·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning8h◆Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks8h◆Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts8h◆In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning8h◆FrontierChallenge: Evaluating Scientific Workflow Completion8h◆IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier8h◆AgenticGen: Reward-Guided Agentic Video Generation for Advertising8h◆Strangers to Themselves: What Language Models Say About Themselves Is Generic8h◆Omni Interaction Agent Technical Report8h◆CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification8h◆Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability8h◆Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization8h◆RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding8h◆Tracing Computation Density in LLMs8h◆Cultural Binding Heads in Language Models8h◆Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training8h◆Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models8h◆Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning8h◆'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection8h◆DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation8h◆Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning8h◆Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks8h◆Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts8h◆In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning8h◆FrontierChallenge: Evaluating Scientific Workflow Completion8h◆IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier8h◆AgenticGen: Reward-Guided Agentic Video Generation for Advertising8h◆Strangers to Themselves: What Language Models Say About Themselves Is Generic8h◆Omni Interaction Agent Technical Report8h◆CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification8h◆Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability8h◆Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization8h◆RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding8h◆Tracing Computation Density in LLMs8h◆Cultural Binding Heads in Language Models8h◆Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training8h◆Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models8h◆Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning8h◆'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection8h◆DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation8h◆
Tag

#continual-learning

12 articles tagged #continual-learning

arxivJul 24bullish

Adaptive Multi-Horizon Reinforcement Learning

arXiv:2607.20656v1 Announce Type: cross Abstract: Effective decision-making in complex and changing environments requires balancing short-term and long-term consequences. In reinforcement learning (RL), this trade-off is typically controlled through a fixed discount factor, which imposes a single ex

#reinforcement-learning#continual-learning#machine-learningRead on arxiv →
arxivJul 23bullish
HomeModelsNews

OpenEvoShield: Dual Non-Stationary Continual Defense for Open-World Multi-Agent System Attacks

arXiv:2607.19351v1 Announce Type: new Abstract: LLM-based multi-agent systems (LLM-MAS) are increasingly deployed in safety-critical applications, where adversaries inject malicious instructions through inter-agent communication to propagate harmful behaviors. Unlike static threats, these attacks ar

M1M2M34 models · +1#safety#security#continual-learningRead on arxiv →
arxivJul 23bullish

You Live More Than Once: Towards Hierarchical Skill Meta-Evolving

arXiv:2605.28390v2 Announce Type: replace Abstract: Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems. Existing works mainly focus on hard-coded skill evolving strategies or parametric learning that rely on expensive parameter updates in the underlying LLM

#artificial-intelligence#continual-learning#meta-learningRead on arxiv →
arxivJul 23bullish

SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental Learning

arXiv:2607.19384v1 Announce Type: new Abstract: Real-world intelligent systems often require both distributed collaboration across data-isolated clients and continual adaptation to evolving tasks. This setting naturally gives rise to Federated Class Incremental Learning (FCIL), which combines Federa

#federated-learning#continual-learning#multi-task-learningRead on arxiv →
arxivJul 22

Towards Principled Continual Anomaly Detection: A Systematic Framework and Benchmark Scenarios

arXiv:2607.18289v1 Announce Type: cross Abstract: Continual anomaly detection (CAD) studies how models can adapt to evolving data distributions while retaining performance on previously observed regimes. CAD benchmarks, however, depend critically on how tasks are defined, filtered, ordered, and vali

#anomaly-detection#continual-learning#benchmarkRead on arxiv →
arxivJul 16bullish

Hybrid Continual Learning for Low-Resource Australian Aboriginal Language Identification

arXiv:2607.11946v1 Announce Type: new Abstract: Language identification is an important step toward integrating endangered Australian Aboriginal languages (AALs) into speech technologies supporting language revitalisation and digital inclusion. However, extreme data scarcity limits model performance

#language-identification#speech-processing#continual-learningRead on arxiv →
arxivJun 29

Foundation vs. Specialized Models: Evaluating Catastrophic Forgetting in Continual Time Series Forecasting

arXiv:2510.00809v3 Announce Type: replace Abstract: While Time Series Foundation Models (TSFMs) excel in zero-shot tasks, their behavior under continual fine tuning is poorly understood. We present the first systematic study of catastrophic forgetting in TSFMs (TimesFM-2.0, Chronos-2) versus a speci

TICHSA3 models#time-series#continual-learning#catastrophic-forgettingRead on arxiv →
arxivJun 25bullish

Evolving Programmatic Skill Networks

arXiv:2601.03509v2 Announce Type: replace Abstract: We study continual skill acquisition in open-ended embodied environments where an agent must construct, refine, and reuse an expanding library of executable skills. We introduce the Programmatic Skill Network (PSN), a framework in which skills are

PRLA2 models#continual-learning#open-ended-environments#skill-acquisitionRead on arxiv →
arxivJun 20bullish

MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning

arXiv:2506.14990v3 Announce Type: replace Abstract: Benchmarks play a central role in reinforcement learning (RL) research, yet their computational constraints often shape what is studied. Despite the motivation of lifelong learning, most continual RL papers consider only 3-10 sequential tasks, as C

#reinforcement-learning#benchmark#multi-agentRead on arxiv →
arxivJun 16

MAND: Modality-Aware Novelty Detection for Open-World Egocentric Activity Recognition

arXiv:2603.16970v2 Announce Type: replace-cross Abstract: Multimodal egocentric activity recognition integrates visual and inertial cues for robust first-person behavior understanding. However, deploying such systems in open-world environments requires detecting novel activities while continuously l

MA1 model#open-world#continual-learning#multimodalRead on arxiv →
arxivMay 13bullish

MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning

arXiv:2602.07940v3 Announce Type: replace Abstract: To cope with uncertain changes of the external world, intelligent systems must continually learn from complex, evolving environments and respond in real time. This ability, collectively known as general continual learning (GCL), encapsulates practi

ME1 model#continual-learning#pretrained-models#meta-learningRead on arxiv →
arxivApr 10bullish

Information as Structural Alignment: A Dynamical Theory of Continual Learning

arXiv:2604.07108v1 Announce Type: cross Abstract: Catastrophic forgetting is not an engineering failure. It is a mathematical consequence of storing knowledge as global parameter superposition. Existing methods, such as regularization, replay, and frozen subnetworks, add external mechanisms to a sha

STGO2 models#continual-learning#catastrophic-forgetting#machine-learningRead on arxiv →