay

uScenes: A Multimodal RGB and 3D Sonar Dataset for Underwater Robot Perception

Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture - Bridging Predictive and Generative Self-Supervised Learning

VersaGauss: A Versatile Framework for Generating Multiphase Dynamics with 3D Gaussians

VICT: Verifier-Instrumented Credit Tracing for Long-Horizon LLM Agent Reinforcement Learning

Video Generative Models as Geometry Learner

VidParse: Online Parsing of Egocentric Procedures Like a Pro

VISTA: Verifier-Informed Student-to-Teacher Adaptation for On-Policy Self-Distillation

Visual Token Coding for Video Multimodal Large Language Models

WALDO: One-Shot Exemplar-Conditioned Object Detection in Cluttered Scenes

What Can Low Resource Languages Learn From Each Other?

What Do Interaction Representations Actually Measure? Pre-Event Separability in Weakly-Supervised Violence Detection

What Makes Agent Memory Useful for Reliable Unanswerable Question Handling?

What Will This Copper Look Like Later? Forecasting Surface Appearance and Rendering It as a PBR Material

When Can Conditional Flow Matching Replace Pointwise Negative Log-Likelihood?

When Linguistic and Internal Confidence Diverge in Large Language Models

When Muon Meets Task Interference: A Spectral Perspective on Continual Learning and Model Merging

When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI

When the City Teaches the Car: Label-Free 3D Perception from Infrastructure

When Tokenizers Fail: Byte-Level Chunking for Zero-Shot Transfer to Low-Resource Languages

Why Didn't It Check? Unsupported Final Claims and Their Repair in Two Tool-Equipped Language Models

WilLaGS: Latent-Conditional 3D Appearance Fields for Robust Gaussian Splatting In-the-Wild

XHotpotQA: A Benchmark for Cross-Lingual Knowledge Composition in Multi-Hop Question Answering

ZipMVS: Multi-View Stereo with Compressed Cost Volumes

4DSynth: Controllable Procedural World Synthesis for Dynamic Embodied Simulation

6.5% of the Neuro-Symbolic Literature Can Be Reproduced from Its Published Artifacts, a Six-Stage Audit Framework and First Instantiation

A causal graph-informed temporal convolution architecture for interpretable retail electricity price forecasting

A Contract-Centered Architecture for Scalable and Manageable Agentic Runtimes