{"list":"other","total":56,"rows":[{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"id":"2402.14804","title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","created":"2024-02-22","cited_by_count":526},{"id":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220},{"id":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173},{"id":"2308.07921","title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","created":"2023-08-15","cited_by_count":166},{"id":"2310.03731","title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","created":"2023-10-05","cited_by_count":156},{"id":"2004.09249","title":"CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings","created":"2020-04-20","cited_by_count":132},{"id":"2503.04721","title":"Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities","created":"2025-03-06","cited_by_count":100},{"id":"2506.21619","title":"IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech","created":"2025-06-23","cited_by_count":90},{"id":"2501.06282","title":"MinMo: A Multimodal Large Language Model for Seamless Voice Interaction","created":"2025-01-10","cited_by_count":79},{"id":"2505.02625","title":"LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis","created":"2025-05-05","cited_by_count":76},{"id":"2402.16352","title":"MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs","created":"2024-02-26","cited_by_count":72},{"id":"2409.15594","title":"Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents","created":"2024-09-23","cited_by_count":72},{"id":"2505.03733","title":"WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch","created":"2025-05-06","cited_by_count":72},{"id":"2110.07393","title":"M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge","created":"2021-10-14","cited_by_count":71},{"id":"2406.13340","title":"SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words","created":"2024-06-19","cited_by_count":68},{"id":"2303.11510","title":"ICASSP 2023 Deep Noise Suppression Challenge","created":"2023-03-21","cited_by_count":65},{"id":"2104.03603","title":"AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario","created":"2021-04-08","cited_by_count":60},{"id":"2205.09812","title":"Voice Activity Projection: Self-supervised Learning of Turn-taking Events","created":"2022-05-19","cited_by_count":60},{"id":"2507.23159","title":"Full-Duplex-Bench v1.5: Evaluating Overlap Handling for Full-Duplex Speech Models","created":"2025-07-30","cited_by_count":54},{"id":"2411.17607","title":"Scaling Speech-Text Pre-training with Synthetic Interleaved Data","created":"2024-11-26","cited_by_count":47},{"id":"2505.10557","title":"MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning","created":"2025-05-15","cited_by_count":45},{"id":"2112.06223","title":"ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation","created":"2021-12-12","cited_by_count":44},{"id":"2510.07838","title":"Full-Duplex-Bench-v2: A Multi-Turn Evaluation Framework for Duplex Dialogue Systems with an Automated Examiner","created":"2025-10-09","cited_by_count":41},{"id":"2410.08196","title":"MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code","created":"2024-10-10","cited_by_count":39},{"id":"2106.01541","title":"MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding","created":"2021-06-03","cited_by_count":36},{"id":"2510.14958","title":"MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning","created":"2025-10-16","cited_by_count":35},{"id":"2502.17810","title":"URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models","created":"2025-02-25","cited_by_count":30},{"id":"2505.17060","title":"SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation","created":"2025-05-17","cited_by_count":27},{"id":"2403.06487","title":"Multilingual Turn-taking Prediction Using Voice Activity Projection","created":"2024-03-11","cited_by_count":26},{"id":"2505.14464","title":"Not All Correct Answers Are Equal: Why Your Distillation Source Matters","created":"2025-05-20","cited_by_count":25},{"id":"2510.11718","title":"CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images","created":"2025-10-13","cited_by_count":23},{"id":"2510.07293","title":"AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs","created":"2025-10-08","cited_by_count":22},{"id":"2511.10262","title":"MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models","created":"2025-11-13","cited_by_count":22},{"id":"1709.04005","title":"Addressee and Response Selection in Multi-Party Conversations with Speaker Interaction RNNs","created":"2017-09-12","cited_by_count":21},{"id":"2507.19040","title":"FD-Bench: A Full-Duplex Benchmarking Pipeline Designed for Full Duplex Spoken Dialogue Systems","created":"2025-07-25","cited_by_count":20},{"id":"2206.13135","title":"TALCS: An Open-Source Mandarin-English Code-Switching Corpus and a Speech Recognition Baseline","created":"2022-06-27","cited_by_count":17},{"id":"2501.16643","title":"An LLM Benchmark for Addressee Recognition in Multi-modal Multi-party Dialogue","created":"2025-01-28","cited_by_count":15},{"id":"2509.22644","title":"WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning","created":"2025-09-26","cited_by_count":15},{"id":"2405.17057","title":"ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation","created":"2024-05-27","cited_by_count":14},{"id":"2508.18240","title":"MTalk-Bench: Evaluating Speech-to-Speech Models in Multi-Turn Dialogues via Arena-style and Rubrics Protocols","created":"2025-08-22","cited_by_count":14},{"id":"2509.02521","title":"FLM-Audio: Natural Monologues Improves Native Full-Duplex Chatbots via Dual Training","created":"2025-09-02","cited_by_count":11},{"id":"2409.18602","title":"Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations","created":"2024-09-27","cited_by_count":9},{"id":"2509.05657","title":"LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding","created":"2025-09-06","cited_by_count":7},{"id":"2405.17103","title":"Empowering Character-level Text Infilling by Eliminating Sub-Tokens","created":"2024-05-27","cited_by_count":5},{"id":"2506.01934","title":"RoboEgo System Card: An Omnimodal Model with Native Full Duplexity","created":"2025-06-02","cited_by_count":5},{"id":"2506.02979","title":"Towards a Japanese Full-duplex Spoken Dialogue System","created":"2025-06-03","cited_by_count":5},{"id":"2508.19532","title":"Alignment with Fill-In-the-Middle for Enhancing Code Generation","created":"2025-08-27","cited_by_count":4},{"id":"2203.00674","title":"Advancing an Interdisciplinary Science of Conversation: Insights from a Large Multimodal Corpus of Human Speech","created":"2022-03-01","cited_by_count":3},{"id":"2505.05446","title":"Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding","created":"2025-05-08","cited_by_count":3},{"id":"2505.23540","title":"Probability-Consistent Preference Optimization for Enhanced LLM Reasoning","created":"2025-05-29","cited_by_count":2},{"id":"2602.03798","title":"FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation","created":"2026-02-03","cited_by_count":2},{"id":"2604.12282","title":"Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format Reasoning","created":"2026-04-14","cited_by_count":2},{"id":"2605.09603","title":"Edit-Based Refinement for Parallel Masked Diffusion Language Models","created":"2026-05-10","cited_by_count":2}],"next_cursor":null}