{"total":89,"rows":[{"id":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107,"area":"safety"},{"id":"2406.18853","title":"Decoding-Time Language Model Alignment with Multiple Objectives","created":"2024-06-27","cited_by_count":94,"area":"alignment"},{"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":"2402.02992","title":"Decoding-time Realignment of Language Models","created":"2024-02-05","cited_by_count":67,"area":"alignment"},{"id":"2404.11531","title":"Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization","created":"2024-04-17","cited_by_count":56,"area":null},{"id":"2402.18243","title":"Learning or Self-aligning? Rethinking Instruction Fine-tuning","created":"2024-02-28","cited_by_count":43,"area":"lr"},{"id":"2403.03640","title":"Apollo: A Lightweight Multilingual Medical LLM towards Democratizing Medical AI to 6B People","created":"2024-03-06","cited_by_count":38,"area":null},{"id":"2404.11045","title":"Offset Unlearning for Large Language Models","created":"2024-04-17","cited_by_count":36,"area":"safety"},{"id":"2405.03000","title":"MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoning","created":"2024-05-05","cited_by_count":36,"area":"lr"},{"id":"2406.17692","title":"From Distributional to Overton Pluralism: Investigating Large Language Model Alignment","created":"2024-06-25","cited_by_count":33,"area":"alignment"},{"id":"2405.19262","title":"Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models","created":"2024-05-29","cited_by_count":32,"area":"alignment"},{"id":"2502.19148","title":"Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs","created":"2025-02-26","cited_by_count":29,"area":null},{"id":"2410.11163","title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2504.07070","title":"A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models","created":"2025-04-09","cited_by_count":27,"area":"alignment"},{"id":"2502.04510","title":"Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems","created":"2025-02-06","cited_by_count":23,"area":null},{"id":"2410.18640","title":"Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model","created":"2024-10-24","cited_by_count":22,"area":"alignment"},{"id":"2405.17871","title":"Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment","created":"2024-05-28","cited_by_count":20,"area":"mllm"},{"id":"2405.14507","title":"Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast","created":"2024-05-23","cited_by_count":19,"area":"moe"},{"id":"2409.17819","title":"Inference-Time Language Model Alignment via Integrated Value Guidance","created":"2024-09-26","cited_by_count":19,"area":"alignment"},{"id":"2406.10303","title":"A Survey on Large Language Models from General Purpose to Medical Applications: Datasets, Methodologies, and Evaluations","created":"2024-06-14","cited_by_count":16,"area":null},{"id":"2403.19094","title":"Learning From Correctness Without Prompting Makes LLM Efficient Reasoner","created":"2024-03-28","cited_by_count":15,"area":"lr"},{"id":"2405.14488","title":"MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability","created":"2024-05-23","cited_by_count":15,"area":null},{"id":"2502.20548","title":"$Q\\sharp$: Provably Optimal Distributional RL for LLM Post-Training","created":"2025-02-27","cited_by_count":15,"area":"lr"},{"id":"2406.12295","title":"Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding","created":"2024-06-18","cited_by_count":13,"area":null},{"id":"2507.04756","title":"CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering","created":"2025-07-07","cited_by_count":13,"area":null},{"id":"2505.12716","title":"Shadow-FT: Tuning Instruct Model via Training on Paired Base Model","created":"2025-05-19","cited_by_count":10,"area":null},{"id":"2510.09913","title":"Don't Throw Away Your Pretrained Model","created":"2025-10-10","cited_by_count":10,"area":"lr"},{"id":"2406.15480","title":"On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion","created":"2024-06-17","cited_by_count":9,"area":null},{"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":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2510.14943","title":"LaSeR: Reinforcement Learning with Last-Token Self-Rewarding","created":"2025-10-16","cited_by_count":9,"area":"lr"},{"id":"2405.13578","title":"ConTrans: Weak-to-Strong Alignment Engineering via Concept Transplantation","created":"2024-05-22","cited_by_count":8,"area":null},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2503.10071","title":"Advanced Tool Learning and Selection System (ATLASS): A Closed-Loop Framework Using LLM","created":"2025-03-13","cited_by_count":8,"area":"agents"},{"id":"2505.24872","title":"ProxyThinker: Test-Time Guidance through Small Visual Reasoners","created":"2025-05-30","cited_by_count":8,"area":"lr"},{"id":"2601.05167","title":"RelayLLM: Efficient Reasoning via Collaborative Decoding","created":"2026-01-08","cited_by_count":8,"area":"lr"},{"id":"2607.26246","title":"Weak-to-Strong On-Policy Distillation","created":"2026-07-28","cited_by_count":8,"area":"distill"},{"id":"2405.01345","title":"The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights","created":"2024-05-02","cited_by_count":7,"area":"lr"},{"id":"2410.10870","title":"PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches","created":"2024-10-08","cited_by_count":7,"area":null},{"id":"2506.14123","title":"Sampling from Your Language Model One Byte at a Time","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2602.23306","title":"ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding","created":"2026-02-26","cited_by_count":7,"area":"lr"},{"id":"2605.18855","title":"Delta Attention Residuals","created":"2026-05-13","cited_by_count":7,"area":null},{"id":"2406.18695","title":"Learning to Correct for QA Reasoning with Black-box LLMs","created":"2024-06-26","cited_by_count":6,"area":"lr"},{"id":"2410.06154","title":"GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models","created":"2024-10-08","cited_by_count":6,"area":"mllm"},{"id":"2410.19230","title":"Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors","created":"2024-10-25","cited_by_count":6,"area":null},{"id":"2601.21257","title":"MoCo: A One-Stop Shop for Model Collaboration