{"list":"other","total":64,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"1802.01886","title":"Texygen: A Benchmarking Platform for Text Generation Models","created":"2018-02-06","cited_by_count":491},{"id":"2009.10297","title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","created":"2020-09-22","cited_by_count":479},{"id":"2503.04697","title":"L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning","created":"2025-03-06","cited_by_count":384},{"id":"2306.02707","title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4","created":"2023-06-05","cited_by_count":379},{"id":"2507.17746","title":"Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains","created":"2025-07-23","cited_by_count":366},{"id":"2310.11564","title":"Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging","created":"2023-10-17","cited_by_count":280},{"id":"2502.04463","title":"Training Language Models to Reason Efficiently","created":"2025-02-06","cited_by_count":247},{"id":"2601.05242","title":"GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization","created":"2026-01-08","cited_by_count":193},{"id":"2001.04643","title":"DDSP: Differentiable Digital Signal Processing","created":"2020-01-14","cited_by_count":178},{"id":"2507.18624","title":"Checklists Are Better Than Reward Models For Aligning Language Models","created":"2025-07-24","cited_by_count":128},{"id":"1705.07962","title":"pix2code: Generating Code from a Graphical User Interface Screenshot","created":"2017-05-22","cited_by_count":114},{"id":"2302.05527","title":"CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code","created":"2023-02-10","cited_by_count":102},{"id":"2501.00274","title":"LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts","created":"2024-12-31","cited_by_count":87},{"id":"2506.02355","title":"Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening","created":"2025-06-03","cited_by_count":80},{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80},{"id":"2506.21506","title":"Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge","created":"2025-06-26","cited_by_count":76},{"id":"1707.09627","title":"Learning to Infer Graphics Programs from Hand-Drawn Images","created":"2017-07-30","cited_by_count":74},{"id":"2111.03017","title":"MT3: Multi-Task Multitrack Music Transcription","created":"2021-11-04","cited_by_count":71},{"id":"2412.14042","title":"CAD-Recode: Reverse Engineering CAD Code from Point Clouds","created":"2024-12-18","cited_by_count":66},{"id":"2504.05228","title":"NoveltyBench: Evaluating Language Models for Humanlike Diversity","created":"2025-04-07","cited_by_count":66},{"id":"1605.07008","title":"madmom: a new Python Audio and Music Signal Processing Library","created":"2016-05-23","cited_by_count":64},{"id":"2412.19663","title":"CAD-GPT: Synthesising CAD Construction Sequence with Spatial Reasoning-Enhanced Multimodal LLMs","created":"2024-12-27","cited_by_count":53},{"id":"2506.05256","title":"Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning","created":"2025-06-05","cited_by_count":52},{"id":"2505.00047","title":"Base Models Beat Aligned Models at Randomness and Creativity","created":"2025-04-30","cited_by_count":51},{"id":"2403.05286","title":"LLM4Decompile: Decompiling Binary Code with Large Language Models","created":"2024-03-08","cited_by_count":39},{"id":"2505.20793","title":"Rendering-Aware Reinforcement Learning for Vector Graphics Generation","created":"2025-05-27","cited_by_count":39},{"id":"2406.14088","title":"ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation","created":"2024-06-20","cited_by_count":37},{"id":"2504.04753","title":"CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images","created":"2025-04-07","cited_by_count":35},{"id":"2310.07712","title":"Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models","created":"2023-10-11","cited_by_count":31},{"id":"2310.07160","title":"LLark: A Multimodal Instruction-Following Language Model for Music","created":"2023-10-11","cited_by_count":29},{"id":"2503.23989","title":"Rubric Is All You Need: Enhancing LLM-based Code Evaluation With Question-Specific