{"total":259,"rows":[{"id":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118,"area":null},{"id":"2505.21497","title":"Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers","created":"2025-05-27","cited_by_count":63,"area":null},{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59,"area":null},{"id":"2511.21689","title":"ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration","created":"2025-11-26","cited_by_count":47,"area":null},{"id":"2505.19797","title":"The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants","created":"2025-05-26","cited_by_count":38,"area":null},{"id":"2510.15511","title":"Language Models are Injective and Hence Invertible","created":"2025-10-17","cited_by_count":35,"area":null},{"id":"2503.17489","title":"Judge Anything: MLLM as a Judge Across Any Modality","created":"2025-03-21","cited_by_count":34,"area":null},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2509.08753","title":"Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling","created":"2025-09-10","cited_by_count":27,"area":null},{"id":"2512.14865","title":"Audio MultiChallenge: A Multi-Turn Evaluation of Spoken Dialogue Systems on Natural Human Interaction","created":"2025-12-16","cited_by_count":19,"area":null},{"id":"2604.10905","title":"Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music","created":"2026-04-13","cited_by_count":19,"area":null},{"id":"2509.01907","title":"RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events","created":"2025-09-02","cited_by_count":14,"area":null},{"id":"2507.13300","title":"AbGen: Evaluating Large Language Models in Ablation Study Design and Evaluation for Scientific Research","created":"2025-07-17","cited_by_count":13,"area":null},{"id":"2603.00039","title":"CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation","created":"2026-02-09","cited_by_count":13,"area":null},{"id":"2503.13572","title":"VeriContaminated: Assessing LLM-Driven Verilog Coding for Data Contamination","created":"2025-03-17","cited_by_count":12,"area":null},{"id":"2504.10146","title":"GeoUni: A Unified Model for Generating Geometry Diagrams, Problems and Problem Solutions","created":"2025-04-14","cited_by_count":11,"area":null},{"id":"2505.03054","title":"BLAB: Brutally Long Audio Bench","created":"2025-05-05","cited_by_count":11,"area":null},{"id":"2506.02961","title":"FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models","created":"2025-06-03","cited_by_count":11,"area":null},{"id":"2605.06747","title":"HumanNet: Scaling Human-centric Video Learning to One Million Hours","created":"2026-05-07","cited_by_count":11,"area":null},{"id":"2605.18577","title":"OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding","created":"2026-05-18","cited_by_count":11,"area":null},{"id":"2507.10787","title":"Can Multimodal Foundation Models Understand Schematic Diagrams? An Empirical Study on Information-Seeking QA over Scientific Papers","created":"2025-07-14","cited_by_count":10,"area":null},{"id":"2510.21739","title":"Next-Generation LLM for UAV: From Natural Language to Autonomous Flight","created":"2025-10-02","cited_by_count":10,"area":null},{"id":"2602.16110","title":"OmniCT: Towards a Unified Slice-Volume LVLM for Comprehensive CT Analysis","created":"2026-02-18","cited_by_count":10,"area":null},{"id":"2512.17495","title":"GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation","created":"2025-12-19","cited_by_count":9,"area":null},{"id":"2505.19978","title":"DeepDialogue: A Multi-Turn Emotionally-Rich Spoken Dialogue Dataset","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2510.16567","title":"Hallucination Benchmark for Speech Foundation Models","created":"2025-10-18","cited_by_count":8,"area":null},{"id":"2512.03676","title":"Different types of syntactic agreement recruit the same units within large language models","created":"2025-12-03","cited_by_count":8,"area":null},{"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,"area":null},{"id":"2503.21480","title":"OmniVox: Zero-Shot Emotion Recognition with Omni-LLMs","created":"2025-03-27","cited_by_count":7,"area":null},{"id":"2505.14887","title":"In-Context Learning Boosts Speech Recognition via Human-like Adaptation to Speakers and Language Varieties","created":"2025-05-20","cited_by_count":7,"area":null},{"id":"2505.20298","title":"MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2505.22765","title":"StressTest: Can YOUR Speech LM Handle the Stress?","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2507.10859","title":"MultiVox: A Benchmark for Evaluating Voice Assistants for Multimodal