Research","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2602.03211","title":"Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models","created":"2026-02-03","cited_by_count":6,"area":"diffusion"},{"id":"2603.16219","title":"SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized Generation","created":"2026-03-17","cited_by_count":6,"area":"lr"},{"id":"2502.06806","title":"Logits are All We Need to Adapt Closed Models","created":"2025-02-03","cited_by_count":5,"area":null},{"id":"2506.15751","title":"Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts","created":"2025-06-18","cited_by_count":5,"area":"safety"},{"id":"2504.17421","title":"Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks","created":"2025-04-24","cited_by_count":4,"area":null},{"id":"2510.09354","title":"Logit Arithmetic Elicits Long Reasoning Capabilities Without Training","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2604.11446","title":"Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration","created":"2026-04-13","cited_by_count":4,"area":null},{"id":"2402.01602","title":"Foundation Model Sherpas: Guiding Foundation Models through Knowledge and Reasoning","created":"2024-02-02","cited_by_count":3,"area":"lr"},{"id":"2407.11009","title":"CharED: Character-wise Ensemble Decoding for Large Language Models","created":"2024-06-25","cited_by_count":3,"area":"lr"},{"id":"2512.24503","title":"Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice","created":"2025-12-30","cited_by_count":3,"area":"lr"},{"id":"2501.05336","title":"Stream Aligner: Efficient Sentence-Level Alignment via Distribution Induction","created":"2025-01-09","cited_by_count":2,"area":"alignment"},{"id":"2502.12776","title":"Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models","created":"2025-02-18","cited_by_count":2,"area":"lr"},{"id":"2505.18488","title":"Synthesizing and Adapting Error Correction Data for Mobile Large Language Model Applications","created":"2025-05-24","cited_by_count":2,"area":null},{"id":"2506.21887","title":"Interactive Multi-Objective Probabilistic Preference Learning with Soft and Hard Bounds","created":"2025-06-27","cited_by_count":2,"area":null},{"id":"2507.12759","title":"Logit Arithmetic Elicits Long Reasoning Capabilities Without Training","created":"2025-07-17","cited_by_count":2,"area":"lr"},{"id":"2510.09211","title":"DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction","created":"2025-10-10","cited_by_count":2,"area":"lr"},{"id":"2512.03056","title":"Delta Sampling: Data-Free Knowledge Transfer Across Diffusion Models","created":"2025-11-25","cited_by_count":2,"area":"diffusion"},{"id":"2602.05182","title":"The Single-Multi Evolution Loop for Self-Improving Model Collaboration Systems","created":"2026-02-05","cited_by_count":2,"area":"synth"},{"id":"2602.14302","title":"Floe: Federated Specialization for Real-Time LLM-SLM Inference","created":"2026-02-15","cited_by_count":2,"area":null},{"id":"2606.07812","title":"Scaling Participation in Modular AI Systems","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2609.08798","title":"Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation","created":"2026-09-08","cited_by_count":2,"area":"distill"},{"id":"2407.01155","title":"CPT: Consistent Proxy Tuning for Black-box Optimization","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2410.14765","title":"What's New in My Data? Novelty Exploration via Contrastive Generation","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2509.26169","title":"Alignment-Aware Decoding","created":"2025-09-30","cited_by_count":1,"area":"alignment"},{"id":"2603.12811","title":"OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution","created":"2026-03-13","cited_by_count":1,"area":"alignment"},{"id":"2606.05145","title":"Failed Reasoning Traces Tell You What Is Fixable (But Not by Reading Them)","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2606.12342","title":"ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing","created":"2026-06-10","cited_by_count":1,"area":"safety"},{"id":"2607.23394","title":"Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning","created":"2026-07-25","cited_by_count":1,"area":null},{"id":"2609.05968","title":"Test-Time Weak-to-Strong Alignment: Transferring Implicit Rewards from Weak to Strong Flow Models","created":"2026-09-05","cited_by_count":1,"area":"alignment"},{"id":"2601.03423","title":"Training-Free Adaptation of New-Generation LLMs using Legacy Clinical Models","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2604.11465","title":"Three Roles, One Model: Role Orchestration at Inference Time to Close the Performance Gap Between Small and Large Agents","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2604.13538","title":"Synthesizing Instruction-Tuning Datasets with Contrastive Decoding","created":"2026-04-15","cited_by_count":0,"area":"synth"},{"id":"2605.11712","title":"Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2605.20555","title":"Complementing reinforcement learning with SFT through logit averaging in the post training of LLMs","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2606.29282","title":"ScaleErasure: Inference-Time Minimal Intervention for Precise Concept Erasure in Next-Scale Autoregressive Image Generation","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.05461","title":"AdaStop: Cost-Aware Early Stopping for DNN Test Selection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.31105","title":"BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.22153","title":"SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.30226","title":"PoEM: Predicting RL Outcomes from Existing Policies","created":"2026-09-24","cited_by_count":0,"area":"alignment"},{"id":"2609.36956","title":"Controlled Decoding Attacks on Black-Box LLMs","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2609.38142","title":"AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation","created":"2026-09-29","cited_by_count":0,"area":"distill"},{"id":"2610.00333","title":"LEGO-OPD: Factorized Teacher Composition for Multimodal On-Policy Distillation","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.16003","title":"PAIR: Memory-Efficient and Fast Inference with Reading--Reasoning Fusion","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}