{"total":51,"rows":[{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254,"area":null},{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206,"area":"mechinterp"},{"id":"2406.08607","title":"Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference","created":"2024-06-12","cited_by_count":88,"area":"safety"},{"id":"2404.00599","title":"EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories","created":"2024-03-31","cited_by_count":72,"area":null},{"id":"2410.23054","title":"Controlling Language and Diffusion Models by Transporting Activations","created":"2024-10-30","cited_by_count":68,"area":"diffusion"},{"id":"2410.08193","title":"GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment","created":"2024-10-10","cited_by_count":54,"area":"alignment"},{"id":"2410.22821","title":"EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations","created":"2024-10-30","cited_by_count":34,"area":null},{"id":"2505.06274","title":"PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model","created":"2025-05-06","cited_by_count":28,"area":"alignment"},{"id":"2406.12274","title":"SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models","created":"2024-06-18","cited_by_count":23,"area":"alignment"},{"id":"2406.18966","title":"DataGen: Unified Synthetic Dataset Generation via Large Language Models","created":"2024-06-27","cited_by_count":23,"area":"synth"},{"id":"2409.03659","title":"LLM-based multi-agent poetry generation in non-cooperative environments","created":"2024-09-05","cited_by_count":15,"area":"agents"},{"id":"2502.14289","title":"Drift: Decoding-time Personalized Alignments with Implicit User Preferences","created":"2025-02-20","cited_by_count":13,"area":"alignment"},{"id":"2410.19109","title":"RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework","created":"2024-10-24","cited_by_count":11,"area":null},{"id":"2410.22296","title":"Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks","created":"2024-10-29","cited_by_count":10,"area":null},{"id":"2502.17607","title":"Synthetic Text Generation for Training Large Language Models via Gradient Matching","created":"2025-02-24","cited_by_count":10,"area":null},{"id":"2506.19382","title":"Measuring and Guiding Monosemanticity","created":"2025-06-24","cited_by_count":10,"area":"mechinterp"},{"id":"2410.10074","title":"Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2411.03250","title":"DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models","created":"2024-11-05","cited_by_count":9,"area":"diffusion"},{"id":"2411.09263","title":"Rethinking Weight-Averaged Model-merging","created":"2024-11-14","cited_by_count":8,"area":null},{"id":"2502.16645","title":"CODESYNC: Synchronizing Large Language Models with Dynamic Code Evolution at Scale","created":"2025-02-23","cited_by_count":8,"area":"alignment"},{"id":"2412.10418","title":"Constrained Decoding with Speculative Lookaheads","created":"2024-12-09","cited_by_count":6,"area":null},{"id":"2502.04075","title":"From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Models","created":"2025-02-06","cited_by_count":6,"area":null},{"id":"2506.05967","title":"Preference Learning for AI Alignment: a Causal Perspective","created":"2025-06-06","cited_by_count":6,"area":"alignment"},{"id":"2405.12939","title":"Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models","created":"2024-05-21","cited_by_count":5,"area":"lr"},{"id":"2502.20684","title":"JAM: Controllable and Responsible Text Generation via Causal Reasoning and Latent Vector Manipulation","created":"2025-02-28","cited_by_count":5,"area":"lr"},{"id":"2602.05536","title":"When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2412.00357","title":"Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models","created":"2024-11-30","cited_by_count":4,"area":"diffusion"},{"id":"2505.01954","title":"Semantic Probabilistic Control of Language Models","created":"2025-05-04","cited_by_count":4,"area":null},{"id":"2404.07117","title":"Continuous Language Model Interpolation for Dynamic and Controllable Text Generation","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2406.02721","title":"Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2407.04615","title":"On the Low-Rank Parametrization of Reward Models for Controlled Language Generation","created":"2024-07-05","cited_by_count":3,"area":"alignment"},{"id":"2410.09675","title":"COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement","created":"2024-10-12","cited_by_count":3,"area":null},{"id":"2503.02368","title":"Evolutionary Guided Decoding: Iterative Value Refinement for LLMs","created":"2025-03-04","cited_by_count":3,"area":null},{"id":"2511.09292","title":"C$^3$TG: Conflict-aware, Composite, and Collaborative Controlled Text Generation","created":"2025-11-12","cited_by_count":3,"area":null},{"id":"2512.24013","title":"Bridging the Perception-Cognition Gap:Re-engineering SAM2 with Hilbert-Mamba for Robust VLM-based Medical Diagnosis","created":"2025-12-30","cited_by_count":3,"area":"mllm"},{"id":"2602.09538","title":"UniARM: Towards a Unified Autoregressive Reward Model for Multi-Objective Test-Time Alignment","created":"2026-02-10","cited_by_count":3,"area":"alignment"},{"id":"2603.05432","title":"Ensembling Language Models with Sequential Monte Carlo","created":"2026-03-05","cited_by_count":3,"area":null},{"id":"2402.08498","title":"\"Reasoning\" with Rhetoric: On the Style-Evidence Tradeoff in LLM-Generated Counter-Arguments","created":"2024-02-13","cited_by_count":2,"area":"lr"},{"id":"2404.09384","title":"Generative transformations and patterns in LLM-native approaches for software verification and falsification","created":"2024-04-14","cited_by_count":2,"area":null},{"id":"2502.12217","title":"Optimal Brain Iterative Merging: Mitigating Interference in LLM Merging","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2503.11182","title":"Palette of Language Models: A Solver for Controlled Text Generation","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2505.19075","title":"Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs","created":"2025-05-25","cited_by_count":2,"area":"lr"},{"id":"2401.08491","title":"Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2410.24199","title":"Linguistically-Controlled Paraphrase Generation","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2504.02106","title":"ContrastScore: Towards Higher Quality, Less Biased, More Efficient Evaluation Metrics with Contrastive Evaluation","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2508.04047","title":"LaPA$^2$: Length-Aware Prefix and Prompt Attention Augmentation for Long-Form Controllable Text Generation","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2512.15765","title":"Shapley-based Data Valuation for LLM Alignment via Sequential Preference Optimization","created":"2025-12-12","cited_by_count":1,"area":"alignment"},{"id":"2607.29246","title":"Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL","created":"2026-07-31","cited_by_count":1,"area":"alignment"},{"id":"2402.13667","title":"GCOF: Self-iterative Text Generation for Copywriting Using Large Language Model","created":"2024-02-21","cited_by_count":0,"area":null},{"id":"2510.21794","title":"Token-Level Inference-Time Alignment for Vision-Language Models","created":"2025-10-20","cited_by_count":0,"area":"mllm"},{"id":"2601.07152","title":"Agents of Diffusion: Enhancing Diffusion Language Models with Multi-Agent Reinforcement Learning for Structured Data Generation (Extended Version)","created":"2026-01-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}