Interactions","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2507.17747","title":"Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarks","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2508.00904","title":"Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling","created":"2025-07-29","cited_by_count":7,"area":null},{"id":"2509.22437","title":"Chimera: Diagnosing Shortcut Learning in Visual-Language Understanding","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2512.16378","title":"Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs","created":"2025-12-18","cited_by_count":7,"area":null},{"id":"2601.02391","title":"WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables","created":"2025-12-25","cited_by_count":7,"area":null},{"id":"2506.05191","title":"MokA: Multimodal Low-Rank Adaptation for MLLMs","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2507.22753","title":"Opportunities and Challenges of LLMs in Education: An NLP Perspective","created":"2025-07-30","cited_by_count":6,"area":null},{"id":"2507.23511","title":"MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2508.15831","title":"Who's Asking? Investigating Bias Through the Lens of Disability Framed Queries in LLMs","created":"2025-08-18","cited_by_count":6,"area":null},{"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,"area":null},{"id":"2603.09232","title":"How Contrastive Decoding Enhances Large Audio Language Models","created":"2026-03-10","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2504.08024","title":"Summarizing Speech: A Comprehensive Survey","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2504.16921","title":"IberBench: LLM Evaluation on Iberian Languages","created":"2025-04-23","cited_by_count":5,"area":null},{"id":"2508.04865","title":"Agnostics: Learning to Code in Any Programming Language via Reinforcement with a Universal Learning Environment","created":"2025-08-06","cited_by_count":5,"area":null},{"id":"2510.00628","title":"Hearing the Order: Investigating Position Bias in Large Audio-Language Models","created":"2025-10-01","cited_by_count":5,"area":null},{"id":"2510.03777","title":"GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time","created":"2025-10-04","cited_by_count":5,"area":null},{"id":"2510.05542","title":"Sci-Phi: A Large Language Model Spatial Audio Descriptor","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2510.06371","title":"OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QA","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2510.06475","title":"PuzzlePlex: Benchmarking Foundation Models on Reasoning and Planning with Puzzles","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2510.13979","title":"Do Slides Help? Multi-modal Context for Automatic Transcription of Conference Talks","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2512.04453","title":"Open-Ended Goal Inference through Actions and Language for Human-Robot Collaboration","created":"2025-12-04","cited_by_count":5,"area":null},{"id":"2602.17598","title":"The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$\\rightarrow$LLM Pipelines?","created":"2026-02-19","cited_by_count":5,"area":null},{"id":"2608.28945","title":"Automated Researchers Can Mitigate Well-characterized Alignment Failures","created":"2026-08-28","cited_by_count":5,"area":null},{"id":"2505.11612","title":"Heart2Mind: Human-Centered Contestable Psychiatric Disorder Diagnosis System using Wearable ECG Monitors","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2512.18263","title":"TICL+: A Case Study On Speech In-Context Learning for Children's Speech Recognition","created":"2025-12-20","cited_by_count":4,"area":null},{"id":"2602.01030","title":"Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations","created":"2026-02-01","cited_by_count":4,"area":null},{"id":"2602.05220","title":"Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions","created":"2026-02-05","cited_by_count":4,"area":null},{"id":"2604.00267","title":"Omni-MMSI: Toward Identity-attributed Social Interaction Understanding","created":"2026-03-31","cited_by_count":4,"area":null},{"id":"2604.09497","title":"BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation","created":"2026-04-10","cited_by_count":4,"area":null},{"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,"area":null},{"id":"2606.05121","title":"Audio Interaction Model","created":"2026-06-03","cited_by_count":4,"area":null},{"id":"2609.24812","title":"MSI-Bench: Evaluating Multi-Speaker Voice Interaction for Collaborative AI Agents","created":"2026-09-21","cited_by_count":4,"area":null},{"id":"2504.04050","title":"FISH-Tuning: Enhancing PEFT Methods with Fisher Information","created":"2025-04-05","cited_by_count":3,"area":null},{"id":"2505.08215","title":"Unveiling the Best Practices for Applying Speech Foundation Models to Speech Intelligibility Prediction for Hearing-Impaired