{"total":521,"rows":[{"id":"2508.05635","title":"Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation","created":"2025-08-07","cited_by_count":137,"area":"diffusion"},{"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":"2505.17862","title":"Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities","created":"2025-05-23","cited_by_count":110,"area":"lr"},{"id":"2506.04779","title":"MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark","created":"2025-06-05","cited_by_count":103,"area":"lr"},{"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":"2505.08054","title":"FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning","created":"2025-05-12","cited_by_count":58,"area":"lr"},{"id":"2505.11717","title":"WebInject: Prompt Injection Attack to Web Agents","created":"2025-05-16","cited_by_count":51,"area":"agents"},{"id":"2507.02768","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","created":"2025-07-03","cited_by_count":50,"area":"synth"},{"id":"2505.17612","title":"Distilling LLM Agent into Small Models with Retrieval and Code Tools","created":"2025-05-23","cited_by_count":47,"area":"lr"},{"id":"2511.21689","title":"ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration","created":"2025-11-26","cited_by_count":47,"area":null},{"id":"2508.02095","title":"VLM4D: Towards Spatiotemporal Awareness in Vision Language Models","created":"2025-08-04","cited_by_count":46,"area":"lr"},{"id":"2504.21233","title":"Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math","created":"2025-04-30","cited_by_count":44,"area":"lr"},{"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":"2503.11579","title":"Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers","created":"2025-03-14","cited_by_count":36,"area":"mllm"},{"id":"2503.10582","title":"VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search","created":"2025-03-13","cited_by_count":35,"area":"mllm"},{"id":"2510.15511","title":"Language Models are Injective and Hence Invertible","created":"2025-10-17","cited_by_count":35,"area":null},{"id":"2511.19663","title":"Fara-7B: An Efficient Agentic Model for Computer Use","created":"2025-11-24","cited_by_count":35,"area":"agents"},{"id":"2503.17489","title":"Judge Anything: MLLM as a Judge Across Any Modality","created":"2025-03-21","cited_by_count":34,"area":null},{"id":"2505.19099","title":"SeePhys: Does Seeing Help Thinking? -- Benchmarking Vision-Based Physics Reasoning","created":"2025-05-25","cited_by_count":34,"area":"lr"},{"id":"2506.02555","title":"SurgVLM: A Large Vision-Language Model and Systematic Evaluation Benchmark for Surgical Intelligence","created":"2025-06-03","cited_by_count":31,"area":"mllm"},{"id":"2505.10610","title":"MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly","created":"2025-05-15","cited_by_count":29,"area":"mllm"},{"id":"2505.19147","title":"Shifting AI Efficiency From Model-Centric to Data-Centric Compression","created":"2025-05-25","cited_by_count":29,"area":"mllm"},{"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":"2603.16060","title":"ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning","created":"2026-03-17","cited_by_count":29,"area":"lr"},{"id":"2503.15621","title":"LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning","created":"2025-03-19","cited_by_count":28,"area":"mllm"},{"id":"2505.16517","title":"ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models","created":"2025-05-22","cited_by_count":27,"area":"lr"},{"id":"2509.08753","title":"Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling","created":"2025-09-10","cited_by_count":27,"area":null},{"id":"2505.17117","title":"From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning","created":"2025-05-21","cited_by_count":25,"area":"lr"},{"id":"2507.23779","title":"Phi-Ground Tech Report: Advancing Perception in GUI Grounding","created":"2025-07-31","cited_by_count":25,"area":"lr"},{"id":"2506.04141","title":"MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos","created":"2025-06-04","cited_by_count":22,"area":"lr"},{"id":"2509.11864","title":"NeuroStrike: Neuron-Level Attacks on Aligned LLMs","created":"2025-09-15","cited_by_count":22,"area":"alignment"},{"id":"2510.05069","title":"SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs","created":"2025-10-06","cited_by_count":22,"area":"lr"},{"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,"area":"inference"},{"id":"2512.02231","title":"See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models","created":"2025-12-01","cited_by_count":20,"area":"mllm"},{"id":"2506.23329","title":"IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering","created":"2025-06-29","cited_by_count":19,"area":"mllm"},{"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":"2601.18744","title":"TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models","created":"2026-01-26","cited_by_count":18,"area":"lr"},{"id":"2508.19542","title":"CVBench: Benchmarking Cross-Video Synergies for Complex Multimodal Reasoning","created":"2025-08-27","cited_by_count":16,"area":"lr"},{"id":"2507.21585","title":"SafeDriveRAG: Towards Safe Autonomous Driving with Knowledge Graph-based Retrieval-Augmented Generation","created":"2025-07-29","cited_by_count":15,"area":"mllm"},{"id":"2511.07931","title":"SpeechJudge: Towards Human-Level Judgment for Speech Naturalness","created":"2025-11-11","cited_by_count":15,"area":"alignment"},{"id":"2505.19406","title":"Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model","created":"2025-05-26","cited_by_count":14,"area":"lr"},{"id":"2508.07493","title":"VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding","created":"2025-08-10","cited_by_count":14,"area":"rag"},{"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":"2608.27549","title":"Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning","created":"2026-08-27","cited_by_count":14,"area":"lr"},{"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":"2505.15000","title":"Towards