{"list":"other","total":69,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610},{"id":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"2503.01743","title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","created":"2025-03-03","cited_by_count":521},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"2507.21509","title":"Persona Vectors: Monitoring and Controlling Character Traits in Language Models","created":"2025-07-29","cited_by_count":345},{"id":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243},{"id":"2507.08128","title":"Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models","created":"2025-07-10","cited_by_count":219},{"id":"2305.10790","title":"Listen, Think, and Understand","created":"2023-05-18","cited_by_count":209},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181},{"id":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133},{"id":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118},{"id":"2505.13032","title":"MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix","created":"2025-05-19","cited_by_count":117},{"id":"2207.00221","title":"VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations","created":"2022-07-01","cited_by_count":114},{"id":"2506.04779","title":"MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark","created":"2025-06-05","cited_by_count":103},{"id":"2212.10537","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","created":"2022-12-20","cited_by_count":102},{"id":"2309.09510","title":"Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech","created":"2023-09-18","cited_by_count":101},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100},{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87},{"id":"2309.00916","title":"BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing","created":"2023-09-02","cited_by_count":79},{"id":"2501.09425","title":"Vision-Language Models Do Not Understand Negation","created":"2025-01-16","cited_by_count":72},{"id":"2410.18908","title":"A Survey on Speech Large Language Models for Understanding","created":"2024-10-24","cited_by_count":71},{"id":"2411.05361","title":"Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks","created":"2024-11-08","cited_by_count":71},{"id":"2311.06753","title":"AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs","created":"2023-11-12","cited_by_count":59},{"id":"2310.08753","title":"CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models","created":"2023-10-12","cited_by_count":43},{"id":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43},{"id":"2402.13236","title":"Towards audio language modeling -- an overview","created":"2024-02-20","cited_by_count":40},{"id":"2410.02678","title":"Distilling an End-to-End Voice Assistant Without Instruction Training Data","created":"2024-10-03","cited_by_count":39},{"id":"2506.10274","title":"Discrete Audio Tokens: More Than a Survey!","created":"2025-06-12","cited_by_count":38},{"id":"2406.03872","title":"BLSP-Emo: Towards Empathetic Large Speech-Language Models","created":"2024-06-06","cited_by_count":36},{"id":"2406.08402","title":"Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models","created":"2024-06-12","cited_by_count":31},{"id":"2410.16130","title":"Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning","created":"2024-10-21","cited_by_count":31},{"id":"2407.09886","title":"Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation","created":"2024-07-13","cited_by_count":27},{"id":"2505.19037","title":"Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models","created":"2025-05-25","cited_by_count":27},{"id":"2511.08723","title":"ParaS2S: Benchmarking and Aligning Spoken Language Models for Paralinguistic-aware Speech-to-Speech Interaction","created":"2025-11-11","cited_by_count":24},{"id":"2411.07111","title":"Building a Taiwanese Mandarin Spoken Language Model: A First Attempt","created":"2024-11-11","cited_by_count":23},{"id":"2508.03543","title":"EmoSteer-TTS: Fine-Grained and Training-Free Emotion-Controllable Text-to-Speech via Activation Steering","created":"2025-08-05","cited_by_count":23},{"id":"2305.10763","title":"CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-training","created":"2023-05-18","cited_by_count":18},{"id":"2404.17806","title":"T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining","created":"2024-04-27","cited_by_count":18},{"id":"2406.02032","title":"M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation","created":"2024-06-04","cited_by_count":16},{"id":"2408.07919","title":"Advancing Multi-grained Alignment for Contrastive Language-Audio Pre-training","created":"2024-08-15","cited_by_count":14},{"id":"2505.22946","title":"NegVQA: Can Vision Language Models Understand Negation?","created":"2025-05-28","cited_by_count":13},{"id":"2509.26388","title":"Game-Time: Evaluating Temporal Dynamics in Spoken Language Models","created":"2025-09-30","cited_by_count":13},{"id":"2408.13040","title":"SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks","created":"2024-08-23","cited_by_count":12},{"id":"2505.14518","title":"Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples","created":"2025-05-20","cited_by_count":11},{"id":"2510.10157","title":"BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation","created":"2025-10-11","cited_by_count":11},{"id":"2406.07203","title":"ParaCLAP -- Towards a general language-audio model for computational paralinguistic tasks","created":"2024-06-11","cited_by_count":10},{"id":"2503.22104","title":"M2D-CLAP: Exploring General-purpose Audio-Language Representations Beyond CLAP","created":"2025-03-28","cited_by_count":10},{"id":"2506.11350","title":"GLAP: General contrastive audio-text pretraining across domains and languages","created":"2025-06-12","cited_by_count":10},{"id":"2504.04479","title":"Activation Patching for Interpretable Steering in Music Generation","created":"2025-04-06","cited_by_count":8},{"id":"2601.14728","title":"AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering","created":"2026-01-21","cited_by_count":8},{"id":"2505.20166","title":"From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data","created":"2025-05-26","cited_by_count":7},{"id":"2509.21990","title":"WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLM","created":"2025-09-26","cited_by_count":7},{"id":"2512.04748","title":"Model Whisper: Steering Vectors Unlock Large Language Models' Potential in Test-time","created":"2025-12-04","cited_by_count":7},{"id":"2601.22873","title":"EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech Synthesis","created":"2026-01-30","cited_by_count":7},{"id":"2601.12248","title":"AQUA-Bench: Beyond Finding Answers to Knowing When There Are None in Audio Question Answering","created":"2026-01-18","cited_by_count":6},{"id":"2506.23553","title":"Human-CLAP: Human-perception-based contrastive language-audio pretraining","created":"2025-06-30","cited_by_count":4},{"id":"2511.16757","title":"Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation","created":"2025-11-20","cited_by_count":4},{"id":"2604.25591","title":"Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models","created":"2026-04-28","cited_by_count":4},{"id":"2603.20554","title":"When Negation Is a Geometry Problem in Vision-Language Models","created":"2026-03-20","cited_by_count":2},{"id":"2603.29258","title":"Omni-NegCLIP: Enhancing CLIP with Front-Layer Contrastive Fine-Tuning for Comprehensive Negation Understanding","created":"2026-03-31","cited_by_count":1}],"next_cursor":null}