{"list":"other","total":56,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"2401.06121","title":"TOFU: A Task of Fictitious Unlearning for LLMs","created":"2024-01-11","cited_by_count":533},{"id":"2404.05868","title":"Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning","created":"2024-04-08","cited_by_count":504},{"id":"2310.12508","title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","created":"2023-10-19","cited_by_count":386},{"id":"2109.13398","title":"Unrolling SGD: Understanding Factors Influencing Machine Unlearning","created":"2021-09-27","cited_by_count":279},{"id":"2410.02355","title":"AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models","created":"2024-10-03","cited_by_count":236},{"id":"2310.07579","title":"In-Context Unlearning: Language Models as Few Shot Unlearners","created":"2023-10-11","cited_by_count":224},{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206},{"id":"2402.10058","title":"Towards Safer Large Language Models through Machine Unlearning","created":"2024-02-15","cited_by_count":139},{"id":"2203.12817","title":"Continual Learning and Private Unlearning","created":"2022-03-24","cited_by_count":130},{"id":"2308.09936","title":"BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions","created":"2023-08-19","cited_by_count":125},{"id":"2010.12883","title":"Variational Bayesian Unlearning","created":"2020-10-24","cited_by_count":117},{"id":"2502.17420","title":"The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence","created":"2025-02-24","cited_by_count":115},{"id":"2403.11641","title":"Arc2Face: A Foundation Model for ID-Consistent Human Faces","created":"2024-03-18","cited_by_count":101},{"id":"2305.06535","title":"KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment","created":"2023-05-11","cited_by_count":99},{"id":"2403.03329","title":"Guardrail Baselines for Unlearning in LLMs","created":"2024-03-05","cited_by_count":96},{"id":"2310.20138","title":"DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models","created":"2023-10-31","cited_by_count":79},{"id":"2406.00034","title":"Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories","created":"2024-05-26","cited_by_count":77},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76},{"id":"2506.18167","title":"Understanding Reasoning in Thinking Language Models via Steering Vectors","created":"2025-06-22","cited_by_count":72},{"id":"2410.09855","title":"Text4Seg: Reimagining Image Segmentation as Text Generation","created":"2024-10-13","cited_by_count":61},{"id":"2501.11858","title":"EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents","created":"2025-01-21","cited_by_count":57},{"id":"2506.07022","title":"AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint","created":"2025-06-08","cited_by_count":49},{"id":"2409.19732","title":"Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement","created":"2024-09-29","cited_by_count":45},{"id":"2410.18057","title":"CLEAR: Character Unlearning in Textual and Visual Modalities","created":"2024-10-23","cited_by_count":39},{"id":"2504.09466","title":"AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender","created":"2025-04-13","cited_by_count":38},{"id":"2407.16997","title":"Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective","created":"2024-07-24","cited_by_count":36},{"id":"2503.11314","title":"Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering","created":"2025-03-14","cited_by_count":36},{"id":"2505.20977","title":"Evaluating and Steering Modality Preferences in Multimodal Large Language Model","created":"2025-05-27","cited_by_count":33},{"id":"2405.07288","title":"Erasing Concepts from Text-to-Image Diffusion Models with Few-shot Unlearning","created":"2024-05-12","cited_by_count":29},{"id":"2412.00383","title":"Unified Parameter-Efficient Unlearning for LLMs","created":"2024-11-30","cited_by_count":25},{"id":"2406.10952","title":"Avoiding Copyright Infringement via Large Language Model Unlearning","created":"2024-06-16","cited_by_count":24},{"id":"2502.11190","title":"ReLearn: Unlearning via Learning for Large Language Models","created":"2025-02-16","cited_by_count":22},{"id":"2503.23084","title":"The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction","created":"2025-03-29","cited_by_count":21},{"id":"2410.23330","title":"CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP","created":"2024-10-30","cited_by_count":19},{"id":"2411.09273","title":"Cross-Modal Consistency in Multimodal Large Language Models","created":"2024-11-14","cited_by_count":19},{"id":"2402.09801","title":"EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models","created":"2024-02-15","cited_by_count":17},{"id":"2503.22048","title":"ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models","created":"2025-03-27","cited_by_count":17},{"id":"2501.03012","title":"Analyzing Finetuning Representation Shift for Multimodal LLMs Steering","created":"2025-01-06","cited_by_count":16},{"id":"2404.15100","title":"Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation","created":"2024-04-23","cited_by_count":15},{"id":"2507.14987","title":"AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning","created":"2025-07-20","cited_by_count":15},{"id":"2508.12815","title":"Learning to Steer: Input-dependent Steering for Multimodal LLMs","created":"2025-08-18","cited_by_count":15},{"id":"2506.08390","title":"On Reasoning Strength Planning in Large Reasoning Models","created":"2025-06-10","cited_by_count":13},{"id":"2505.14071","title":"Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models","created":"2025-05-20","cited_by_count":9}],"next_cursor":null}