{"total":54,"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":"2410.12877","title":"Improving Instruction-Following in Language Models through Activation Steering","created":"2024-10-15","cited_by_count":160,"area":"mechinterp"},{"id":"2410.03617","title":"What Matters for Model Merging at Scale?","created":"2024-10-04","cited_by_count":55,"area":null},{"id":"2407.08770","title":"Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing","created":"2024-07-11","cited_by_count":23,"area":"alignment"},{"id":"2509.19727","title":"Personality Vector: Modulating Personality of Large Language Models by Model Merging","created":"2025-09-24","cited_by_count":17,"area":null},{"id":"2502.11019","title":"Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning","created":"2025-02-16","cited_by_count":16,"area":null},{"id":"2406.02925","title":"Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition","created":"2024-06-05","cited_by_count":14,"area":null},{"id":"2412.11679","title":"Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach","created":"2024-12-16","cited_by_count":12,"area":null},{"id":"2412.19512","title":"Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging","created":"2024-12-27","cited_by_count":11,"area":null},{"id":"2409.08846","title":"Fingerprint Vector: Enabling Scalable and Efficient Model Fingerprint Transfer via Vector Addition","created":"2024-09-13","cited_by_count":10,"area":"safety"},{"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":"2412.11704","title":"Adapting Chat Language Models Using Only Target Unlabeled Language Data","created":"2024-12-16","cited_by_count":6,"area":null},{"id":"2502.20186","title":"Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge","created":"2025-02-27","cited_by_count":6,"area":null},{"id":"2503.20110","title":"Efficient Model Development through Fine-tuning Transfer","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2504.20106","title":"Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors","created":"2025-04-27","cited_by_count":6,"area":"alignment"},{"id":"2505.21963","title":"LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM Agents","created":"2025-05-28","cited_by_count":6,"area":"agents"},{"id":"2407.01470","title":"DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging","created":"2024-07-01","cited_by_count":5,"area":"alignment"},{"id":"2506.06844","title":"Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models","created":"2025-06-07","cited_by_count":5,"area":null},{"id":"2502.11533","title":"Be Cautious When Merging Unfamiliar LLMs: A Phishing Model Capable of Stealing Privacy","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2505.00649","title":"Investigating Task Arithmetic for Zero-Shot Information Retrieval","created":"2025-05-01","cited_by_count":4,"area":null},{"id":"2512.04844","title":"Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates","created":"2025-12-04","cited_by_count":4,"area":null},{"id":"2607.07916","title":"Persona Cartography: Charting Language Model Personality Traits in Weight Space","created":"2026-07-08","cited_by_count":4,"area":null},{"id":"2503.01611","title":"In-context Learning vs. Instruction Tuning: The Case of Small and Multilingual Language Models","created":"2025-03-03","cited_by_count":3,"area":null},{"id":"2512.16925","title":"V-Agent: An Interactive Video Search System Using Vision-Language Models","created":"2025-11-04","cited_by_count":3,"area":"mllm"},{"id":"2512.18699","title":"Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesis","created":"2025-12-21","cited_by_count":3,"area":null},{"id":"2508.09016","title":"A Survey on Training-free Alignment of Large Language Models","created":"2025-08-12","cited_by_count":2,"area":"alignment"},{"id":"2511.02451","title":"Merging Continual Pretraining Models for Domain-Specialized LLMs: A Case Study in Finance","created":"2025-11-04","cited_by_count":2,"area":"lr"},{"id":"2602.13071","title":"Bus-Conditioned Zero-Shot Trajectory Generation via Task Arithmetic","created":"2026-02-13","cited_by_count":2,"area":null},{"id":"2503.01233","title":"PEO: Improving Bi-Factorial Preference Alignment with Post-Training Policy Extrapolation","created":"2025-03-03","cited_by_count":1,"area":"alignment"},{"id":"2506.01266","title":"Detoxification of Large Language Models through Output-layer Fusion with a Calibration Model","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2508.01148","title":"DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging","created":"2025-08-02","cited_by_count":1,"area":null},{"id":"2602.07930","title":"Patches of Nonlinearity: Instruction Vectors in Large Language Models","created":"2026-02-08","cited_by_count":1,"area":null},{"id":"2603.02041","title":"EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2604.06377","title":"The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment","created":"2026-04-07","cited_by_count":1,"area":"lr"},{"id":"2604.21637","title":"Multilinguality at the Edge: Developing Language Models for the Global South","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2605.01256","title":"GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models","created":"2026-05-02","cited_by_count":1,"area":null},{"id":"2609.02685","title":"DKL: Decoupled Knowledge Learning for Instruction-Tuned Language Models","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2509.23381","title":"Guard Vector: Beyond English LLM Guardrails with Task-Vector Composition and Streaming-Aware Prefix SFT","created":"2025-09-27","cited_by_count":0,"area":"safety"},{"id":"2511.20662","title":"Democratizing LLM Efficiency: From Hyperscale Optimizations to Universal Deployability","created":"2025-11-03","cited_by_count":0,"area":"rag"},{"id":"2601.03648","title":"ELO: Efficient Layer-Specific Optimization for Continual Pretraining of Multilingual LLMs","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2601.10804","title":"BYOL: Bring Your Own Language Into LLMs","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2603.03324","title":"Controlling Chat Style in Language Models via Single-Direction Editing","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2603.28263","title":"Merge and Conquer: Instructing Multilingual Models by Adding Target Language Weights","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2603.28858","title":"OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.11129","title":"DeCoVec: Building Decoding Space based Task Vector for Large Language Models via In-Context Learning","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.13538","title":"Synthesizing Instruction-Tuning Datasets with Contrastive Decoding","created":"2026-04-15","cited_by_count":0,"area":"synth"},{"id":"2604.18106","title":"Efficient Low-Resource Language Adaptation via Multi-Source Dynamic Logit Fusion","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2606.28525","title":"A Gravitational Interpretation of Safety Reversion under Fine-Tuning","created":"2026-06-26","cited_by_count":0,"area":"safety"},{"id":"2607.00666","title":"Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts","created":"2026-07-01","cited_by_count":0,"area":"vla"},{"id":"2607.02214","title":"Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.20918","title":"UpgradeBench: A Decision-Centric Benchmark for Upgrading Fine-Tuned LLM Specialists","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.30609","title":"Reading the News: Adapting Large Language Models to Swedish Journalism Through Continued Pre-Training","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.14829","title":"Enemray: Toward Capable Language Models for Hassaniya","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2610.05872","title":"Off-Policy Merging Beats On-Policy Self-Distillation for Continual Learning","created":"2026-10-05","cited_by_count":0,"area":"distill"}],"next_cursor":null}