{"total":58,"rows":[{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247,"area":null},{"id":"2507.01352","title":"Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy","created":"2025-07-02","cited_by_count":214,"area":"lr"},{"id":"2506.01937","title":"RewardBench 2: Advancing Reward Model Evaluation","created":"2025-06-02","cited_by_count":150,"area":"alignment"},{"id":"2511.01689","title":"Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI","created":"2025-11-03","cited_by_count":24,"area":"alignment"},{"id":"2511.07158","title":"Guiding Generative Models to Uncover Diverse and Novel Crystals via Reinforcement Learning","created":"2025-11-10","cited_by_count":21,"area":"deeprl"},{"id":"2505.22338","title":"Text2Grad: Reinforcement Learning from Natural Language Feedback","created":"2025-05-28","cited_by_count":18,"area":"alignment"},{"id":"2512.21852","title":"A Comedy of Estimators: On KL Regularization in RL Training of LLMs","created":"2025-12-26","cited_by_count":18,"area":"lr"},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"id":"2510.06674","title":"Agent-in-the-Loop: A Data Flywheel for Continuous Improvement in LLM-based Customer Support","created":"2025-10-08","cited_by_count":10,"area":"agents"},{"id":"2605.09808","title":"Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants","created":"2026-05-10","cited_by_count":10,"area":null},{"id":"2505.11614","title":"Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions","created":"2025-05-16","cited_by_count":9,"area":null},{"id":"2506.18631","title":"ReDit: Reward Dithering for Improved LLM Policy Optimization","created":"2025-06-23","cited_by_count":8,"area":"lr"},{"id":"2505.13355","title":"Survey: Multi-Armed Bandits Meet Large Language Models","created":"2025-05-19","cited_by_count":7,"area":null},{"id":"2510.10085","title":"Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning","created":"2025-10-11","cited_by_count":6,"area":"alignment"},{"id":"2601.10567","title":"Generative AI collective behavior needs an interactionist paradigm","created":"2026-01-15","cited_by_count":6,"area":null},{"id":"2510.21978","title":"Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models","created":"2025-10-24","cited_by_count":5,"area":"lr"},{"id":"2601.16529","title":"SycoEval-EM: Sycophancy Evaluation of Large Language Models in Simulated Clinical Encounters for Emergency Care","created":"2026-01-23","cited_by_count":5,"area":null},{"id":"2601.23135","title":"Why GRPO Needs Normalization: A Local-Curvature Perspective on Adaptive Gradients","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2603.00024","title":"Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMs","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2605.23989","title":"Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security","created":"2026-05-17","cited_by_count":5,"area":"agents"},{"id":"2512.10575","title":"RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systems","created":"2025-12-11","cited_by_count":4,"area":"alignment"},{"id":"2602.15829","title":"Operationalising the Superficial Alignment Hypothesis via Task Complexity","created":"2026-02-17","cited_by_count":4,"area":null},{"id":"2603.23301","title":"Steering LLMs for Culturally Localized Generation","created":"2026-03-24","cited_by_count":4,"area":"mechinterp"},{"id":"2606.32032","title":"Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs","created":"2026-06-30","cited_by_count":4,"area":"alignment"},{"id":"2509.21049","title":"Physics of Learning: A Lagrangian perspective to different learning paradigms","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2510.13183","title":"DSCD: Large Language Model Detoxification with Self-Constrained Decoding","created":"2025-10-15","cited_by_count":3,"area":null},{"id":"2512.18202","title":"Sophia: A Persistent Agent Framework of Artificial Life","created":"2025-12-20","cited_by_count":3,"area":"agents"},{"id":"2605.08031","title":"Object Hallucination-Free Reinforcement Unlearning for Vision-Language Models","created":"2026-05-08","cited_by_count":3,"area":"mllm"},{"id":"2605.09269","title":"DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification","created":"2026-05-10","cited_by_count":3,"area":"mllm"},{"id":"2605.27996","title":"Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure","created":"2026-05-27","cited_by_count":3,"area":"alignment"},{"id":"2606.18284","title":"Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier","created":"2026-06-10","cited_by_count":3,"area":"lr"},{"id":"2506.12365","title":"Advances in LLMs with Focus on Reasoning, Adaptability, Efficiency and Ethics","created":"2025-06-14","cited_by_count":2,"area":"lr"},{"id":"2602.15038","title":"Indic-TunedLens: Interpreting Multilingual Models in Indian Languages","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2603.16120","title":"Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Users","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2609.19101","title":"Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations","created":"2026-09-16","cited_by_count":2,"area":"alignment"},{"id":"2508.07375","title":"TurnGuide: Enhancing Meaningful Full Duplex Spoken Interactions via Dynamic Turn-Level Text-Speech Interleaving","created":"2025-08-10","cited_by_count":1,"area":null},{"id":"2601.03420","title":"Jailbreaking LLMs Without Gradients or Priors: Effective and Transferable Attacks","created":"2026-01-06","cited_by_count":1,"area":"safety"},{"id":"2602.10740","title":"Reinforced Curriculum Pre-Alignment for Domain-Adaptive VLMs","created":"2026-02-11","cited_by_count":1,"area":"mllm"},{"id":"2602.13203","title":"Adversarial Network Imagination: Causal LLMs and Digital Twins for Proactive Telecom Mitigation","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2602.14318","title":"In Transformer We Trust? A Perspective on Transformer Architecture Failure Modes","created":"2026-02-15","cited_by_count":1,"area":null},{"id":"2511.18411","title":"SmolKalam: Ensemble Quality-Filtered Translation at Scale for High Quality Arabic Post-Training Data","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2602.15640","title":"Latency-aware Human-in-the-Loop Reinforcement Learning for Semantic Communications","created":"2026-02-17","cited_by_count":0,"area":"deeprl"},{"id":"2602.19583","title":"DEEP: Docker-based Execution and Evaluation Platform","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.10335","title":"Fuel Gauge: Estimating Chain-of-Thought Length Ahead of Time in Large Multimodal Models","created":"2026-03-11","cited_by_count":0,"area":"lr"},{"id":"2604.16259","title":"Beyond Distribution Sharpening: The Importance of Task Rewards","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2604.26866","title":"MoRFI: Monotonic Sparse Autoencoder Feature Identification","created":"2026-04-29","cited_by_count":0,"area":"mechinterp"},{"id":"2605.24052","title":"Truthful Online Preference Aggregation for LLM Fine-Tuning in Mobile Crowdsourcing","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.06622","title":"UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMs","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.10706","title":"Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.19750","title":"Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"id":"2606.29758","title":"PS-PPO: Prefix-Sampling PPO for Critic-Free RLHF","created":"2026-06-29","cited_by_count":0,"area":"alignment"},{"id":"2609.00051","title":"From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling","created":"2026-08-30","cited_by_count":0,"area":"safety"},{"id":"2609.05111","title":"Unifying ICL, SFT, KL-Regularized RL Through a Bayesian Lens","created":"2026-09-04","cited_by_count":0,"area":"alignment"},{"id":"2609.27166","title":"Scaling of Capability and Efficiency at Inference Time in Large Reasoning Models","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.29775","title":"Prefilling the Reasoning Channel: Output-Prefix Attacks on Reasoning LLMs","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"id":"2610.01509","title":"Sharpening Tax in Post-Training","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.13356","title":"SWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent Trajectories","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.20350","title":"Lifted State Policy Optimization: Internalizing Self-Correction through Transition Geometry","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}