{"list":"other","total":62,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2412.16720","title":"OpenAI o1 System Card","created":"2024-12-21","cited_by_count":1244},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"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":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497},{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491},{"id":"1703.10135","title":"Tacotron: Towards End-to-End Speech Synthesis","created":"2017-03-29","cited_by_count":490},{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464},{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429},{"id":"2312.13771","title":"AppAgent: Multimodal Agents as Smartphone Users","created":"2023-12-21","cited_by_count":415},{"id":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343},{"id":"2502.18600","title":"Chain of Draft: Thinking Faster by Writing Less","created":"2025-02-25","cited_by_count":297},{"id":"2507.11473","title":"Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety","created":"2025-07-15","cited_by_count":249},{"id":"2504.15895","title":"Dynamic Early Exit in Reasoning Models","created":"2025-04-22","cited_by_count":219},{"id":"2406.04904","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","created":"2024-06-07","cited_by_count":179},{"id":"2310.03731","title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","created":"2023-10-05","cited_by_count":156},{"id":"2312.04474","title":"Chain of Code: Reasoning with a Language Model-Augmented Code Emulator","created":"2023-12-07","cited_by_count":123},{"id":"2503.05179","title":"Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching","created":"2025-03-07","cited_by_count":117},{"id":"2503.24370","title":"Effectively Controlling Reasoning Models through Thinking Intervention","created":"2025-03-31","cited_by_count":65},{"id":"2506.13206","title":"Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models","created":"2025-06-16","cited_by_count":65},{"id":"2305.07243","title":"Better speech synthesis through scaling","created":"2023-05-12","cited_by_count":63},{"id":"2509.07980","title":"Parallel-R1: Towards Parallel Thinking via Reinforcement Learning","created":"2025-09-09","cited_by_count":61},{"id":"2410.17799","title":"OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation","created":"2024-10-23","cited_by_count":60},{"id":"2505.14183","title":"ThinkSwitcher: When to Think Hard, When to Think Fast","created":"2025-05-20","cited_by_count":37},{"id":"2504.13367","title":"THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models","created":"2025-04-17","cited_by_count":35},{"id":"2411.18138","title":"SALMONN-omni: A Codec-free LLM for Full-duplex Speech Understanding and Generation","created":"2024-11-27","cited_by_count":33},{"id":"2504.06261","title":"Hogwild! Inference: Parallel LLM Generation via Concurrent Attention","created":"2025-04-08","cited_by_count":32},{"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":"2502.11517","title":"Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding","created":"2025-02-17","cited_by_count":28},{"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":"2505.11107","title":"Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity","created":"2025-05-16","cited_by_count":22},{"id":"2505.16186","title":"SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning","created":"2025-05-22","cited_by_count":20},{"id":"2412.07017","title":"Asynchronous LLM Function Calling","created":"2024-12-09","cited_by_count":18},{"id":"2501.16466","title":"Incalmo: An Autonomous LLM-assisted System for Red Teaming Multi-Host Networks","created":"2025-01-27","cited_by_count":17},{"id":"2505.15684","title":"ThinkLess: A Training-Free Inference-Efficient Method for Reducing Reasoning Redundancy","created":"2025-05-21","cited_by_count":17},{"id":"2510.10103","title":"Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning","created":"2025-10-11","cited_by_count":16},{"id":"2510.17238","title":"StreamingThinker: Large Language Models Can Think While Reading","created":"2025-10-20","cited_by_count":15},{"id":"2505.15000","title":"Towards Spoken Mathematical Reasoning: Benchmarking Speech-based Models over Multi-faceted Math Problems","created":"2025-05-21","cited_by_count":12},{"id":"2509.24393","title":"Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention","created":"2025-09-29","cited_by_count":11},{"id":"2505.02707","title":"Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play","created":"2025-05-05","cited_by_count":10},{"id":"2506.04182","title":"Long or short CoT? Investigating Instance-level Switch of Large Reasoning Models","created":"2025-06-04","cited_by_count":8},{"id":"2503.20533","title":"Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence","created":"2025-03-26","cited_by_count":6},{"id":"2501.00868","title":"Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation","created":"2025-01-01","cited_by_count":5},{"id":"2505.17519","title":"Chain-of-Lure: A Universal Jailbreak Attack Framework using Unconstrained Synthetic Narratives","created":"2025-05-23","cited_by_count":5},{"id":"2512.03176","title":"Plantain: Plan-Answer Interleaved Reasoning","created":"2025-12-02","cited_by_count":5},{"id":"2509.24269","title":"AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models","created":"2025-09-29","cited_by_count":4},{"id":"2508.10032","title":"The Cost of Thinking: Increased Jailbreak Risk in Large Language Models","created":"2025-08-09","cited_by_count":2}],"next_cursor":null}