{"total":24,"rows":[{"id":"2607.02770","title":"Gemma 4 Technical Report","created":"2026-07-02","cited_by_count":259,"area":"mllm"},{"id":"2605.27074","title":"IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams","created":"2026-05-26","cited_by_count":7,"area":"mllm"},{"id":"2606.10738","title":"Spatial-Omni: Spatial Audio Understanding Integration in Multimodal LLMs via FOA Encoding","created":"2026-06-09","cited_by_count":7,"area":"mllm"},{"id":"2606.02522","title":"Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events","created":"2026-06-01","cited_by_count":5,"area":"mllm"},{"id":"2606.00622","title":"MM-Snowball: Evaluating and Mitigating Hallucination Snowballing in Multimodal Multi-Turn Dialogue","created":"2026-05-30","cited_by_count":2,"area":"mllm"},{"id":"2607.08768","title":"UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks","created":"2026-07-09","cited_by_count":2,"area":"mllm"},{"id":"2605.22168","title":"Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability","created":"2026-05-21","cited_by_count":1,"area":"mllm"},{"id":"2606.10147","title":"From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs","created":"2026-06-08","cited_by_count":1,"area":"mllm"},{"id":"2607.22708","title":"StepX-Edge: An On-Device UI Vision-Language Model via Architecture-Training-Deployment Co-Design","created":"2026-07-20","cited_by_count":1,"area":"mllm"},{"id":"2608.10949","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","created":"2026-08-11","cited_by_count":1,"area":"mllm"},{"id":"2605.08974","title":"Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models","created":"2026-05-09","cited_by_count":0,"area":"mllm"},{"id":"2605.27038","title":"TPS-Drive: Task-Guided Representation Purification for VLM-based Autonomous Driving","created":"2026-05-26","cited_by_count":0,"area":"mllm"},{"id":"2606.19965","title":"ROSE: Benchmarking the Perception-to-Action Gap in Multimodal Models","created":"2026-06-18","cited_by_count":0,"area":"mllm"},{"id":"2607.05310","title":"Evaluating and Understanding Model Editing for Medical Vision Language Models","created":"2026-07-06","cited_by_count":0,"area":"mllm"},{"id":"2607.29637","title":"CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding","created":"2026-07-31","cited_by_count":0,"area":"mllm"},{"id":"2608.05949","title":"VLMs for Videogame Data Annotation","created":"2026-08-06","cited_by_count":0,"area":"mllm"},{"id":"2608.25529","title":"Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding Scenarios","created":"2026-08-26","cited_by_count":0,"area":"mllm"},{"id":"2608.26722","title":"UniGeo: A Multi-modal Large Language Model for Text-Guided Cross-View Geo-Localization","created":"2026-08-27","cited_by_count":0,"area":"mllm"},{"id":"2609.09852","title":"$S^3$-Bench: Evaluating Speech Interaction Models as Scientific Voice Assistants","created":"2026-09-09","cited_by_count":0,"area":"mllm"},{"id":"2609.14350","title":"Two-Stage Mixture-of-LoRA for Multi-Task Medical Vision-Language Learning","created":"2026-09-13","cited_by_count":0,"area":"mllm"},{"id":"2609.29607","title":"STRAND: Benchmarking and Improving Object-Centric Spatio-Temporal Monitoring in Video Large Language Models","created":"2026-08-28","cited_by_count":0,"area":"mllm"},{"id":"2609.39662","title":"Typographic Attack Against VLM-based AI-generated Image Detection","created":"2026-09-30","cited_by_count":0,"area":"mllm"},{"id":"2610.06399","title":"CVIF: A Criticality-Driven Visual Intervention Framework for Geometric Diagram Understanding in MLLMs","created":"2026-10-05","cited_by_count":0,"area":"mllm"},{"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}