{"total":19,"rows":[{"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":"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":"2605.15156","title":"MeMo: Memory as a Model","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2603.16941","title":"The Voice Behind the Words: Quantifying Intersectional Bias in SpeechLLMs","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2601.21853","title":"LEMUR: Learned Multi-Vector Retrieval","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2603.22267","title":"TiCo: Time-Controllable Spoken Dialogue Model","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2605.20268","title":"Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.25156","title":"ATMA: Long-Context Language Modeling via Polar Attention and Gated-Delta Compression Memory","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2608.27370","title":"Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2607.16246","title":"Let the Data Decide: Supervision Analysis, Capability Trade-offs, and Adaptive Objective Routing in Continued Pre-Training via Off-Policy Distillation","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2608.06959","title":"Summarize First, Download Later: Onboard VLMs for Bandwidth-Efficient Earth Observation","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.12615","title":"Drive-to-Music: Context-Aware Generative Audio for In-Vehicle Experiences","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.16710","title":"Continuous-Time Machine Learning: A Unified Mathematical Perspective","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.19555","title":"A Multi-Modal Generative Model for Tomato Disease Leaves Understanding","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.30218","title":"Minimally Invasive Steering of Language Models","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.32020","title":"A Benchmark for LLM's Understanding of Middle School and High School Science Topics","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.34992","title":"Composable Decoding on the Probability Simplex: Theory and Implementation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36860","title":"IronLLM: Forging Compact Edge-Native Language Models for Real-Time Embodied Intelligence","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00026","title":"High-Value Synthetic Supervision for Parameter-Efficient Adaptation of a Compact Japanese Speech Model","created":"2026-09-02","cited_by_count":0,"area":null}],"next_cursor":null}