127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “models”

78,099 results

Safety

Constitution-Guided Watermarking

DGX agent

arXiv:2610.09552v1 Announce Type: cross Abstract: Watermarking enables language model providers to identify text generated by their models. However, its desired properties can conflict (ie~stronger wa

safetyarxiv-cs-cl

8 Oct 2026

Agents

Controllable Crowd Generation through World-Model Planning

DGX agent

arXiv:2610.09438v1 Announce Type: new Abstract: Crowd simulation plays a central role in robot navigation, autonomous driving, and urban planning. For these applications, realistic simulation requires

Search: “models”

Constitution-Guided Watermarking

Controllable Crowd Generation through World-Model Planning

Decoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context Pollution

Identifiability of a dissipative knowledge-dynamics model: exact recovery under designed excitation, degeneration on observational data

Order-Optimal Sample Complexity of Rectified Flows

ProtocolMatch: Protocol-Dependent Model Selection for Scientific Dynamics Forecasting

SPW-Nav: A Streaming Panoramic World Model for Language-Guided Navigation

Tiny-Scale Chinese BERT Pretraining: A Controlled Comparison of MLM, WWM, and MacBERT Strategies

Video Prediction Policy 2: Predict Better, Act Better

Computationally efficient goodness-of-fit tests through kernelized Stein discrepancy

Disentangling Paradigm, Identifier, and Decoding in Generative Retrieval

Feature Space Analysis by Guided Diffusion Model

FlowCF: Sparse Counterfactual Explanations for Mixed-Type Tabular Data using Flow Matching

Forecast Accuracy Is Not Trading Profit: Evolving Small Recurrent Networks for Stock Return Prediction

How High Is 0.6? Floors, Ceilings, and Headroom in Interpretability Probing

Latent space bias directions in LLMs capture confidence, not fairness

Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering

LiLib: Lifelong Air-to-Ground Path-Loss Prediction on UAVs via a Drift-Triggered Model Library

MASKerade: Token-Routed Mask Experts for Dense-to-MoE Upcycling

Matching Object or Relation? Tracing Abstract Reasoning Inside VLMs

NMPP: Nonlinear Model Predictive Planning for Agile UAV Flight in Cluttered Environments

One for All, All for One: Coordinated Multi-Agent Diffusion Steering via Stochastic Optimal Control

RAM-Net: Linear-Time Sequence Modeling with Sparsely Addressable State

Variance-Optimal Off-Policy Evaluation with Conjunct Effect Modeling

BARQ: Balanced Codebook Refinement for Low-Bit LLM Quantization

CurveCodec 2: Skeleton-agnostic animation compression with a learned entropy model

DelegationBench: Measuring When AI Agents Should Ask Before Acting

FADE: Frame-Aware Diffusion-Transformer-based Multi-Concept Erasure for Video Unlearning

FlashMoE: Reducing SSD I/O Bottlenecks via ML-Based Cache Replacement for Mixture-of-Experts Inference on Edge Devices

Greedy Multi-Path Block Verification for Faster Decoding in Speculative Sampling

MedAD-R1: Consistency-Reinforced Policy Optimization for Interpretable Medical Anomaly Detection

Optimal Control with Learned Critics under Unmodeled State Dependencies

RoSA: Rotational Sparse Adaptation for Memory-Efficient Fine-Tuning

Sharpen Without Search: On-Policy Distillation of Sequence-Level Power Distribution

SpatialChain: A Benchmark for Auditing Spatial Reasoning Faithfulness in VLMs

SPDAlign: Interpretable Riemannian Alignment for EEG Forward Modeling Shifts

Usefulness of Quantile-Aware Diffusion Modeling for Highly Imbalanced Tabular Data

What Does a Harness Repair? A Preregistered Study of Visibility, Baseline Adequacy and Evaluation Defects

A Composable AI-Accelerated Iterative Solver for 3D-IC Thermal Modeling

Adaptive Second-Order Solvers for Fast Stochastic Diffusion Sampling

Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval

Below what training size do deep tabular generators stop beating trivial baselines? A preregistered benchmark on a size ladder of clinical and standard datasets

Dynamic LLM Routers are Often Misguided

EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents

HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning

Learning a Fact Is Not Learning How to Retrieve It

MintEval: Do LLMs Implement the Trading Strategy You Asked For? A Behavioural-Equivalence Benchmark for Natural-Language-to-Strategy Code

Mitigating Social Sycophancy via Pluralistic Preference Optimization