Rubrics","created":"2025-03-31","cited_by_count":29},{"id":"2305.12520","title":"SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly","created":"2023-05-21","cited_by_count":28},{"id":"2506.08123","title":"QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA","created":"2025-06-09","cited_by_count":28},{"id":"2010.10291","title":"Automatic multitrack mixing with a differentiable mixing console of neural audio effects","created":"2020-10-20","cited_by_count":27},{"id":"2204.13668","title":"Unaligned Supervision For Automatic Music Transcription in The Wild","created":"2022-04-28","cited_by_count":25},{"id":"2310.06530","title":"Refining Decompiled C Code with Large Language Models","created":"2023-10-10","cited_by_count":24},{"id":"2506.01241","title":"ExpertLongBench: Benchmarking Language Models on Expert-Level Long-Form Generation Tasks with Structured Checklists","created":"2025-06-02","cited_by_count":24},{"id":"1910.08930","title":"Sketch2Code: Transformation of Sketches to UI in Real-time Using Deep Neural Network","created":"2019-10-20","cited_by_count":23},{"id":"2505.18298","title":"Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards","created":"2025-05-23","cited_by_count":20},{"id":"2406.02255","title":"MidiCaps: A large-scale MIDI dataset with text captions","created":"2024-06-04","cited_by_count":19},{"id":"2505.11225","title":"HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization","created":"2025-05-16","cited_by_count":19},{"id":"2207.08759","title":"Style Transfer of Audio Effects with Differentiable Signal Processing","created":"2022-07-18","cited_by_count":18},{"id":"2506.10376","title":"MLLM-Based UI2Code Automation Guided by UI Layout Information","created":"2025-06-12","cited_by_count":17},{"id":"2510.04474","title":"DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization","created":"2025-10-06","cited_by_count":16},{"id":"2306.10785","title":"Multitrack Music Transcription with a Time-Frequency Perceiver","created":"2023-06-19","cited_by_count":13},{"id":"2407.04822","title":"YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem Augmentation","created":"2024-07-05","cited_by_count":13},{"id":"1806.04278","title":"The NES Music Database: A multi-instrumental dataset with expressive performance attributes","created":"2018-06-12","cited_by_count":11},{"id":"2405.04975","title":"Prototype2Code: End-to-end Front-end Code Generation from UI Design Prototypes","created":"2024-05-08","cited_by_count":10},{"id":"2412.18940","title":"Amuse: Human-AI Collaborative Songwriting with Multimodal Inspirations","created":"2024-12-25","cited_by_count":9},{"id":"2511.05650","title":"Optimizing Diversity and Quality through Base-Aligned Model Collaboration","created":"2025-11-07","cited_by_count":8},{"id":"2410.21233","title":"ST-ITO: Controlling Audio Effects for Style Transfer with Inference-Time Optimization","created":"2024-10-28","cited_by_count":7},{"id":"2502.13713","title":"TALKPLAY: Multimodal Music Recommendation with Large Language Models","created":"2025-02-19","cited_by_count":7},{"id":"2502.17726","title":"The GigaMIDI Dataset with Features for Expressive Music Performance Detection","created":"2025-02-24","cited_by_count":7},{"id":"2606.31154","title":"PPT-Eval: A Benchmark for Computer-Use Agents on PowerPoint Tasks","created":"2026-06-30","cited_by_count":7},{"id":"2407.08889","title":"Diff-MST: Differentiable Mixing Style Transfer","created":"2024-07-11","cited_by_count":6},{"id":"2502.14405","title":"Differentiable Black-box and Gray-box Modeling of Nonlinear Audio Effects","created":"2025-02-20","cited_by_count":6},{"id":"2210.15306","title":"Rigid-Body Sound Synthesis with Differentiable Modal Resonators","created":"2022-10-27","cited_by_count":5},{"id":"2506.10125","title":"D-LiFT: Improving LLM-based Decompiler Backend via Code Quality-driven Fine-tuning","created":"2025-06-11","cited_by_count":5},{"id":"2512.01559","title":"LLM2Fx-Tools: Tool Calling For Music Post-Production","created":"2025-12-01","cited_by_count":3},{"id":"2605.24193","title":"Music Transcription with (Almost) No Supervision","created":"2026-05-22","cited_by_count":1}],"next_cursor":null}