{"total":70,"rows":[{"id":"2605.07061","title":"Do Joint Audio-Video Generation Models Understand Physics?","created":"2026-05-08","cited_by_count":8,"area":null},{"id":"2606.19336","title":"Learning User Simulators with Turing Rewards","created":"2026-06-17","cited_by_count":7,"area":null},{"id":"2606.25041","title":"Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models","created":"2026-06-23","cited_by_count":7,"area":null},{"id":"2606.07229","title":"MMAE: A Massive Multitask Audio Editing Benchmark","created":"2026-06-05","cited_by_count":5,"area":null},{"id":"2605.11363","title":"PresentAgent-2: Towards Generalist Multimodal Presentation Agents","created":"2026-05-12","cited_by_count":4,"area":null},{"id":"2605.21041","title":"Conditioning Gaussian Processes on Almost Anything","created":"2026-05-20","cited_by_count":4,"area":null},{"id":"2605.12056","title":"OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2605.20035","title":"Stage-adaptive Token Selection for Efficient Omni-modal LLMs","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2607.00920","title":"GMO-E$^2$DIT: Grounded Multi-Operation Editing for E-Commerce Images","created":"2026-07-01","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":"2605.06053","title":"Towards Generation-Efficient Uncertainty Estimation in Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.08820","title":"FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence","created":"2026-05-09","cited_by_count":2,"area":null},{"id":"2605.09640","title":"Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2608.24168","title":"FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generation","created":"2026-08-25","cited_by_count":2,"area":null},{"id":"2608.26005","title":"VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction","created":"2026-08-26","cited_by_count":2,"area":null},{"id":"2605.07593","title":"TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.08762","title":"Omni-DeepSearch: A Benchmark for Audio-Driven Omni-Modal Deep Search","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2606.01016","title":"PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2606.24255","title":"Social Structure Matters in 3D Human-Human Interaction Generation","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2607.01590","title":"Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2608.04355","title":"The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2609.08275","title":"Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generation","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2609.21392","title":"Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal Interaction","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2609.23417","title":"Omni2Web: Benchmarking Audiovisual Website Development","created":"2026-09-20","cited_by_count":1,"area":null},{"id":"2606.09590","title":"Clinically Grounded Privacy Evaluation of Medical LMs","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.12025","title":"Human-Enhanced Loop Modeling (HELM): Agent-Based Finite Element Modeling of Concrete Bridge Barriers","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.13768","title":"CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.20295","title":"Token-Operations-Oriented Inference Optimization Techniques for Large Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.20970","title":"CogniRoute: Learning to Route Social Evidence in Omni-Modal Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.23271","title":"Scaling LLM Knowledge Boundaries via Distribution-Optimized Synthesis","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.26968","title":"RedVox: Safety and Fairness Gaps in Speech Models Across Languages","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.08317","title":"Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.22561","title":"Codifying the Judge: Scalable Evaluation via Program Distillation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.27109","title":"MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.05154","title":"RIG-RoPE: Relation-Stratified Multimodal Attention with Instance-Local Rotary Geometry and Representation-Aware Traversal Coordinates","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2608.07067","title":"DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understanding","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.07917","title":"TongGuOCR: A Layout-Aware and Token-Augmented OCR MLLM for Chinese Historical Documents","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.12898","title":"TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.13681","title":"Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretraining, Debugging-Aware SFT, and Task-Specific SFT","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.16717","title":"PersonaShot: Benchmarking Person-Centric Narrative Continuity in Multi-Shot Video Generation","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.24877","title":"From Seeing to Acting: Smart Glasses as First-Person Intelligence Platforms","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.25559","title":"AdaVDR: Adaptive Tool Use and Reflection for Video Deep Research","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.04196","title":"Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.10706","title":"HuRo: Robotizing Human Videos for Scalable VLA Pretraining","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.15393","title":"CodeTS: Verifiable Text-to-Time Series Generation via Executable Code","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.21465","title":"OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.22214","title":"The Bairong System for MLC-SLM 2026: Dynamic Question-Aware Evidence Routing for Multilingual Conversational Speech Understanding","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.22385","title":"Active Spatial Inspection for Effective and Efficient Embodied Exploration","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.25738","title":"OmniFysics-Nano-V2 Technical Report: Understanding the Physical World Across Modalities","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.36290","title":"The Surge of Anti-Semitism in German Social Media following the October 7 Attacks","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36563","title":"AffectReveal: Event-Grounded Emotion Recognition Beyond Visual Appearances","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38530","title":"Shifting Mechanisms: How Positional Encoding Choice Shapes In-Context Retrieval","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39446","title":"DuplexAct-Bench: Broadening Full-Duplex Speech Evaluation toward Proactive Interaction across Diverse Behavioral Requirements","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39827","title":"Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02388","title":"Octrees as an Explicit 3D Language","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04392","title":"Detecting Defects that Matter: An Application-Driven Benchmark for Anomaly Detection in Manufacturing and Retail Logistics (VAND 4.0 Challenge)","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.06345","title":"Breaking Bureaucracy: Evaluating open-source LLMs for legal document review","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.06505","title":"Improving Proactive AI Assistance with Hierarchical Procedural Understanding","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.06611","title":"Lens3D: Target-Conditioned Visual Foveation for Fine-Grained 3D Understanding","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.06955","title":"ROMA: LLM System for Real-World Object-Centric Multi-Sensory Active Perception","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.09588","title":"Adaptive Code Generation for Controlling Robots","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.10624","title":"SAVU-BENCH: A Real-World Benchmark for Spatial Audio-Visual Understanding","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.11736","title":"Towards Unified Evaluation of Prompt Enhancers for Video Generation","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.16260","title":"ScreenASR-Bench: A Tiered Benchmark for Speech Recognition with Visual Context","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17124","title":"D2: High-Capability Full-Duplex Spoken Language Models from Half-Duplex Backbones","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18141","title":"Mitigating Cross-Modal Hallucinations by Correcting Modality Misrouting in Omnimodal LLMs","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18247","title":"PACT: A Pragmatic Prompting Framework for Expressive and Voice-Preserving Speech-to-Speech Translation","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18499","title":"EgoOmniWorld: Unifying Egocentric Understanding via Ego-Action-World Interactions","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19166","title":"Fantastic Metrics and How to Find Them: Meta-Evaluating Metrics for Multi-lingual Style-Personalized Generation","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}