Formalizes continual model routing (CMR), releases CMRBench with over 2000 models, and presents CARvE which outperforms retrieval, fine-tuning and adapter-merging baselines on model/family/domain accuracy.
hub
Continual lifelong learning with neural networks: A review
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
representative citing papers
Formalizes Reasoning Portability (RP) and proposes RDB-CL to modulate per-sample KL regularization in RLVR for MLLM continual learning, achieving +12.0% Last accuracy over vanilla RLVR baseline by preserving reusable reasoning on high-RP samples.
LoRA adapters should be scaled by 1/sqrt(rank) rather than 1/rank to stabilize learning and enable effective use of higher ranks during fine-tuning of large language models.
A deterministic episodic-to-semantic consolidation function with a structural lemma proving identity invariance, demonstrated in synthetic experiments on an embodied service agent.
Heuresis evaluates six search strategies for autonomous ML research agents and finds that novel ideas are rare, none rated original, and only one reaches top-10 quality while strategies steer axes but do not expand the quality-novelty frontier.
Silent collapse in recursive learning contracts internal distributions like entropy and diversity despite stable metrics, preceded by three precursors that enable the MTR monitoring framework to intervene early.
Task-aligned supervised geometric stability predicts linear steerability with high accuracy while unsupervised stability detects representational drift earlier and with lower false alarms than CKA or Procrustes.
Proposes a self-evolving cognitive framework integrating causal world modeling, intervention-driven reasoning, and continual refinement for embodied scientific intelligence.
C2FL proposes spatial clustering plus continual learning techniques inside federated learning to maintain performance under combined spatial heterogeneity and temporal drift.
SF-NorMuon is a new schedule-free spectral optimizer that closes the gap with tuned AdamW on 125M-772M parameter models across 1-8x Chinchilla horizons while providing stationarity guarantees.
IEFF enables retrain-free feature efficiency rollouts in ranking systems by elastically controlling feature coverage at serving time, achieving 5x faster rollouts, zero retraining GPU cost, and 50-55% less performance degradation than abrupt feature removal.
Proposes LoRA-based mixture-of-experts with autoencoder routing for continual bidirectional motion-language learning, reporting near-zero forgetting on a 5-task HumanML3D benchmark derived via semantic clustering.
RIZZ is a continual adaptation framework for black-box LLM agents that uses dynamically spawned memory branches, context-aware routing, verifier-gated updates, and prompt compilation to control interference across nonstationary inputs.
citing papers explorer
-
Continual Model Routing in Evolving Model Hubs
Formalizes continual model routing (CMR), releases CMRBench with over 2000 models, and presents CARvE which outperforms retrieval, fine-tuning and adapter-merging baselines on model/family/domain accuracy.
-
Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era
Formalizes Reasoning Portability (RP) and proposes RDB-CL to modulate per-sample KL regularization in RLVR for MLLM continual learning, achieving +12.0% Last accuracy over vanilla RLVR baseline by preserving reusable reasoning on high-RP samples.
-
A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA
LoRA adapters should be scaled by 1/sqrt(rank) rather than 1/rank to stabilize learning and enable effective use of higher ranks during fine-tuning of large language models.
-
Episodic-to-Semantic Consolidation Without Identity Drift
A deterministic episodic-to-semantic consolidation function with a structural lemma proving identity invariance, demonstrated in synthetic experiments on an embodied service agent.
-
Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty
Heuresis evaluates six search strategies for autonomous ML research agents and finds that novel ideas are rare, none rated original, and only one reaches top-10 quality while strategies steer axes but do not expand the quality-novelty frontier.
-
Silent Collapse in Recursive Learning Systems
Silent collapse in recursive learning contracts internal distributions like entropy and diversity despite stable metrics, preceded by three precursors that enable the MTR monitoring framework to intervene early.
-
The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability
Task-aligned supervised geometric stability predicts linear steerability with high accuracy while unsupervised stability detects representational drift earlier and with lower false alarms than CKA or Procrustes.
-
Self-Evolving Cognitive Framework via Causal World Modeling for Embodied Scientific Intelligence
Proposes a self-evolving cognitive framework integrating causal world modeling, intervention-driven reasoning, and continual refinement for embodied scientific intelligence.
-
C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift
C2FL proposes spatial clustering plus continual learning techniques inside federated learning to maintain performance under combined spatial heterogeneity and temporal drift.
-
Anytime Training with Schedule-Free Spectral Optimization
SF-NorMuon is a new schedule-free spectral optimizer that closes the gap with tuned AdamW on 125M-772M parameter models across 1-8x Chinchilla horizons while providing stationarity guarantees.
-
Intelligent Elastic Feature Fading: Enabling Model Retrain-Free Feature Efficiency Rollouts at Scale
IEFF enables retrain-free feature efficiency rollouts in ranking systems by elastically controlling feature coverage at serving time, achieving 5x faster rollouts, zero retraining GPU cost, and 50-55% less performance degradation than abrupt feature removal.
-
Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation
Proposes LoRA-based mixture-of-experts with autoencoder routing for continual bidirectional motion-language learning, reporting near-zero forgetting on a 5-task HumanML3D benchmark derived via semantic clustering.
-
RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box Agents
RIZZ is a continual adaptation framework for black-box LLM agents that uses dynamically spawned memory branches, context-aware routing, verifier-gated updates, and prompt compilation to control interference across nonstationary inputs.