Skip to content
Slow Variables

Ask the data

Answers come from the same store as the site; every number is checked against the record it cites.

Indicators / series

watch.arxiv_continual_feed.continual_learning.pt

Source: arXiv query feed - continual learning (watchlist) (arXiv) · arXiv API terms · CSV

arXiv

idtextgradeas of datepublished datetieraudited vs reportedextraction methodreview statusretrieved athttp statuscontent hashsupersedes idurlflags
bdb125d064c0271bWhat Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selectiongrade B, evidence tier 62026-09-042026-09-046reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
acaf9467ddffd7aeDistill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendationgrade B, evidence tier 62026-09-042026-09-046reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
72755c13a8f03879MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learninggrade B, evidence tier 62026-09-042026-09-046reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
33c2e9814d0efd43RISE: Recursive Improvement via Self-Extrapolating Policy Distillationgrade B, evidence tier 62026-09-042026-09-046reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
2e541cff79bc9b03ViT3Flow: A Test-Time Training Transformer MeanFlow for Postoperative Radiograph Synthesis in Scoliosisgrade B, evidence tier 62026-09-042026-09-046reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
9672848d0605f726Unifying ICL, SFT, KL-Regularized RL Through a Bayesian Lensgrade B, evidence tier 62026-09-042026-09-046reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
383fe579fa704670KanAdapter: A Kolmogorov-Arnold Network-based Plug-and-Play Module for Efficient Fine-tuning of Foundation Speech Modelsgrade B, evidence tier 62026-09-042026-09-046reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
7d54b26b31651c97Selective Knowledge Control for Continual GUI Agent Learning over Application Streamsgrade B, evidence tier 62026-09-062026-09-066reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
add950553f56b072Robust Dynamic Expansion for Continual Learning under Backdoor Attacks via Purification and Selective Recoverygrade B, evidence tier 62026-09-062026-09-066reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
92a1d453281b6bccOracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolutiongrade B, evidence tier 62026-09-062026-09-066reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
d12fd0beadeeda01Continual Learning Mechanisms Compose for Long-Horizon Memorizationgrade B, evidence tier 62026-09-072026-09-076reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
08ea8351916c425dNeuCME: Toward Dynamic Multimodal Continual Learning via Neural Combinatorics of Multiple Expertsgrade B, evidence tier 62026-09-072026-09-076reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
eb2c75cff6213bfbRevisiting Complete Reasoning Traces for Post-Traininggrade B, evidence tier 62026-09-072026-09-076reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
c235cc7a30b0a848Flow3D-OPD: Multi-Teacher On-Policy Distillation for 3D Geometry Generation with Flow-Matching Diffusion Transformergrade B, evidence tier 62026-09-072026-09-076reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
689224e5201c7e64TASTE: Throughput-Aware Batch Size Tuning for On-Device Edge Learninggrade B, evidence tier 62026-09-072026-09-076reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
11c121d69a879a7cWorldAgen: Unified State-Action Prediction with Test-Time World Model Traininggrade B, evidence tier 62026-09-082026-09-086reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
b60a739dbd9f0a48TV-Regulated OPD: Direction Matters in On-Policy Distillationgrade B, evidence tier 62026-09-082026-09-086reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
b9d95f2f699756b1Miles v0.1: Production-Level Post-Traininggrade B, evidence tier 62026-09-082026-09-086reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
9e69c282d4aac123NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harnessgrade B, evidence tier 62026-09-082026-09-086reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
76dcfdb32d0ce76cVideo-MOPD: Multi-Teacher On-Policy Distillation for Video Understandinggrade B, evidence tier 62026-09-082026-09-086reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
afd83dffe368ea97Distillation as Probability Transport: Routed On-Policy Distillationgrade B, evidence tier 62026-09-082026-09-086reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
5f3fc006bbe34936LeCor: Learning to Be Corrected by Meta-Learned Test-Time Training for Interactive 3D Lung-Tumour Segmentationgrade B, evidence tier 62026-09-082026-09-086reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
d7142dff06ecf74cOn-Policy Distillation for Vision-Language Model Adaptation, an Effective Paradigm on Low-Quality Multimodal Datagrade B, evidence tier 62026-09-092026-09-096reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
f7eeb6c5ffc25e19CompassOPD: Cross-Family On-Policy Distillation via Within-Family Likelihood Shiftsgrade B, evidence tier 62026-09-092026-09-096reportedapiapproved2026-09-10T10:45:27.508803Z200984b86555383—source page
Raw snippets and dispute text
  • bdb125d064c0271b What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection
  • acaf9467ddffd7ae Distill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendation
  • 72755c13a8f03879 MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning
  • 33c2e9814d0efd43 RISE: Recursive Improvement via Self-Extrapolating Policy Distillation
  • 2e541cff79bc9b03 ViT3Flow: A Test-Time Training Transformer MeanFlow for Postoperative Radiograph Synthesis in Scoliosis
  • 9672848d0605f726 Unifying ICL, SFT, KL-Regularized RL Through a Bayesian Lens
  • 383fe579fa704670 KanAdapter: A Kolmogorov-Arnold Network-based Plug-and-Play Module for Efficient Fine-tuning of Foundation Speech Models
  • 7d54b26b31651c97 Selective Knowledge Control for Continual GUI Agent Learning over Application Streams
  • add950553f56b072 Robust Dynamic Expansion for Continual Learning under Backdoor Attacks via Purification and Selective Recovery
  • 92a1d453281b6bcc OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution
  • d12fd0beadeeda01 Continual Learning Mechanisms Compose for Long-Horizon Memorization
  • 08ea8351916c425d NeuCME: Toward Dynamic Multimodal Continual Learning via Neural Combinatorics of Multiple Experts
  • eb2c75cff6213bfb Revisiting Complete Reasoning Traces for Post-Training
  • c235cc7a30b0a848 Flow3D-OPD: Multi-Teacher On-Policy Distillation for 3D Geometry Generation with Flow-Matching Diffusion Transformer
  • 689224e5201c7e64 TASTE: Throughput-Aware Batch Size Tuning for On-Device Edge Learning
  • 11c121d69a879a7c WorldAgen: Unified State-Action Prediction with Test-Time World Model Training
  • b60a739dbd9f0a48 TV-Regulated OPD: Direction Matters in On-Policy Distillation
  • b9d95f2f699756b1 Miles v0.1: Production-Level Post-Training
  • 9e69c282d4aac123 NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
  • 76dcfdb32d0ce76c Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding
  • afd83dffe368ea97 Distillation as Probability Transport: Routed On-Policy Distillation
  • 5f3fc006bbe34936 LeCor: Learning to Be Corrected by Meta-Learned Test-Time Training for Interactive 3D Lung-Tumour Segmentation
  • d7142dff06ecf74c On-Policy Distillation for Vision-Language Model Adaptation, an Effective Paradigm on Low-Quality Multimodal Data
  • f7eeb6c5ffc25e19 CompassOPD: Cross-Family On-Policy Distillation via Within-Family Likelihood Shifts