{"list":"other","total":99,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"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":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"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":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"2310.04451","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","created":"2023-10-03","cited_by_count":785},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463},{"id":"2007.06600","title":"Closed-Form Factorization of Latent Semantics in GANs","created":"2020-07-13","cited_by_count":408},{"id":"2307.15189","title":"Med-Flamingo: a Multimodal Medical Few-shot Learner","created":"2023-07-27","cited_by_count":392},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322},{"id":"2310.15213","title":"Function Vectors in Large Language Models","created":"2023-10-23","cited_by_count":308},{"id":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300},{"id":"2102.01356","title":"Recent Advances in Adversarial Training for Adversarial Robustness","created":"2021-02-02","cited_by_count":279},{"id":"2311.06668","title":"In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering","created":"2023-11-11","cited_by_count":245},{"id":"2310.06474","title":"Multilingual Jailbreak Challenges in Large Language Models","created":"2023-10-10","cited_by_count":240},{"id":"2205.05124","title":"Extracting Latent Steering Vectors from Pretrained Language Models","created":"2022-05-10","cited_by_count":225},{"id":"2505.23747","title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","created":"2025-05-29","cited_by_count":217},{"id":"1312.5663","title":"k-Sparse Autoencoders","created":"2013-12-19","cited_by_count":215},{"id":"2310.10348","title":"Attribution Patching Outperforms Automated Circuit Discovery","created":"2023-10-16","cited_by_count":209},{"id":"2501.18837","title":"Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming","created":"2025-01-31","cited_by_count":181},{"id":"2404.16014","title":"Improving Dictionary Learning with Gated Sparse Autoencoders","created":"2024-04-24","cited_by_count":179},{"id":"2309.00236","title":"Image Hijacks: Adversarial Images can Control Generative Models at Runtime","created":"2023-09-01","cited_by_count":172},{"id":"2310.15154","title":"Linear Representations of Sentiment in Large Language Models","created":"2023-10-23","cited_by_count":163},{"id":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159},{"id":"2510.14276","title":"Qwen3Guard Technical Report","created":"2025-10-16","cited_by_count":155},{"id":"2503.17547","title":"Learning Multi-Level Features with Matryoshka Sparse Autoencoders","created":"2025-03-21","cited_by_count":143},{"id":"2505.23884","title":"Test-Time Training Done Right","created":"2025-05-29","cited_by_count":130},{"id":"2503.09532","title":"SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability","created":"2025-03-12","cited_by_count":124},{"id":"2401.18018","title":"On Prompt-Driven Safeguarding for Large Language Models","created":"2024-01-31","cited_by_count":116},{"id":"2502.16681","title":"Are Sparse Autoencoders Useful? A Case Study in Sparse Probing","created":"2025-02-23","cited_by_count":115},{"id":"2410.13928","title":"Automatically Interpreting Millions of Features in Large Language Models","created":"2024-10-17","cited_by_count":113},{"id":"2411.11296","title":"Steering Language Model Refusal with Sparse Autoencoders","created":"2024-11-18","cited_by_count":95},{"id":"2407.14499","title":"Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery","created":"2024-07-19","cited_by_count":91},{"id":"2403.14472","title":"Detoxifying Large Language Models via Knowledge Editing","created":"2024-03-21","cited_by_count":87},{"id":"2403.17336","title":"Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models","created":"2024-03-26","cited_by_count":86},{"id":"2504.02821","title":"Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models","created":"2025-04-03","cited_by_count":71},{"id":"2405.20773","title":"Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character","created":"2024-05-25","cited_by_count":68},{"id":"2402.06255","title":"Fight Back Against Jailbreaking via Prompt Adversarial Tuning","created":"2024-02-09","cited_by_count":67},{"id":"2412.00473","title":"Jailbreak Large Vision-Language Models Through Multi-Modal Linkage","created":"2024-11-30","cited_by_count":62},{"id":"2302.03693","title":"Concept Algebra for (Score-Based) Text-Controlled Generative Models","created":"2023-02-07","cited_by_count":59},{"id":"2408.00765","title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities","created":"2024-08-01","cited_by_count":57},{"id":"2409.15310","title":"Visual Prompting in Multimodal Large Language Models: A Survey","created":"2024-09-05","cited_by_count":54},{"id":"2406.05113","title":"LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models","created":"2024-06-07","cited_by_count":52},{"id":"2410.19750","title":"The Geometry of Concepts: Sparse Autoencoder Feature Structure","created":"2024-10-10","cited_by_count":52},{"id":"2302.14383","title":"Linear Spaces of Meanings: Compositional Structures in Vision-Language Models","created":"2023-02-28","cited_by_count":48},{"id":"2401.06824","title":"Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective","created":"2024-01-12","cited_by_count":48},{"id":"2509.20358","title":"PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation","created":"2025-09-24","cited_by_count":41},{"id":"1605.02633","title":"Oracle Based Active Set Algorithm for Scalable Elastic Net Subspace Clustering","created":"2016-05-09","cited_by_count":40},{"id":"2504.08729","title":"Steering CLIP's vision transformer with sparse autoencoders","created":"2025-04-11","cited_by_count":38},{"id":"2306.00966","title":"The Hidden Language of Diffusion Models","created":"2023-06-01","cited_by_count":34},{"id":"2402.13514","title":"Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions","created":"2024-02-21","cited_by_count":30},{"id":"2502.03708","title":"Toward universal steering and monitoring of AI models","created":"2025-02-06","cited_by_count":30},{"id":"2402.13148","title":"Defending Jailbreak Prompts via In-Context Adversarial Game","created":"2024-02-20","cited_by_count":29},{"id":"2501.05764","title":"Controlling Large Language Models Through Concept Activation Vectors","created":"2025-01-10","cited_by_count":28},{"id":"2303.15441","title":"Zero-shot Model Diagnosis","created":"2023-03-27","cited_by_count":23},{"id":"2411.14982","title":"Large Multi-modal Models Can Interpret Features in Large Multi-modal Models","created":"2024-11-22","cited_by_count":23},{"id":"2409.16727","title":"RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems","created":"2024-09-25","cited_by_count":21},{"id":"2406.04331","title":"PaCE: Parsimonious Concept Engineering for Large Language Models","created":"2024-06-06","cited_by_count":19},{"id":"2501.03012","title":"Analyzing Finetuning Representation Shift for Multimodal LLMs Steering","created":"2025-01-06","cited_by_count":16},{"id":"2310.17611","title":"Uncovering Meanings of Embeddings via Partial Orthogonality","created":"2023-10-26","cited_by_count":15},{"id":"2505.00976","title":"Attack and defense techniques in large language models: A survey and new perspectives","created":"2025-05-02","cited_by_count":14},{"id":"2506.01197","title":"Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures","created":"2025-06-01","cited_by_count":14},{"id":"2503.06982","title":"Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization","created":"2025-03-10","cited_by_count":13},{"id":"2506.12707","title":"SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression","created":"2025-06-15","cited_by_count":13},{"id":"2507.22171","title":"Enhancing Jailbreak Attacks on LLMs via Persona Prompts","created":"2025-07-28","cited_by_count":11},{"id":"2107.07268","title":"Cross-modal Variational Auto-encoder for Content-based Micro-video Background Music Recommendation","created":"2021-07-15","cited_by_count":10},{"id":"2402.06264","title":"LLaVA-Docent: Instruction Tuning with Multimodal Large Language Model to Support Art Appreciation Education","created":"2024-02-09","cited_by_count":8},{"id":"2411.00773","title":"LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation","created":"2024-11-01","cited_by_count":8},{"id":"2502.08697","title":"Bilevel Learning for Bilevel Planning","created":"2025-02-12","cited_by_count":7},{"id":"2504.02828","title":"Concept Lancet: Image Editing with Compositional Representation Transplant","created":"2025-04-03","cited_by_count":4},{"id":"2507.04183","title":"Voyaging into Perpetual Dynamic Scenes from a Single View","created":"2025-07-05","cited_by_count":2},{"id":"2512.17992","title":"Unifying Deep Predicate Invention with Pre-trained Foundation Models","created":"2025-12-19","cited_by_count":2}],"next_cursor":null}