127,652Total entries

60Added by human

127,592Found by agent

13Categories

Knowledge catalogue

Search: “index”

2,770 results

Research

The K-SCAN Clustering Algorithm

DGX agent

arXiv:2607.24537v1 Announce Type: new Abstract: In the Big Data era, the scalability of clustering algorithms constitutes a key challenge. Traditional density-based methods (e.g., DBSCAN) offer robust

researcharxiv-cs-lg

28 Jul 2026

Research

Search: “index”

The K-SCAN Clustering Algorithm

To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion

Topological Data Analysis and Graph-Theoretic Approaches for Tennis Match Prediction

A Consensus-Based Framework for Relative Preference Evaluation of Large Language Models

DM3D: Dynamic Mamba via Offset-Guided Feature Resampling for Point Cloud Understanding

Encoding Invisible Causation for Bridge Diagnostic Agents: Triple-Guided Retrieval-Augmented Fine-Tuning with QLoRA

Evaluation design conditions the expert-vs-auto MeSH gap: a controlled comparison of bag-of-words and BiomedBERT on the Cohen benchmark

FBLayout: Optimizing Memory Layout for Efficient LLM Finetuning on Mobile GPUs

Looped Latent Attention: Cross-Loop KV Compression for Looped Transformers

Reliability-Aware Bayesian Optimization of 1310 nm PCSELs with FDTD Verification

Statistical mechanics of extensive-width Bayesian neural networks near interpolation

VTM-Nav: Harnessing Cross-Episode Experience for Object-Goal Navigation with Hierarchical Visual-Topological Memory

GLM 5.2 and ik_llama.ccp

Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate it

Autonomous Topology Mutation: Safe Runtime Restructuring for Multi-Agent LLM Systems with Capability, State, and Shadow Invariants

From Checklists to Clusters: A Homeostatic Account of AGI Evaluation

From Scalars to Time Series: Rethinking Implicit Neural Representations for Time-Varying Volumetric Data

Gradient Concentration, Not Weight Saliency, Explains Representation-Level Class Unlearning

I built an open-source multi-agent SDLC harness that beats a cold Claude Code run on large repos, by learning the repo once. Real benchmarks (incl. where it loses) inside. [P]

Perspective Latents as an Architectural Condition for Causal Emergence in Active Inference Agents

Reexamining zero-shot summarization: Empirical investigation of trustworthiness of LLM-summarizers

TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics

TwistedMerge: Certified Higher-Order Diagnostics and Abstention for Model Merging

Unsupervised Metal Artifact Reduction in Dental CBCT using Fine-tuned Cycle-Consistent Adversarial Networks

We benchmarked Opus 5 comprehensively on document understanding through ParseBench. It is roughly on par with Opus 4.8 - it does a few point…

Adaptive Multi-Expert Graph Transformer for Interpretable EEG-Based Diagnostics

Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation

BLUE: Semantics-Preserving Video Compression for Efficient Vision-Language Surveillance Analytics

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning

Comparing Model-agnostic Feature Selection Methods through Relative Efficiency

Enhancing LLMs for Identifying and Prioritizing Important Medical Jargons from Electronic Health Record Notes Utilizing Data Augmentation: A Comparative Study

KineBench: Benchmarking Embodied World Models via IDM-Free Kinematic Grounding

MoA-Structured Decode Attention DNF Derivation, KV-Cache Accumulation, GQA/MQA, and OpenACC Kernel

Multi-Resolution Voxelized Map-Based Stereo Visual-Inertial Odometry

ReferTrack: Referring Then Tracking for Embodied Visual Tracking

TriAgent: Divergence-Aware Multi-Agent Committees for Cost-Efficient Financial Sentiment Analysis

Incredible

BREAKING: Kimi K3 by @Kimi_Moonshot is 1st overall on 3D Design with an Elo of 1450. This is a 6 position and 108 Elo jump from @Kimi_Moonsh…

Can’t tell if the PR reads more like a security incident or a product release…

Kimi K3 is second only to Fable 5 on AA-Briefcase, our agentic knowledge work benchmark, but costs more than Opus 4.8 to run while averaging…

An Empirical Study on Stage-Information Interfaces for VLA Fine-Tuning

Anatomically Faithful but Temporally Blind: Auditing Attribution for Left-Ventricular Ejection-Fraction Estimation from Echocardiography

CayleyR: Solving the TopSpin puzzle via cycle intersection

Efficient LiDAR Reflectance Compression via Scanning Serialization

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

On the Sublinear Regret of Continuous K-Max Bandits

Post-Disaster Affected Area Segmentation with a Vision Transformer (ViT)-based EVAP Model using Sentinel-2 and Formosat-5 Imagery

RF-Informed Graph Neural Networks for Accurate and Data-Efficient Circuit Performance Prediction