127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

All entries

127,604 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

Tutorials

Synchronous Multi-view Neural Diffusion

DGX agent

arXiv:2609.39019v1 Announce Type: new Abstract: Multi-view learning seeks to learn more comprehensive representations by exploiting the complementarity and consistency across diverse modalities or vie

All entries

Switching Linear Attention

Synchronous Multi-view Neural Diffusion

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

Synthetic Data Characterization via Training Dynamics

Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior

Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies

szmcp: a ZIM HTML to Markdown converter and yet another ZIM MCP server

T-ARC: Topology-Aware Randomized Clustering via Distributionally Robust Stochastic Block Models

T-Router: Learning Thalamic Routing for Reasoning with Parameter-Efficient Reinforcement Learning

TACIT: Optimization Models that Learn from Their Mistakes

Tacit-TTS: From Autoregressive Decoding to Masked Prediction for Efficient Transcript-Free Voice Cloning

TACTIC: Temporal and Context-Aware LLM Tactical Planning for Roadside LiDAR Attacks

Tactile Curiosity Drives Robot Interaction

TAGGRAPH: Tag-Augmented Graphs for Graph Retrieval of Agent Persistent Histories

Taipan: A Query-free Transfer-based Multiple Sensitive Attribute Inference Attack Solely from Auxiliary Graphs

TALK-Dem: Benchmarking Embodied Task Planning under Dementia-Associated Communication Patterns

Talk2Agent: Benchmarking Voice Interfaces for Text Agents

Taming Speculative Search for Test-Time Scaling in LLM Serving

Targeted Retrieval, Compact Representations: How CoT Reasoning Improves Long-Context Counting

Team MSU GenText-Forensics Challenge 2026 Technical Report

TED:Text-Axis Evidence Decomposition for Prompted Anomaly Localization

Template-Search Domain Adaptation via Multi-Stage Feature Alignment for Cross-Modal Object Tracking

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

Text-to-3D Policy: Fine-Grained Language-Behavior Alignment for Unseen Specification Generalization

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

The Advantages of Fresh Sketching for Ridge Regression

The Backdrop Exposes What the World Around an Agent Costs It

The Concrete-Arbitrary Gap: Kinship Reasoning in LLMs Is Not Indifferent to Presentation

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

The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends

The future of browser-based security: Leveraging browser data for proactive defense

The Geometry of Harmfulness in Multi-Turn Attacks

The Geometry of Randomized Smoothing on Feasible Sets

The Golden Path Hypothesis: Reusable Schedules in Diffusion Caching

The Invisible Language Tax: Token Premiums of French and Regional Languages in 2026 LLM Tokenizers, and a French-Optimized Prototype

The Missing Coefficients: Bayesian Pairwise Merging for Model Personalization

The Nixtlaverse: An Open-Source Ecosystem for Forecasting

The Planning Limits of Latent World Models

The Row Normalization Puzzle in Muon

The System Prompt Illusion: How Instruction Preambles Modify Computation in Language Models

Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression

Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?

ThinkV2V: Unleashing the Reasoning Capability of MLLMs for Instruction-Guided Video Editing

This is impressive! Face-to-face conversation is where AI interfaces are heading. @tavus gave me early access to Griffin, a video-to-video m…

Time-adaptive infinite-dimensional Gaussian process regression on manifolds

Tissue Detection Determines False Positives in Diffusion-Based Histopathology Artifact Detection

To clarify: this was satire. I wasn’t fired from OpenAI. The underlying issue is serious: how do we independently verify AI-generated code, …