People","created":"2025-05-13","cited_by_count":3,"area":null},{"id":"2508.16390","title":"A Large-Scale Benchmark for Evaluating Large Language Models on Medical Question Answering in Romanian","created":"2025-08-22","cited_by_count":3,"area":null},{"id":"2510.23558","title":"ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2511.05578","title":"UTF-8 Plumbing: Byte-level Tokenizers Unavoidably Enable LLMs to Generate Ill-formed UTF-8","created":"2025-11-05","cited_by_count":3,"area":null},{"id":"2512.02716","title":"Menta: A Small Language Model for On-Device Mental Health Prediction","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2602.06139","title":"EgoAVU: Egocentric Audio-Visual Understanding","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2603.06193","title":"Whisper-CD: Accurate Long-Form Speech Recognition using Multi-Negative Contrastive Decoding","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2604.10733","title":"Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2604.17248","title":"VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech","created":"2026-04-19","cited_by_count":3,"area":null},{"id":"2604.21905","title":"Low-Rank Adaptation Redux for Large Models","created":"2026-04-23","cited_by_count":3,"area":null},{"id":"2606.00147","title":"RAFT: Data Refinement and Adaptive Distillation for Domain Fine-Tuning with Alleviated Forgetting","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2606.20521","title":"HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining","created":"2026-06-18","cited_by_count":3,"area":null},{"id":"2607.07964","title":"KronQ: LLM Quantization via Kronecker-Factored Hessian","created":"2026-07-08","cited_by_count":3,"area":null},{"id":"2608.17050","title":"Frozen Memory Is Not Enough: Rethinking External Memory as Extraction","created":"2026-08-17","cited_by_count":3,"area":null},{"id":"2609.08977","title":"Multimodal Duplex Interaction Agent","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2504.19327","title":"DeepInsert: Early Layer Bypass for Efficient and Performant Multimodal Understanding","created":"2025-04-27","cited_by_count":2,"area":null},{"id":"2506.04076","title":"Acoustically Precise Hesitation Tagging Is Essential for End-to-End Verbatim Transcription Systems","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2506.21220","title":"Complexity-aware fine-tuning","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2507.12463","title":"MMHU: A Massive-Scale Multimodal Benchmark for Human Behavior Understanding","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2507.14815","title":"FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing","created":"2025-07-20","cited_by_count":2,"area":null},{"id":"2507.16514","title":"The Ever-Evolving Science Exam","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2508.19721","title":"CAM\\~OES: A Comprehensive Automatic Speech Recognition Benchmark for European Portuguese","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2509.02523","title":"Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices","created":"2025-09-02","cited_by_count":2,"area":null},{"id":"2509.03525","title":"Speech-Based Cognitive Screening: A Systematic Evaluation of LLM Adaptation Strategies","created":"2025-08-24","cited_by_count":2,"area":null},{"id":"2509.07526","title":"Competitive Audio-Language Models with Data-Efficient Single-Stage Training on Public Data","created":"2025-09-09","cited_by_count":2,"area":null},{"id":"2509.20321","title":"Conversational Speech Reveals Structural Robustness Failures in SpeechLLM Backbones","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2509.23488","title":"Mapping Overlaps in Benchmarks through Perplexity in the Wild","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2510.02569","title":"Transcribe, Translate, or Transliterate: An Investigation of Intermediate Representations in Spoken Language Models","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2510.12121","title":"Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2510.13105","title":"EgoSocial: Benchmarking Proactive Intervention Ability of Omnimodal LLMs via Egocentric Social Interaction Perception","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2511.14098","title":"Collaborative QA using Interacting LLMs. Impact of Network Structure, Node Capability and Distributed Data","created":"2025-11-18","cited_by_count":2,"area":null},{"id":"2512.01603","title":"MAC-SLU: Multi-Intent Automotive Cabin Spoken Language Understanding Benchmark","created":"2025-12-01","cited_by_count":2,"area":null},{"id":"2512.05439","title":"BEAVER: An Efficient Deterministic LLM Verifier","created":"2025-12-05","cited_by_count":2,"area":null}],"next_cursor":"100"}