{"total":99,"rows":[{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2601.03192","title":"MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory","created":"2026-01-06","cited_by_count":129,"area":"lr"},{"id":"2508.16153","title":"Memento: Fine-tuning LLM Agents without Fine-tuning LLMs","created":"2025-08-22","cited_by_count":127,"area":"agents"},{"id":"2406.06391","title":"Towards Lifelong Learning of Large Language Models: A Survey","created":"2024-06-10","cited_by_count":64,"area":null},{"id":"2505.02486","title":"SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning","created":"2025-05-05","cited_by_count":33,"area":"mllm"},{"id":"2509.12235","title":"RL Fine-Tuning Heals OOD Forgetting in SFT","created":"2025-09-08","cited_by_count":31,"area":"lr"},{"id":"2502.19735","title":"R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning","created":"2025-02-27","cited_by_count":21,"area":"lr"},{"id":"2601.18510","title":"Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates","created":"2026-01-26","cited_by_count":19,"area":"agents"},{"id":"2511.01571","title":"PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model","created":"2025-11-03","cited_by_count":18,"area":"vla"},{"id":"2510.24702","title":"Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents","created":"2025-10-28","cited_by_count":17,"area":"agents"},{"id":"2502.17510","title":"Recurrent Knowledge Identification and Fusion for Language Model Continual Learning","created":"2025-02-22","cited_by_count":15,"area":null},{"id":"2603.21383","title":"PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost","created":"2026-03-22","cited_by_count":14,"area":"agents"},{"id":"2510.14865","title":"Midtraining Bridges Pretraining and Posttraining Distributions","created":"2025-10-16","cited_by_count":12,"area":null},{"id":"2503.21056","title":"Online Reasoning Video Segmentation with Just-in-Time Digital Twins","created":"2025-03-27","cited_by_count":11,"area":"lr"},{"id":"2510.02833","title":"Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs","created":"2025-10-03","cited_by_count":10,"area":"alignment"},{"id":"2512.18671","title":"SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse","created":"2025-12-21","cited_by_count":9,"area":null},{"id":"2406.14026","title":"Demystifying Language Model Forgetting with Low-rank Example Associations","created":"2024-06-20","cited_by_count":8,"area":null},{"id":"2601.03938","title":"FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning","created":"2026-01-07","cited_by_count":8,"area":null},{"id":"2604.14090","title":"From Weights to Activations: Is Steering the Next Frontier of Adaptation?","created":"2026-04-15","cited_by_count":8,"area":null},{"id":"2503.19041","title":"LookAhead Tuning: Safer Language Models via Partial Answer Previews","created":"2025-03-24","cited_by_count":7,"area":"alignment"},{"id":"2605.10468","title":"Can Muon Fine-tune Adam-Pretrained Models?","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2506.17442","title":"Keeping Medical AI Healthy and Trustworthy: A Review of Detection and Correction Methods for System Degradation","created":"2025-06-20","cited_by_count":6,"area":null},{"id":"2604.13627","title":"(How) Learning Rates Regulate Catastrophic Overtraining","created":"2026-04-15","cited_by_count":6,"area":null},{"id":"2509.17348","title":"AIMMerging: Adaptive Iterative Model Merging Using Training Trajectories for Language Model Continual Learning","created":"2025-09-22","cited_by_count":5,"area":null},{"id":"2511.20104","title":"The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs","created":"2025-11-25","cited_by_count":5,"area":null},{"id":"2602.21035","title":"Not Just What's There: Enabling CLIP to Comprehend Negated Visual Descriptions Without Fine-tuning","created":"2026-02-24","cited_by_count":5,"area":"mllm"},{"id":"2605.05676","title":"Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2506.05695","title":"Being Strong Progressively! Enhancing Knowledge Distillation of Large Language Models through a Curriculum Learning Framework","created":"2025-06-06","cited_by_count":4,"area":"distill"},{"id":"2509.24675","title":"Understanding the Dilemma of Unlearning for Large Language Models","created":"2025-09-29","cited_by_count":4,"area":"safety"},{"id":"2511.13368","title":"Donors and Recipients: On Asymmetric Transfer Across Tasks and Languages with Parameter-Efficient Fine-Tuning","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2601.19752","title":"Agentic Design Patterns: A System-Theoretic Framework","created":"2026-01-27","cited_by_count":4,"area":"agents"},{"id":"2604.05096","title":"RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real World","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2606.09659","title":"End-to-End Context Compression at