{"total":78,"rows":[{"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":"2605.25343","title":"Toward Native Multimodal Modeling: A Roadmap","created":"2026-05-25","cited_by_count":7,"area":"wm"},{"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":"2606.30534","title":"Orca: The World is in Your Mind","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2609.13814","title":"Realtime-Venus: A full-duplex interaction system with asynchronous delegation","created":"2026-09-12","cited_by_count":4,"area":null},{"id":"2609.21967","title":"NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities","created":"2026-09-18","cited_by_count":4,"area":null},{"id":"2605.28192","title":"Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual Reasoning","created":"2026-05-27","cited_by_count":3,"area":"lr"},{"id":"2606.24286","title":"AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression","created":"2026-06-23","cited_by_count":3,"area":"mllm"},{"id":"2607.19339","title":"OmniReasoner: Thinking with Long Audio-Video via Native Tool Use","created":"2026-07-21","cited_by_count":3,"area":"lr"},{"id":"2607.20166","title":"Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning","created":"2026-07-22","cited_by_count":3,"area":"lr"},{"id":"2608.03812","title":"OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models","created":"2026-08-04","cited_by_count":3,"area":"inference"},{"id":"2608.05703","title":"StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding","created":"2026-08-06","cited_by_count":3,"area":"agents"},{"id":"2609.08977","title":"Multimodal Duplex Interaction Agent","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2605.16403","title":"When Vision Speaks for Sound","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2606.12125","title":"ReUnit: Multi-Granularity Visual Unitization for Long Video Understanding","created":"2026-06-10","cited_by_count":2,"area":"mllm"},{"id":"2607.04443","title":"Wan-Streamer v0.2: Higher Resolution, Same Latency","created":"2026-07-05","cited_by_count":2,"area":null},{"id":"2609.17360","title":"Same Words, Different Actions: Paired Turn-Taking Evaluation under Rewritten Dialogue Contexts","created":"2026-09-15","cited_by_count":2,"area":null},{"id":"2609.27389","title":"EvoAudio: Recursive Self-Improvement for Audio Understanding","created":"2026-09-23","cited_by_count":2,"area":"synth"},{"id":"2609.37818","title":"Thinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken Dialogue","created":"2026-09-29","cited_by_count":2,"area":null},{"id":"2605.01766","title":"Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time","created":"2026-05-03","cited_by_count":1,"area":"mllm"},{"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":"2608.26517","title":"HUG-VIS: A Multimodal Benchmark for Human-centered Understanding and Generation in Visual Intelligence","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.03423","title":"DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2609.17416","title":"Never Stop Thinking: Continuous-Time Language Agents","created":"2026-07-11","cited_by_count":1,"area":"lr"},{"id":"2609.19596","title":"Full-Duplex Speech Models Take the Floor When Asked, Not When Needed","created":"2026-09-17","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":"2609.31193","title":"Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMs","created":"2026-09-25","cited_by_count":1,"area":"lr"},{"id":"2609.34247","title":"SALMONN-duo: Adaptive Dual-System Coordination for Full-Duplex Voice Agents","created":"2026-09-28","cited_by_count":1,"area":"agents"},{"id":"2605.15300","title":"Deep Pre-Alignment for VLMs","created":"2026-05-14","cited_by_count":0,"area":"mllm"},{"id":"2606.24477","title":"video-SALMONN-R$^3$: Learning to ReWatch, ReAsk, and ReAnswer for Efficient Video Understanding","created":"2026-06-23","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":"2607.02640","title":"Metronome: Bound the Cache, Keep the Beat for Real-Time Interaction Model Serving","created":"2026-07-02","cited_by_count":0,"area":"inference"},{"id":"2607.10162","title":"Hearing Like Humans? Sound Symbolism and Perceptual Alignment in Speech Language Models","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.21151","title":"V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure","created":"2026-07-23","cited_by_count":0,"area":"alignment"},{"id":"2608.07631","title":"PACE: A Playback-Aligned Context Engine for LLM-Based Full-Duplex Voice Dialogue","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.08067","title":"DialectS2S: End-to-End Speech Dialogue Modeling for Low-Resource Chinese Dialects","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.09158","title":"From Inaudible Inputs to Model Failures: Low-Frequency Safety Risks in LALMs","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.09593","title":"MADBench: A Benchmark for Modality-Aware Audio Deepfake Detection","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.24160","title":"OmniJudge or OmniBias? Diagnosing