{"list":"other","total":64,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2506.08009","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","created":"2025-06-09","cited_by_count":625},{"id":"2312.17090","title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","created":"2023-12-28","cited_by_count":503},{"id":"2601.03233","title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","created":"2026-01-06","cited_by_count":236},{"id":"2407.14358","title":"Stable Audio Open","created":"2024-07-19","cited_by_count":197},{"id":"2510.02283","title":"Self-Forcing++: Towards Minute-Scale High-Quality Video Generation","created":"2025-10-02","cited_by_count":192},{"id":"2505.00212","title":"Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems","created":"2025-04-30","cited_by_count":185},{"id":"2602.02214","title":"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation","created":"2026-02-02","cited_by_count":184},{"id":"2412.15322","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","created":"2024-12-19","cited_by_count":134},{"id":"2407.01494","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","created":"2024-07-01","cited_by_count":110},{"id":"2503.22679","title":"Q-Insight: Understanding Image Quality via Visual Reinforcement Learning","created":"2025-03-28","cited_by_count":98},{"id":"2401.16423","title":"Synchformer: Efficient Synchronization from Sparse Cues","created":"2024-01-29","cited_by_count":97},{"id":"2503.23377","title":"JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization","created":"2025-03-30","cited_by_count":88},{"id":"2512.13507","title":"Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model","created":"2025-12-15","cited_by_count":80},{"id":"2505.14460","title":"VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank","created":"2025-05-20","cited_by_count":79},{"id":"2505.10320","title":"J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning","created":"2025-05-15","cited_by_count":75},{"id":"2309.16429","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","created":"2023-09-28","cited_by_count":69},{"id":"2405.19298","title":"Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare","created":"2024-05-29","cited_by_count":66},{"id":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43},{"id":"2305.02572","title":"High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learning","created":"2023-05-04","cited_by_count":37},{"id":"2506.21448","title":"ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing","created":"2025-06-26","cited_by_count":34},{"id":"2601.16914","title":"LoL: Longer than Longer, Scaling Video Generation to Hour","created":"2026-01-23","cited_by_count":32},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28},{"id":"2506.18564","title":"VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning","created":"2025-06-23","cited_by_count":26},{"id":"2602.19163","title":"JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation","created":"2026-02-22","cited_by_count":25},{"id":"2512.21094","title":"T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation","created":"2025-12-24","cited_by_count":24},{"id":"2602.05551","title":"FastVMT: Eliminating Redundancy in Video Motion Transfer","created":"2026-02-05","cited_by_count":23},{"id":"2403.01901","title":"FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio","created":"2024-03-04","cited_by_count":20},{"id":"2510.11369","title":"Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment","created":"2025-10-13","cited_by_count":18},{"id":"2412.19351","title":"ETTA: Elucidating the Design Space of Text-to-Audio Models","created":"2024-12-26","cited_by_count":17},{"id":"2506.08003","title":"Audio-Sync Video Generation with Multi-Stream Temporal Control","created":"2025-06-09","cited_by_count":15},{"id":"2002.05070","title":"AlignNet: A Unifying Approach to Audio-Visual Alignment","created":"2020-02-12","cited_by_count":13},{"id":"2404.07336","title":"PEAVS: Perceptual Evaluation of Audio-Visual Synchrony Grounded in Viewers' Opinion Scores","created":"2024-04-10","cited_by_count":13},{"id":"2409.15157","title":"LoVA: Long-form Video-to-Audio Generation","created":"2024-09-23","cited_by_count":13},{"id":"2605.18396","title":"NEWTON: Agentic Planning for Physically Grounded Video Generation","created":"2026-05-18","cited_by_count":12},{"id":"2603.22883","title":"Group Editing: Edit Multiple Images in One Go","created":"2026-03-24","cited_by_count":11},{"id":"2203.14639","title":"SyncNet: correlating objective for time delay estimation in audio signals","created":"2022-03-28","cited_by_count":10},{"id":"2503.06984","title":"Synchronized Video-to-Audio Generation via Mel Quantization-Continuum Decomposition","created":"2025-03-10","cited_by_count":10},{"id":"2511.18833","title":"PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation","created":"2025-11-24","cited_by_count":9},{"id":"2602.08682","title":"ALIVE: Animate Your World with Lifelike Audio-Video Generation","created":"2026-02-09","cited_by_count":9},{"id":"2505.08498","title":"LCES: Zero-shot Automated Essay Scoring via Pairwise Comparisons Using Large Language Models","created":"2025-05-13","cited_by_count":8},{"id":"2510.04577","title":"Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers","created":"2025-10-06","cited_by_count":8},{"id":"2504.02867","title":"Multi-Agent LLM Judge: automatic personalized LLM judge design for evaluating natural language generation applications","created":"2025-04-01","cited_by_count":7},{"id":"2509.21893","title":"Syncphony: Synchronized Audio-to-Video Generation with Diffusion Transformers","created":"2025-09-26","cited_by_count":7},{"id":"2510.01010","title":"ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning","created":"2025-10-01","cited_by_count":7},{"id":"2511.13219","title":"FoleyBench: A Benchmark For Video-to-Audio Models","created":"2025-11-17","cited_by_count":7},{"id":"2409.14709","title":"Video-to-Audio Generation with Fine-grained Temporal Semantics","created":"2024-09-23","cited_by_count":6},{"id":"2601.16933","title":"Reward-Forcing: Autoregressive Video Generation with Reward Feedback","created":"2026-01-23","cited_by_count":6},{"id":"2504.06778","title":"CAFA: a Controllable Automatic Foley Artist","created":"2025-04-09","cited_by_count":5},{"id":"2601.00943","title":"PhyEduVideo: A Benchmark for Evaluating Text-to-Video Models for Physics Education","created":"2026-01-02","cited_by_count":5},{"id":"2504.19730","title":"Evaluate-and-Purify: Fortifying Code Language Models Against Adversarial Attacks Using LLM-as-a-Judge","created":"2025-04-28","cited_by_count":4},{"id":"2510.21581","title":"Foley Control: Aligning a Frozen Latent Text-to-Audio Model to Video","created":"2025-10-24","cited_by_count":4},{"id":"2507.06774","title":"Checklist Engineering Empowers Multilingual LLM Judges","created":"2025-07-09","cited_by_count":3},{"id":"2512.02650","title":"Hear What Matters! Text-conditioned Selective Video-to-Audio Generation","created":"2025-12-02","cited_by_count":3},{"id":"2602.12304","title":"OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model","created":"2026-02-12","cited_by_count":3},{"id":"2507.12796","title":"DeQA-Doc: Adapting DeQA-Score to Document Image Quality Assessment","created":"2025-07-17","cited_by_count":2},{"id":"2601.14304","title":"Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding","created":"2026-01-18","cited_by_count":2},{"id":"2605.22051","title":"EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generation","created":"2026-05-21","cited_by_count":2}],"next_cursor":null}