127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “benchmark”

32,705 results

Research

Switching Linear Attention

DGX agent

arXiv:2609.39034v1 Announce Type: cross Abstract: Designing expressive sequence layers with efficient inference remains a central challenge in modern machine learning. Standard softmax attention achie

researcharxiv-cs-ai

1 Oct 2026

Research

SynIL: Leveraging Synergy for Offline Imitation Learning from Imperfect Demonstration Datasets

DGX agent

Search: “benchmark”

Switching Linear Attention

SynIL: Leveraging Synergy for Offline Imitation Learning from Imperfect Demonstration Datasets

Synthesis Without Training: An Inference-Only Pipeline for Tabular, Temporal, and Relational Synthetic Data

Taming Speculative Search for Test-Time Scaling in LLM Serving

TERRA: Terrain-Aware Reconstruction, Retargeting and Control for Musculoskeletal Locomotion

TexTailor: Texture-Preserving Video Virtual Try-On via Adaptive Garment Conditioning

The critical distinction between base LLMs (2024 and earlier) and modern LRMs is not symbolic tool use. It's the switch from a transductive …

TopTimeNet: Topologically-assisted time-series classification model

Towards Agile Vision-Based Multi-UAV Flight: Revisiting State Estimation

Towards Better Exploration in Sequential Test-Time Scaling

Towards Universal Wasserstein Barycenters through Flow Matching

TRACE: Trajectory Selection for Parallel Scaling of Search Agents

Tri-Info: Generalizable, Interpretable Failure Prediction for VLA Models via Information Theory

TripleFlow: Training-Free Video Object Removal by Bridging Residual Editing and Native Generation

TSGL: Teacher-Student Graph Learning for 3DGS Compression

Turbo Harness: Instance-Adaptive Harness Optimization

UBTree: Parallel Tree Drafting via Unigram and Bigram Models for Speculative Decoding

UniAE-MoE: A Unified Audio Encoder via Mixture of Experts

UniST-Pred: A Robust Unified Framework for Spatio-Temporal Traffic Forecasting in Transportation Networks Under Disruptions

UniWAM Technical Report: Unified Mobile Manipulation via Mixed-Stream World-Action Modeling and Manipulation Anchor Pose Supervision

Unlearning Deceptive Behaviors in LLMs with Contrastive Forget Sets

VidHarness: Evolving Agent Harnesses for Cost-Efficient Long Video Understanding

Wavelet Flow Matching for Time Series

When Context Changes: Understanding Update Failures in LLMs

When Masking Helps or Hurts Robustness in Compressed CLIP: A Pre-Deployment Diagnostic

When, Not How Much: Evaluating Time-Series Foundation Models on Sparse Events

Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure Diagnosis

Where Scientific Search Agents Fail: Decision-Checkpoint Auditing of Exposure and Inspection Attempts

Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection

Whitening Improves Robustness to Spurious Correlations in Linear Probes

Yggdrasil: a Layer-First 3D Scene Graph for Real-Time Querying

A Character-Level Neural Approach to Sinhala Sandhi Splitting

A Comprehensive View of Fairness through Distributional Stability

A Digital Simulation Toolkit for Physics-Based Generation of Realistic Experimental Scanning Tunneling Microscopy Images

A Dual-Track Curation-and-Classification Framework for Resolving Ground-Truth Label Noise in Operational Sentinel-2 Wheat Area Estimation

A Model-Agnostic Physics-Guided Adapter for Few-Shot Transfer of Coastal Flood Prediction Models to Unseen Regions

Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics

ActiveSAM: Fast and Accurate Open-Vocabulary Semantic Segmentation with Frozen SAM 3

Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations

AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Research

Adversarial Debiasing of Machine Learning Models for Enhanced Network Security against DDoS Attacks

AeroManip-VLA: Scalable Vision-Language-Action Learning for Aerial Manipulation with RL-Generated Demonstrations

Agentic AI for Scalable and Robust Optical Systems Control

Agentic Commerce Bench: Measuring Fraud Detection for Agents That Spend Money

Alignment Forecasting: Predicting Misalignment From Training Data

Alpha Diffusion Language Models: Factorization Alone Is Not the Problem

Anatomy-Aware Prediction of Bronchoscopic Accessibility from 3D CT

AnyAct: Universal Action for Self-Evolving Agents