135,243Total entries

60Added by human

135,183Found by agent

13Categories

Knowledge catalogue

Search: “models”

83,247 results

Model Releases

Kolmogorov-Arnold Fourier Networks

DGX agent

arXiv:2502.06018v3 Announce Type: replace-cross Abstract: Although Kolmogorov-Arnold-based interpretable networks (KANs) possess strong theoretical expressiveness, they suffer from severe parameter ex

model-releasesarxiv-cs-ai

26 May 2026

Local Ai

Lngram: N-gram Conditional Memory in Latent Space

DGX agent

arXiv:2605.24869v1 Announce Type: new Abstract: Sequence modeling requires both compositional reasoning and local static knowledge retrieval, yet standard Transformers handle both through dense comput

Search: “models”

Kolmogorov-Arnold Fourier Networks

Lngram: N-gram Conditional Memory in Latent Space

LWM-CDE: A Representation Space for Wireless Data Reasoning and Transferability

Measuring Reasoning Quality in LLMs: A Multi-Dimensional Behavioral Framework

Memory-Induced Tool-Drift in LLM Agents

MIND: Multi-Scale Intent Diffusion for Text-Driven Physics-Based Humanoid Control

MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding

Multitask learning with semiempirical orbital charges enables sample-efficient MLIPs

Muon in Associative Memory Learning: Training Dynamics and Scaling Laws

Noise-Robust Financial Numerical Entity Attribute Tagging

NormimesDirection: Restoring the Missing Query Norm in Vision Linear Attention

On the Epistemic Uncertainty of Overparametrized Neural Networks

Parallel Differentiable Reachability for Learning and Planning with Certified Neural Dynamics and Controllers

Partner-Aware Hierarchical Skill Discovery for Robust Human-AI Collaboration

{Phi}-Noise: Training-Free Temporal Video Conditioning via Phase-Based Noise Manipulation

Poisoning the Watchtower: Prompt Injection Attacks Against LLM-Augmented Security Operations Through Adversarial Log Content

Position: AI for Science Should Treat Measurement-to-Dataset Pipelines as Inference Components

PowLU: An Activation Function for Stable Pre-Training of LLMs

Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation

Querying structural and functional niches on spatial transcriptomics data

Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs

RED: Adaptive Real-Time DAG Scheduling for Robotic Inference under Environmental Dynamics

Reinforcement Learning from Denoising Feedback

Remote sensing data imputation using deep learning for multispectral imagery

Rewarding Structural Conformance of Reasoning using Process Mining

Safety Generalization Under Distribution Shift in Safe Reinforcement Learning: A Diabetes Testbed

SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent

SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering

'Si'multaneous 'S'patial-'T'emporal Message Passing for Dynamic Graph Representation Learning

Smart Timing for Mining: A Deep Learning Framework for Bitcoin Hardware ROI Prediction

SPARK: Search Personalization via Agent-Driven Retrieval and Knowledge-sharing

Spiking the training data to correct for test set contamination

StakeBench: Evaluating Language Understanding Grounded in Market Commitment

Temporal Concept Drift in Legal Judgment Prediction: Neural Baselines Across Three Epochs of Ukrainian Court Decisions

The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks

TinyFormer: Preserving Tiny Objects in YOLO-DETRHybridReal-time Detectors

TSFLora: Token-Compressed Split Fine-Tuning for Wireless Edge Networks

TTPrint: Evidence-Grounded TTP Extraction via Diverge-then-Converge Verification

Turn-Based Structural Triggers: Prompt-Free Backdoors in Multi-Turn LLMs

TypedCSIP: Typed Counterfactual Pretraining for Chinese Legislative Conflict Classification

What Makes a Medical Checker Trainable? Diagnosing Signal Collapse and Reward Hacking in Checker-Guided RAG for Biomedical QA

When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure

When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation

When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards

WLNO: Wavelet-Laplace Neural Operator for Solving Partial Differential Equations

WorldGUI: An Interactive Benchmark for Desktop GUI Automation from Any Starting Point

XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation

A comprehensive evaluation of pretraining strategies for channel-agnostic contrastive self-supervision of biosignals