Multimodal Judges through Balanced, Decoupled Lenses","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.29120","title":"HEAR Who Said What: Unlocking Speaker-Attributed Reasoning via Counterfactual Voice Grounding","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2609.04242","title":"Training-Free Speech-Centric Omni Understanding with Frozen VLMs","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.10947","title":"The Platonic brain bridge hypothesis: human brain networks as an architectural prior for multimodal large language models","created":"2026-09-10","cited_by_count":0,"area":"mllm"},{"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":"2609.25738","title":"OmniFysics-Nano-V2 Technical Report: Understanding the Physical World Across Modalities","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.29792","title":"TimeBraid: Unifying Time Series and Language for Understanding and Forecasting","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.30670","title":"TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.31224","title":"Acoustic-to-Text KV Compression for Full-Duplex Speech Models","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.31714","title":"OmniFysics-Captioner Technical Report: Grounding Omni-Modal Understanding in the Physical World for Better Captioning","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.32569","title":"OmniSmartHome: A Multimodal Reasoning Benchmark for Smart-Home Agents","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.32574","title":"CUE-Mem: Benchmarking Long-Term User Memory via Implicit Cues in Multimodal Conversations","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32763","title":"Mandela-Bench: Multimodal Models Remember Canonical Images Instead of Seeing Them","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33585","title":"IVT-Guard: All-in-One Reasoning Model for AI-Generated Content Detection","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.34223","title":"Uncovering Ordinal-Matching Bias in Audio-Visual LLMs","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34363","title":"SyncRA: Learning Temporal Correspondence in Omni-Modal Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34653","title":"OmniTide: Co-Designing Algorithms and Systems for Efficient On-Device Omni-LLM Streaming","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2609.34854","title":"AUV-Bench: Aesthetic Understanding and Generation Evaluation for User Interfaces","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35115","title":"DuplexCadence: Exact State and Execution from a Speech Model's Declared Timelines","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37035","title":"Watch-Think-Interact: Bootstrapping Long-Horizon Multi-Turn Streaming Video Reasoning with Reinforcement Learning","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":"2609.39847","title":"SEAR: Spoofing Evidence-Grounded Audio Reasoning Benchmark for Audio Language Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39938","title":"LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02181","title":"OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.05274","title":"Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05775","title":"InteractionBench: A Real-Time Interaction Benchmark for Streaming Video Systems","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.06949","title":"AdaLoop: Adaptive-Depth Latent Reasoning for Audio Language Models","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.07533","title":"SkillFormer: Skill-Decomposed Adaptation for Audio Language Models","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.08125","title":"Conversation Is a Two-Body Problem: Dyadic Evaluation of Full-Duplex Dialogue Models","created":"2026-10-06","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":"2610.11299","title":"DuplexAgent-RSI: Recursive Harness Improvement for Full-Duplex Voice Agent Collaboration","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.11948","title":"When History Helps and Hurts: Selective History Use across Multimodal Turns","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12214","title":"DiffuPlex: Accelerating Full-Duplex Spoken Dialog Models via Rolling Masked Diffusion","created":"2026-10-08","cited_by_count":0,"area":"diffusion"},{"id":"2610.12248","title":"EgoVoice: Proactive Spoken Assistance from Egocentric Multimodal Streams","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12458","title":"OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.16933","title":"Estimating Uncertainty of Omnimodal Large Language Models via External Omnimodal Embeddings","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":"2610.17738","title":"DuplexAct: How Interactive Are Frontier Full-Duplex Spoken Language Models?","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":"2610.18829","title":"OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding","created":"2026-10-13","cited_by_count":0,"area":"mllm"}],"next_cursor":null}