Scale","created":"2026-06-08","cited_by_count":4,"area":"inference"},{"id":"2410.17714","title":"CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2412.04503","title":"A Primer on Large Language Models and their Limitations","created":"2024-12-03","cited_by_count":3,"area":null},{"id":"2601.09278","title":"M$^3$Searcher: Modular Multimodal Information Seeking Agency with Retrieval-Oriented Reasoning","created":"2026-01-14","cited_by_count":3,"area":null},{"id":"2603.06610","title":"CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2604.17078","title":"Understanding and Enforcing Weight Disentanglement in Task Arithmetic","created":"2026-04-18","cited_by_count":3,"area":null},{"id":"2606.16100","title":"Your \"Pro\" LLM Subscription May Actually Be \"Free\": Exposing Fingerprint Spoofing Risks in LLM Inference Services","created":"2026-06-15","cited_by_count":3,"area":null},{"id":"2607.25614","title":"MemSFT: Mitigating Alignment Tax with an External Parametric Memory","created":"2026-07-28","cited_by_count":3,"area":"alignment"},{"id":"2505.22120","title":"LoKI: Low-damage Knowledge Implanting of Large Language Models","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2510.00034","title":"Review of Hallucination Understanding in Large Language and Vision Models","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2510.26253","title":"Pragmatic Theories Enhance Understanding of Implied Meanings in LLMs","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2512.22337","title":"The Effectiveness of Approximate Regularized Replay for Efficient Supervised Fine-Tuning of Large Language Models","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2604.24222","title":"Learning from Execution: Self-Evolving Memory for Private-Library Code Generation","created":"2026-04-27","cited_by_count":2,"area":"rag"},{"id":"2607.19604","title":"Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2412.14436","title":"ORBIT: Cost-Effective Dataset Curation for Large Language Model Domain Adaptation with an Astronomy Case Study","created":"2024-12-19","cited_by_count":1,"area":null},{"id":"2504.03822","title":"Arti-\"fickle\" Intelligence: Using LLMs as a Tool for Inference in the Political and Social Sciences","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2510.09152","title":"Logits Replay + MoClip: Stabilized, Low-Cost Post-Training with Minimal Forgetting","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2601.05578","title":"Reinforcement Learning of Large Language Models for Interpretable Credit Card Fraud Detection","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2602.03073","title":"TMS: Trajectory-Mixed Supervision for Reward-Free, On-Policy SFT","created":"2026-02-03","cited_by_count":1,"area":"alignment"},{"id":"2602.06665","title":"Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2602.09395","title":"Sparse Layer Sharpness-Aware Minimization for Efficient Fine-Tuning","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2603.03389","title":"Towards Improved Sentence Representations using Token Graphs","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2604.00979","title":"Dual Optimal: Make Your LLM Peer-like with Dignity","created":"2026-04-01","cited_by_count":1,"area":"alignment"},{"id":"2604.18963","title":"Distillation Traps and Guards: A Calibration Knob for LLM Distillability","created":"2026-04-21","cited_by_count":1,"area":"distill"},{"id":"2604.20225","title":"The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2605.20005","title":"Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2606.00628","title":"Robust Reasoning via Dynamic Token Selection for Distribution-Aligned Self-Distillation","created":"2026-05-30","cited_by_count":1,"area":"distill"},{"id":"2608.11758","title":"AWARe: Mitigating Catastrophic Forgetting via Activation-Weighted Adaptive REtention","created":"2026-08-12","cited_by_count":1,"area":"lr"},{"id":"2412.20057","title":"\"My life is miserable, have to sign 500 autographs everyday\": Exposing Humblebragging, the Brags in Disguise","created":"2024-12-28","cited_by_count":0,"area":null},{"id":"2502.13474","title":"Towards Lightweight, Adaptive and Attribute-Aware Multi-Aspect Controllable Text Generation with Large Language Models","created":"2025-02-19","cited_by_count":0,"area":null},{"id":"2504.04968","title":"The Dream Within Huang Long Cave: AI-Driven Interactive Narrative for Family Storytelling and Emotional Reflection","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2508.07022","title":"MultiMedEdit: A Scenario-Aware Benchmark for Evaluating Knowledge Editing in Medical VQA","created":"2025-08-09","cited_by_count":0,"area":null},{"id":"2509.13672","title":"CL$^2$GEC: A Multi-Discipline Benchmark for Continual Learning in Chinese Literature Grammatical Error Correction","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2509.14921","title":"Trade-offs in Cross-Domain Generalization of Foundation Model Fine-Tuned for Biometric