{"list":"other","total":53,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625},{"id":"2408.11039","title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","created":"2024-08-20","cited_by_count":483},{"id":"2410.10762","title":"AFlow: Automating Agentic Workflow Generation","created":"2024-10-14","cited_by_count":432},{"id":"2409.12917","title":"Training Language Models to Self-Correct via Reinforcement Learning","created":"2024-09-19","cited_by_count":426},{"id":"2305.10425","title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback","created":"2023-05-17","cited_by_count":401},{"id":"2406.03816","title":"ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search","created":"2024-06-06","cited_by_count":344},{"id":"2404.14396","title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","created":"2024-04-22","cited_by_count":331},{"id":"2406.11931","title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","created":"2024-06-17","cited_by_count":331},{"id":"2406.18629","title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","created":"2024-06-26","cited_by_count":273},{"id":"2404.10719","title":"Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study","created":"2024-04-16","cited_by_count":262},{"id":"2404.19733","title":"Iterative Reasoning Preference Optimization","created":"2024-04-30","cited_by_count":246},{"id":"2402.10200","title":"Chain-of-Thought Reasoning Without Prompting","created":"2024-02-15","cited_by_count":210},{"id":"2402.08268","title":"World Model on Million-Length Video And Language With Blockwise RingAttention","created":"2024-02-13","cited_by_count":198},{"id":"2408.08152","title":"DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search","created":"2024-08-15","cited_by_count":197},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194},{"id":"2403.04642","title":"Teaching Large Language Models to Reason with Reinforcement Learning","created":"2024-03-07","cited_by_count":160},{"id":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142},{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106},{"id":"2310.10080","title":"Let's reward step by step: Step-Level reward model as the Navigators for Reasoning","created":"2023-10-16","cited_by_count":102},{"id":"2409.12959","title":"MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines","created":"2024-09-19","cited_by_count":101},{"id":"2404.03653","title":"CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching","created":"2024-04-04","cited_by_count":61},{"id":"2402.03289","title":"Make Every Move Count: LLM-based High-Quality RTL Code Generation Using MCTS","created":"2024-02-05","cited_by_count":43},{"id":"2407.00782","title":"Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning","created":"2024-06-30","cited_by_count":35},{"id":"2409.01392","title":"ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems","created":"2024-09-02","cited_by_count":30},{"id":"2408.16768","title":"SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners","created":"2024-08-29","cited_by_count":18},{"id":"2406.12502","title":"Code-Optimise: Self-Generated Preference Data for Correctness and Efficiency","created":"2024-06-18","cited_by_count":16},{"id":"2409.17972","title":"BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search","created":"2024-09-26","cited_by_count":13},{"id":"2410.01731","title":"ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation","created":"2024-10-02","cited_by_count":11},{"id":"2410.18585","title":"Aligning CodeLLMs with Direct Preference Optimization","created":"2024-10-24","cited_by_count":9}],"next_cursor":null}