{"list":"other","total":54,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382},{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326},{"id":"2110.06197","title":"Crystal Diffusion Variational Autoencoder for Periodic Material Generation","created":"2021-10-12","cited_by_count":270},{"id":"2305.17216","title":"Generating Images with Multimodal Language Models","created":"2023-05-26","cited_by_count":260},{"id":"2306.17775","title":"Practical and Asymptotically Exact Conditional Sampling in Diffusion Models","created":"2023-06-30","cited_by_count":232},{"id":"2501.06848","title":"A General Framework for Inference-time Scaling and Steering of Diffusion Models","created":"2025-01-12","cited_by_count":224},{"id":"2204.11817","title":"Translation between Molecules and Natural Language","created":"2022-04-25","cited_by_count":177},{"id":"2212.10789","title":"Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing","created":"2022-12-21","cited_by_count":166},{"id":"2309.04475","title":"Crystal Structure Prediction by Joint Equivariant Diffusion","created":"2023-07-30","cited_by_count":148},{"id":"2406.07209","title":"MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance","created":"2024-06-11","cited_by_count":144},{"id":"2406.04713","title":"FlowMM: Generating Materials with Riemannian Flow Matching","created":"2024-06-07","cited_by_count":109},{"id":"2506.23971","title":"UMA: A Family of Universal Models for Atoms","created":"2025-06-30","cited_by_count":105},{"id":"2402.04379","title":"Fine-Tuned Language Models Generate Stable Inorganic Materials as Text","created":"2024-02-06","cited_by_count":93},{"id":"2109.15290","title":"MatSciBERT: A Materials Domain Language Model for Text Mining and Information Extraction","created":"2021-09-30","cited_by_count":83},{"id":"2401.13923","title":"Towards 3D Molecule-Text Interpretation in Language Models","created":"2024-01-25","cited_by_count":66},{"id":"2307.07443","title":"Can Large Language Models Empower Molecular Property Prediction?","created":"2023-07-14","cited_by_count":44},{"id":"2507.13264","title":"Voxtral","created":"2025-07-17","cited_by_count":43},{"id":"2502.02582","title":"Open Materials Generation with Stochastic Interpolants","created":"2025-02-04","cited_by_count":28},{"id":"2503.02407","title":"Wyckoff Transformer: Generation of Symmetric Crystals","created":"2025-03-04","cited_by_count":27},{"id":"1905.13741","title":"Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representation","created":"2019-05-31","cited_by_count":23},{"id":"2512.04562","title":"LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models","created":"2025-12-04","cited_by_count":23},{"id":"2411.00177","title":"LLM4Mat-Bench: Benchmarking Large Language Models for Materials Property Prediction","created":"2024-10-31","cited_by_count":21},{"id":"2509.07150","title":"PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials Design","created":"2025-09-08","cited_by_count":14},{"id":"2512.03750","title":"Universally Converging Representations of Matter Across Scientific Foundation Models","created":"2025-12-03","cited_by_count":14},{"id":"2409.06762","title":"Generative Hierarchical Materials Search","created":"2024-09-10","cited_by_count":13},{"id":"2509.12178","title":"All that structure matches does not glitter","created":"2025-09-15","cited_by_count":12},{"id":"2406.17295","title":"Less can be more for predicting properties with large language models","created":"2024-06-25","cited_by_count":11},{"id":"2510.02259","title":"Transformers Discover Molecular Structure Without Graph Priors","created":"2025-10-02","cited_by_count":7},{"id":"2602.20210","title":"Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal Modeling","created":"2026-02-23","cited_by_count":7},{"id":"2605.24002","title":"Harnessing AtomisticSkills for Agentic Atomistic Research","created":"2026-05-18","cited_by_count":6},{"id":"2501.12919","title":"Bridging Text and Crystal Structures: Literature-driven Contrastive Learning for Materials Science","created":"2025-01-22","cited_by_count":4},{"id":"2503.01022","title":"LLM-Fusion: A Novel Multimodal Fusion Model for Accelerated Material Discovery","created":"2025-03-02","cited_by_count":4},{"id":"2605.14759","title":"Crys-JEPA: Accelerating Crystal Discovery via Embedding Screening and Generative Refinement","created":"2026-05-14","cited_by_count":4},{"id":"2605.14344","title":"CrystalReasoner: Reasoning and RL for Property-Conditioned Crystal Structure Generation","created":"2026-05-14","cited_by_count":3},{"id":"2510.20976","title":"L^2M^3OF: A Large Language Multimodal Model for Metal-Organic Frameworks","created":"2025-10-23","cited_by_count":2}],"next_cursor":null}