{"total":12,"items":[{"citing_arxiv_id":"2605.13162","ref_index":28,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Continual Fine-Tuning of Large Language Models via Program Memory","primary_cat":"cs.LG","submitted_at":"2026-05-13T08:26:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ProCL organizes LoRA adapters into input-conditioned program memory slots that combine with a distributed adapter to improve retention and reduce forgetting in continual LLM fine-tuning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12998","ref_index":5,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"\\emph{DRIFT}: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts","primary_cat":"cs.LG","submitted_at":"2026-05-13T04:54:46+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"DRIFT is a benchmark for task-free continual graph learning under continuous distribution shifts, demonstrating that standard methods degrade without task boundary information.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12306","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"KAN-CL: Per-Knot Importance Regularization for Continual Learning with Kolmogorov-Arnold Networks","primary_cat":"cs.LG","submitted_at":"2026-05-12T15:55:09+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"KAN-CL cuts catastrophic forgetting by 88-93% on Split-CIFAR-10/5T and Split-CIFAR-100/10T by anchoring KAN parameters at per-knot granularity while matching baseline accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11742","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Online Continual Learning with Dynamic Label Hierarchies","primary_cat":"cs.LG","submitted_at":"2026-05-12T08:20:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"HALO improves online continual learning under evolving label hierarchies by adaptively combining classification heads regularized with organized learnable prototypes for better adaptation and reduced forgetting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11617","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound","primary_cat":"cs.LG","submitted_at":"2026-05-12T06:45:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"MIST fixes unreliable splits in streaming decision trees for class-incremental learning by using a K-independent McDiarmid bound on Gini impurity, Bayesian moment projection for knowledge transfer, and KLL quantile sketches for adaptive leaf predictions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05776","ref_index":92,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning","primary_cat":"cs.AI","submitted_at":"2026-05-07T07:09:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"HEDP uses energy regularization inspired by Helmholtz free energy plus hybrid energy-distance weighting in prompts to improve domain selection and achieve a 2.57% accuracy gain on benchmarks like CORe50 while mitigating catastrophic forgetting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05738","ref_index":41,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CoMemNet: Contrastive Sampling with Memory Replay Network for Continual Traffic Prediction","primary_cat":"cs.LG","submitted_at":"2026-05-07T06:29:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"CoMemNet is a dual-branch continual learning model for dynamic traffic networks that combines contrastive sampling via Wasserstein features and memory replay to achieve SOTA performance while mitigating forgetting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.14259","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Continual Learning for fMRI-Based Brain Disorder Diagnosis via Functional Connectivity Matrices Generative Replay","primary_cat":"q-bio.TO","submitted_at":"2026-04-15T16:08:52+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A structure-aware VAE generates realistic FC matrices for replay, combined with multi-level knowledge distillation and hierarchical contextual bandit sampling, to enable continual fMRI-based brain disorder diagnosis across sequentially arriving multi-site data without catastrophic forgetting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12941","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Direct Discrepancy Replay: Distribution-Discrepancy Condensation and Manifold-Consistent Replay for Continual Face Forgery Detection","primary_cat":"cs.CV","submitted_at":"2026-04-14T16:35:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A replay method for continual face forgery detection condenses real-fake distribution discrepancies into compact maps and synthesizes compatible samples from current real faces to reduce forgetting under tight memory budgets without storing historical images.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08159","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Face-D(^2)CL: Multi-Domain Synergistic Representation with Dual Continual Learning for Facial DeepFake Detection","primary_cat":"cs.CV","submitted_at":"2026-04-09T12:18:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Face-D²CL fuses spatial and frequency features and uses dual continual learning to reduce forgetting while adapting to new DeepFakes, cutting average error rates by 60.7% and raising unseen-domain AUC by 7.9% over prior SOTA.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.07399","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge","primary_cat":"cs.LG","submitted_at":"2026-04-08T09:16:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CPS-Prompt delivers 1.6x gains in peak memory, training time, and energy on edge hardware for continual learning while staying within 2% accuracy of top prompt-based baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2306.03310","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","primary_cat":"cs.AI","submitted_at":"2023-06-05T23:32:26+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"LIBERO is a new benchmark for lifelong robot learning that evaluates transfer of declarative, procedural, and mixed knowledge across 130 manipulation tasks with provided demonstration data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}