Spoken Mathematical Reasoning: Benchmarking Speech-based Models over Multi-faceted Math Problems","created":"2025-05-21","cited_by_count":12,"area":"lr"},{"id":"2507.03483","title":"BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset","created":"2025-07-04","cited_by_count":12,"area":"lr"},{"id":"2508.04043","title":"VisualTrans: A Benchmark for Real-World Visual Transformation Reasoning","created":"2025-08-06","cited_by_count":12,"area":"lr"},{"id":"2510.03519","title":"TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning","created":"2025-10-03","cited_by_count":12,"area":"lr"},{"id":"2601.21282","title":"WorldBench: Benchmarking Physical Understanding of World Models by Isolating Physics Concepts","created":"2026-01-29","cited_by_count":12,"area":"wm"},{"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":"2507.08799","title":"KV Cache Steering for Controlling Frozen LLMs","created":"2025-07-11","cited_by_count":11,"area":"inference"},{"id":"2507.21503","title":"MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual Questions","created":"2025-07-29","cited_by_count":11,"area":"mllm"},{"id":"2509.02820","title":"Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs","created":"2025-09-02","cited_by_count":11,"area":"safety"},{"id":"2510.24693","title":"STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence","created":"2025-10-28","cited_by_count":11,"area":"lr"},{"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":"2511.23478","title":"Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models","created":"2025-11-28","cited_by_count":10,"area":"lr"},{"id":"2602.12158","title":"SafeNeuron: Neuron-Level Safety Alignment for Large Language Models","created":"2026-02-12","cited_by_count":10,"area":"mllm"},{"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":"2607.24904","title":"Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model","created":"2026-07-27","cited_by_count":10,"area":"lr"},{"id":"2505.13111","title":"Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation","created":"2025-05-19","cited_by_count":9,"area":"distill"},{"id":"2505.14462","title":"RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding","created":"2025-05-20","cited_by_count":9,"area":"mllm"},{"id":"2505.20728","title":"Jigsaw-Puzzles: From Seeing to Understanding to Reasoning in Vision-Language Models","created":"2025-05-27","cited_by_count":9,"area":"lr"},{"id":"2506.07524","title":"TAI3: Testing Agent Integrity in Interpreting User Intent","created":"2025-06-09","cited_by_count":9,"area":"agents"},{"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":"2507.18452","title":"DIFFA: Large Language Diffusion Models Can Listen and Understand","created":"2025-07-24","cited_by_count":8,"area":"diffusion"},{"id":"2508.10027","title":"LLMCARE: early detection of cognitive impairment via transformer models enhanced by LLM-generated synthetic data","created":"2025-08-08","cited_by_count":8,"area":"synth"},{"id":"2510.16567","title":"Hallucination Benchmark for Speech Foundation Models","created":"2025-10-18","cited_by_count":8,"area":null},{"id":"2510.19307","title":"Unified Reinforcement and Imitation Learning for Vision-Language Models","created":"2025-10-22","cited_by_count":8,"area":"mllm"},{"id":"2511.06606","title":"SPUR: A Plug-and-Play Framework for Integrating Spatial Audio Understanding and Reasoning into Large Audio-Language Models","created":"2025-11-10","cited_by_count":8,"area":"lr"},{"id":"2511.13612","title":"P1: Mastering Physics Olympiads with Reinforcement Learning","created":"2025-11-17","cited_by_count":8,"area":"lr"},{"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":"2512.16755","title":"CitySeeker: How Do VLMS Explore Embodied Urban Navigation With Implicit Human Needs?","created":"2025-12-18","cited_by_count":8,"area":"mllm"},{"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":"2602.24195","title":"Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume","created":"2026-02-27","cited_by_count":8,"area":"mllm"},{"id":"2604.24401","title":"All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluation","created":"2026-04-27","cited_by_count":8,"area":"lr"},{"id":"2606.10400","title":"Do Vision-Language Models See or Guess? Measuring and Reducing Textual-Prior Reliance with a Phrasing-Controlled Benchmark","created":"2026-06-09","cited_by_count":8,"area":"mllm"},{"id":"2609.29429","title":"Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures","created":"2026-09-24","cited_by_count":8,"area":"safety"},{"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":"2505.20166","title":"From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data","created":"2025-05-26","cited_by_count":7,"area":"synth"},{"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":"2506.00530","title":"CityLens: Evaluating Large Vision-Language Models for Urban Socioeconomic Sensing","created":"2025-05-31","cited_by_count":7,"area":"mllm"},{"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":"2507.13361","title":"VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs","created":"2025-07-04","cited_by_count":7,"area":"lr"},{"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":"2511.00203","title":"Diffusion LLMs are Natural Adversaries for any LLM","created":"2025-10-31","cited_by_count":7,"area":"safety"}],"next_cursor":"100"}