127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “research”

39,575 results

Research

Disentangling Steering Vectors

DGX agent

arXiv:2609.07037v1 Announce Type: new Abstract: Activation steering has emerged as a lightweight, inference-time approach to control the behavior of Large Language Models (LLMs). However, traditional

researcharxiv-cs-lg

9 Sept 2026

Research

Distribution-free inference on the number of changepoints

DGX agent

arXiv:2609.08234v1 Announce Type: cross Abstract: Suppose we are given an ordered sequence of independent data whose distribution changes K times at unknown locations, for some unknown K geq 0. In thi

Search: “research”

Disentangling Steering Vectors

Distribution-free inference on the number of changepoints

DL^3M: A Vision-to-Language Framework for Expert-Level Medical Reasoning through Deep Learning and Large Language Models

Do Reasoning Representations Help Humans Evaluate LLM Outputs?

Dreaming in Flow: Generative Grounding Feedback for Self-Evolving Unified Multimodal Models

DRIFT: Removing Diffusion Watermarks by Deflecting the Generative Trajectory

DrugReason: Dynamic Multi-View Reasoning over Knowledge Graph and Language Evidence for Drug Repurposing

Dynamic-Programming-Guided Hierarchical BPE and Empirical Analysis of Vocabulary Pruning

Dynamical stability for dense patterns in attractor neural networks

ECHO: Dyadic 3D Facial Motion Generation with Asymmetric Deterministic Articulation and Stochastic Reaction

ECOKV: Geometry-Aware KV Cache Eviction via Complementary Diversity Metrics

Effects of model architecture and learning strategies on deep learning-based recognition of activated sludge microscopic images and comparison with quantitative image analysis

Efficient Learning and Symmetry Discovery under Exact Invariances

EigenLI: Spectral Approximations to Late Interaction

EMBLEM: Enhancing Multi-script Table Detection through Masking

EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models

Equivariance Breaks the Learning Rate

FaceLinkGen: A Re-evaluation of Identity Leakage in Privacy-Preserving Face Recognition and Face Anonymization Systems Using Simple Distillation

Fast PAC Global Optimization via Restarted Langevin: Exploration, Exploitation, and Degenerate Cooling

Feature Superposition in Neural Networks: From Theory to Practice

Federated Binary Gating with Server-Side Vision-Language Inference for Surveillance Anomaly Classification

FedGenSC: Federated Generative Semantic Communication with Channel-Aware Adaptation

FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction

Fine-grained Distributed Backdoor Attacks in Federated Learning

Fine-Grained Visual Preprocessing and Dual-Stream Temporal Modeling for Multimodal Sentiment Analysis on Social Media

FineHOI: Part-Aware Dense Representations for Zero-Shot Human-Object Interaction Detection

FIRE3D: Feed-forward Interactive 3D Scene Reconstruction Within A Minute

Fitting and Learning Basis-Restricted Propositional Formulas

Flexible Motion Generation from Language and Style References

Flexible Spectral-Normalized Neural Gaussian Process for Dynamic Aperture Prediction

Forecasting the Winner of a Live Tennis Match

Formal Bayesian Transfer Learning via the Total Risk Prior

Formation of structural attractors in neuromorphic systems

FRAME: Factored Retrieval via Attribute Readouts for Object-Centric Scene Memory

FreqDoor: A Hidden Trojan in the Frequency Domain for Backdoor Attacks on Vision-Language Models

From Explicit References to Scene Manifolds: Distributional Fidelity and Realism for Radiance Field Quality Assessment

From Human Labels to Literature: Semi-Supervised Learning of NMR Chemical Shifts at Scale

From Where to How: Continuous 4D Interaction Forecasting from Egocentric Video

FSAN: Flow State Attention Network for Aerodynamic Prediction

Full-Page Optical Music Recognition of Handwritten Monophonic Scores

GAN-Blot: A Controllable Structure-Style Synthesis Benchmark for Western Blot Forensics

Generalist Open-World Temporal Perception

Geometry-Aware Test-Time Learning for Quantitative Spatial Reasoning

GIFT: Reconciling Post-Training Objectives via Variational Finite-Temperature Gibbs Initialization

Graph neural networks and the energetic cavity method for combinatorial optimization

GraphFAS: A Distributed System for Automated Graph Feature Generation and Selection in Industrial Transaction Networks

GraphNOSE: A Graph Transformer in Olfaction

Great study on what actually predicts vibe-coding ability. 100 tertiary-level students completed measures of computer-science achievement, d…