Applications","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2509.18169","title":"PiERN: Token-Level Routing for Integrating High-Precision Computation and Reasoning","created":"2025-09-17","cited_by_count":0,"area":"lr"},{"id":"2511.01015","title":"What's the next frontier for Data-centric AI? Data Savvy Agents","created":"2025-11-02","cited_by_count":0,"area":null},{"id":"2512.20634","title":"Real Time Detection and Quantitative Analysis of Spurious Forgetting in Continual Learning","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2602.02027","title":"Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron","created":"2026-02-02","cited_by_count":0,"area":"safety"},{"id":"2602.10404","title":"Modular Multi-Task Learning for Chemical Reaction Prediction","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2602.11220","title":"Patch the Distribution Mismatch: RL Rewriting Agent for Stable Off-Policy SFT","created":"2026-02-11","cited_by_count":0,"area":"agents"},{"id":"2602.11965","title":"Parameter-Efficient Temporal Domain Generalization","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2602.22406","title":"Towards Autonomous Memory Agents","created":"2026-02-25","cited_by_count":0,"area":"agents"},{"id":"2603.17100","title":"An End-to-End Framework for Functionality-Embedded Provenance Graph Construction and Threat Interpretation","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.08388","title":"Awakening the Sleeping Agent: Lean-Specific Agentic Data Reactivates General Tool Use in Goedel Prover","created":"2026-04-09","cited_by_count":0,"area":"agents"},{"id":"2605.22972","title":"A mathematical theory of balancing relational generalization and memorization","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.25629","title":"When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift","created":"2026-05-25","cited_by_count":0,"area":"alignment"},{"id":"2606.00132","title":"Foundation-Preserving Optimization in Generalized Eigenspace","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.03626","title":"TurtleAI: Benchmarking Multimodal Models for Visual Programming in Turtle Graphics","created":"2026-06-02","cited_by_count":0,"area":"mllm"},{"id":"2606.06823","title":"PandaAI: A Practical Agent CQ2 for Neuro-symbolic Data Analysis And Integrated Decision-Making in Quantitative Finance","created":"2026-06-05","cited_by_count":0,"area":"agents"},{"id":"2606.17649","title":"A Risk Decomposition Framework for Pre-Hoc Fine-Tuning Prediction","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.25087","title":"Neural Network Quantization by Learning Low-Loss Subspaces","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.30258","title":"KnowsTFM: Knowledge-Informed Fine-Tuning of Small Tabular Foundation Models","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.05161","title":"SemiAdapt-Instruct: Extensible Instruction Tuning via Latent Domain-Specialised Adapters","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2608.20794","title":"Knowing but Not Saying: Preventing Factual Access Failures in LLM SFT via Recall-Anchored Distillation","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.24192","title":"Preference Data Selection for Mitigating the Alignment Tax in Large Language Models","created":"2026-08-25","cited_by_count":0,"area":"alignment"},{"id":"2608.27910","title":"AI Alignment through a Game-theoretic Lens: A Survey","created":"2026-08-28","cited_by_count":0,"area":"alignment"},{"id":"2609.05913","title":"Neuron-Guided Fine-Tuning: Unlocking Efficient Alignment Mechanisms for Large Language Models","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.08067","title":"Popular Knowledge Propagates More Errors in LLM Knowledge Updating","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.08966","title":"Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.16800","title":"Smarter by the Moment: Environment-Driven Dynamic Policies for Continual LLM Improvement","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.33183","title":"Identifying Temporal Features within Transcoders for Time Sensitive Factual Recall","created":"2026-09-27","cited_by_count":0,"area":"mechinterp"},{"id":"2609.33620","title":"Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.36448","title":"Theory on Attention Dynamics for Out-of-Distribution In-Context Learning","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.03940","title":"A Step Towards Forgetting: Optimiser History and the Loss of Answer Mass","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.05402","title":"Task Vector Descent: Learning from Non-IID Batches","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.12855","title":"Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization","created":"2026-10-09","cited_by_count":0,"area":"synth"},{"id":"2610.12995","title":"What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}