127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “research”

39,588 results

Research

Neuron-Aware Active Few-Shot Learning for LLMs

DGX agent

arXiv:2607.02423v1 Announce Type: cross Abstract: Active Few-Shot Learning (AFSL) adapts LLMs to specialized domains by identifying the most valuable unlabeled samples for annotation and use as few-sh

researcharxiv-cs-ai

3 Jul 2026

Research

Object-centric LeJEPA

DGX agent

arXiv:2607.02404v1 Announce Type: cross Abstract: Image encoders trained with LeJEPA can deliver strong features for downstream tasks, but, like other image-level self-supervised methods, typically re

Search: “research”

Neuron-Aware Active Few-Shot Learning for LLMs

Object-centric LeJEPA

On the Dimension-Free Approximation of Deep Neural Networks for Symmetric Korobov Functions

On the Role of Directionality in Structural Generalization

One way to live 400 years is to do (and experience) 5x more things per day

Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning

PARTREP: Learning What to Repeat for Decoder-only LLMs

Path planning for unmanned naval surface vehicles

Pmeta-TLA: Backdoor Attacks for Speech Classification Models via Meta-Learning with Timbre Leakage Attack

Population-Based Multi-Objective Training of Discriminators for Semi-Supervised GANs

Predicting Early Stages Of Alzheimer's Disease And Identifying Key Biomarkers Using Deep Artificial Neural Network And Ensemble Of Machine Learning Methodologies

Predictive Conformal Slip Monitoring: An Empirical Evaluation of Rolling Split Conformal Prediction for Pre-Incident Traction Loss Detection

Privacy-Preserving and Verifiable Approximate Distributed Coded Computing

Probing Chemical Language Models: Effects of Pre-training and Fine-tuning

Probing Spectrum-Like Organization of States of Mind in Transformer Representation Spaces

ProWAFT: A ROMA-LPD Instance for Workload-Aware and Dynamic Fault Tolerance in FPGA-Based CNN Accelerators

Q-GAIN: A Python Package for Machine Learning and Physically Informed Analysis Applications

QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs

QuadRocket: An Aerial Robotic Testbed for Adaptive Thrust-Vector Control of Rocket-Like Vehicles

Ravines in quantum cost landscapes: opportunities for improved VQA predictions

ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning

Regularized Variational and Spectral Log-Density-Ratio Estimation in the Gaussian Location Model

Rethinking Complexity Metrics for LLM-Integrated Applications: Beyond Source Code

Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving

Revisiting Chain-of-Thought Reasoning under Limited Supervision: Semi-supervised Chain-of-Thought Learning

Revisiting Decentralized Online Convex Optimization with Compressed Communication

Robust and Explainable 3D Mode Shape Recognition Using Region-Aware Graph Neural Networks

Role-Aware Neural Convex Divergence Heads for Asymmetric Representation Learning

RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules

SA-HGNN: Sample-Adaptive Hyperbolic Graph Neural Network for EEG-Based Depression Recognition

Scalable and Distributed Silhouette Approximation

Scaling Latent Reasoning via Looped Language Models

Scaling to Multimodal and Multichannel Heart Sound Classification with Synthetic and Augmented Biosignals

Scene-Conditioned PINN-GNN for Multipath RF Maps: Cross-Scene Generation and In-Scene Completion

Self-Supervised Test-Time Tuning for Packet Loss Concealment

SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication

Set Diffusion: Interpolating Token Orderings Between Autoregression and Diffusion for Fast and Flexible Decoding

Single-Channel EEG-Based Cognitive Load Assessment in Online Learning: A Hybrid Deep Learning Approach

SPARCLE: SPeaker-aware Aligned Representations via Contrastive Language Embeddings

Spatial Support Matters: Geometry-Aware Graph Fusion for Rainfall Field Reconstruction

Spin-Weighted Spherical Harmonics Enable Complete and Scalable E(3)-Equivariant Networks

Statistical Properties of k-means Clustering for Data Missing Completely at Random

Subliminal Clocks: Latent Time Modelling in Diffusion Language Models

SUNTA: Hierarchical Video Prediction with Surprise-based Chunking

The Download: a smoking “endgame” and a new Elizabeth Bear story

The Dual Nature of LLM Persona: Aggregated Tendencies and Frame-Dependent Geometry

The Grammar Does the Work: Functional vs. Lexical Dependency Length Minimization Across Universal Dependencies

The jobs of the future will require high adaptability and creativity, focusing on complex problem framing rather than repetitive execution o…