{"total":95,"rows":[{"id":"2506.03135","title":"OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models","created":"2025-06-03","cited_by_count":114,"area":"lr"},{"id":"2510.17771","title":"Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs","created":"2025-10-20","cited_by_count":55,"area":"mllm"},{"id":"2509.18905","title":"How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective","created":"2025-09-23","cited_by_count":43,"area":"lr"},{"id":"2509.07979","title":"Visual Representation Alignment for Multimodal Large Language Models","created":"2025-09-09","cited_by_count":41,"area":"lr"},{"id":"2503.17349","title":"Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models","created":"2025-03-21","cited_by_count":37,"area":"lr"},{"id":"2510.25760","title":"Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks","created":"2025-10-29","cited_by_count":33,"area":"lr"},{"id":"2509.02359","title":"Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture","created":"2025-09-02","cited_by_count":30,"area":"lr"},{"id":"2503.11892","title":"DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning","created":"2025-03-14","cited_by_count":24,"area":null},{"id":"2511.15722","title":"Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods","created":"2025-11-14","cited_by_count":23,"area":"lr"},{"id":"2601.01984","title":"Thinking with Blueprints: Assisting Vision-Language Models in Spatial Reasoning via Structured Object Representation","created":"2026-01-05","cited_by_count":21,"area":"lr"},{"id":"2510.12184","title":"CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs","created":"2025-10-14","cited_by_count":14,"area":"lr"},{"id":"2601.12626","title":"Linear Mechanisms for Spatiotemporal Reasoning in Vision Language Models","created":"2026-01-18","cited_by_count":14,"area":"lr"},{"id":"2601.14133","title":"TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers","created":"2026-01-20","cited_by_count":14,"area":"mllm"},{"id":"2601.16007","title":"PhysicsMind: Sim and Real Mechanics Benchmarking for Physical Reasoning and Prediction in Foundational VLMs and World Models","created":"2026-01-22","cited_by_count":11,"area":"wm"},{"id":"2511.20032","title":"Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention","created":"2025-11-25","cited_by_count":9,"area":null},{"id":"2509.14837","title":"V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models","created":"2025-09-18","cited_by_count":8,"area":"mllm"},{"id":"2509.09154","title":"Mind Meets Space: Rethinking Agentic Spatial Intelligence from a Neuroscience-inspired Perspective","created":"2025-09-11","cited_by_count":7,"area":"lr"},{"id":"2601.13304","title":"CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning","created":"2026-01-19","cited_by_count":7,"area":"lr"},{"id":"2510.19555","title":"[De|Re]constructing VLMs' Reasoning in Counting","created":"2025-10-22","cited_by_count":6,"area":"lr"},{"id":"2602.00574","title":"Learning Modal-Mixed Chain-of-Thought Reasoning with Latent Embeddings","created":"2026-01-31","cited_by_count":6,"area":"lr"},{"id":"2511.18200","title":"InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity","created":"2025-11-22","cited_by_count":5,"area":"lr"},{"id":"2512.02458","title":"Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration","created":"2025-12-02","cited_by_count":5,"area":"lr"},{"id":"2601.09430","title":"Video-MSR: Benchmarking Multi-hop Spatial Reasoning Capabilities of MLLMs","created":"2026-01-14","cited_by_count":5,"area":"lr"},{"id":"2606.14703","title":"Gaze Heads: How VLMs Look at What They Describe","created":"2026-06-12","cited_by_count":5,"area":"mllm"},{"id":"2607.03358","title":"Pathways of Visual Information Flow in Vision-Language Models","created":"2026-07-03","cited_by_count":5,"area":"mllm"},{"id":"2505.21538","title":"Caption This, Reason That: VLMs Caught in the Middle","created":"2025-05-24","cited_by_count":4,"area":"lr"},{"id":"2602.04208","title":"SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models","created":"2026-02-04","cited_by_count":4,"area":"lr"},{"id":"2603.20662","title":"Attention in Space: Functional Roles of VLM Heads for Spatial Reasoning","created":"2026-03-21","cited_by_count":4,"area":"lr"},{"id":"2603.22278","title":"The Dual Mechanisms of Spatial Variable Binding in Vision-Language Models","created":"2026-03-23","cited_by_count":4,"area":"mllm"},{"id":"2604.26934","title":"World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning","created":"2026-04-29","cited_by_count":4,"area":"wm"},{"id":"2510.22118","title":"GRAID: Enhancing Spatial Reasoning of VLMs Through High-Fidelity Data Generation","created":"2025-10-25","cited_by_count":3,"area":"lr"},{"id":"2512.23328","title":"CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations","created":"2025-12-29","cited_by_count":3,"area":"lr"},{"id":"2601.00092","title":"Spatial4D-Bench: A Versatile 4D Spatial Intelligence Benchmark","created":"2025-12-31","cited_by_count":3,"area":"lr"},{"id":"2602.10146","title":"VERA: Identifying and Leveraging Visual Evidence Retrieval Heads in Long-Context Understanding","created":"2026-02-09","cited_by_count":3,"area":"mllm"},{"id":"2603.06054","title":"Probing Visual Concepts in Lightweight Vision-Language Models for Automated Driving","created":"2026-03-06","cited_by_count":3,"area":"mllm"},{"id":"2603.16506","title":"VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations","created":"2026-03-17","cited_by_count":3,"area":"lr"},{"id":"2604.15809","title":"Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow","created":"2026-04-17","cited_by_count":3,"area":"mllm"},{"id":"2605.30161","title":"Why Far Looks Up: Probing Spatial Representation in Vision-Language Models","created":"2026-05-28","cited_by_count":3,"area":"lr"},{"id":"2606.02578","title":"Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling","created":"2026-06-01","cited_by_count":3,"area":"lr"},{"id":"2509.12897","title":"Cross-Layer Vision Smoothing: Enhancing Visual Understanding via Sustained Focus on Key Objects in Large Vision-Language Models","created":"2025-09-16","cited_by_count":2,"area":"mllm"},{"id":"2510.00034","title":"Review of Hallucination Understanding in Large Language and Vision Models","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2510.08352","title":"Evaluating Small Vision-Language Models on Distance-Dependent Traffic Perception","created":"2025-10-09","cited_by_count":2,"area":"mllm"},{"id":"2602.17419","title":"EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language Models","created":"2026-02-19","cited_by_count":2,"area":"mllm"},{"id":"2603.10703","title":"WalkGPT: Grounded Vision-Language Conversation with Depth-Aware Segmentation for Pedestrian Navigation","created":"2026-03-11","cited_by_count":2,"area":"mllm"},{"id":"2603.18002","title":"Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2603.24866","title":"How Far Are Vision-Language Models from Constructing the Real World? A Benchmark for Physical Generative Reasoning","created":"2026-03-25","cited_by_count":2,"area":"lr"},{"id":"2603.27898","title":"SAGE: Sink-Aware Grounded Decoding for Multimodal Hallucination Mitigation","created":"2026-03-29","cited_by_count":2,"area":"mllm"},{"id":"2605.12586","title":"3D Primitives are a Spatial Language for VLMs","created":"2026-05-12","cited_by_count":2,"area":"mllm"},{"id":"2606.17417","title":"A Closer Look at Failure Modes in Temporal Understanding of Large Audio-Language Models","created":"2026-06-16","cited_by_count":2,"area":"lr"},{"id":"2606.29808","title":"Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework","created":"2026-06-29","cited_by_count":2,"area":"mllm"},{"id":"2506.17462","title":"General-Purpose Robotic Navigation via LVLM-Orchestrated Perception, Reasoning, and Acting","created":"2025-06-20","cited_by_count":1,"area":"lr"},{"id":"2511.13782","title":"Imagine in Space: Exploring the Frontier of Spatial Intelligence and Reasoning Efficiency in Vision Language Models","created":"2025-11-16","cited_by_count":1,"area":"wm"},{"id":"2512.24532","title":"From Building Blocks to Planning: Multi-Step Spatial Reasoning in LLMs with Reinforcement Learning","created":"2025-12-31","cited_by_count":1,"area":"lr"},{"id":"2601.13707","title":"Attention-space Contrastive Guidance for Efficient Hallucination Mitigation in LVLMs","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2602.00344","title":"When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs","created":"2026-01-30","cited_by_count":1,"area":"mllm"},{"id":"2603.02919","title":"Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers","created":"2026-03-03","cited_by_count":1,"area":"diffusion"},{"id":"2603.07474","title":"Cross-Modal Taxonomic Generalization in (Vision-) Language Models","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2603.18453","title":"Learning Consistent Temporal Grounding between Related Tasks in Sports Coaching","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2605.07148","title":"Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models","created":"2026-05-08","cited_by_count":1,"area":"mllm"},{"id":"2605.19792","title":"Mechanisms of Object Localization in Vision-Language Models","created":"2026-05-19","cited_by_count":1,"area":"mllm"},{"id":"2605.27298","title":"Self-Ensembling Vision-Language Models for Chart Data Extraction","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2608.01899","title":"SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Models","created":"2026-08-03","cited_by_count":1,"area":"lr"},{"id":"2608.22916","title":"Knowing Isn't Always Saying: When Do Spatial Encodings Reach Answers in Vision-Language Models?","created":"2026-08-24","cited_by_count":1,"area":"mllm"},{"id":"2608.23074","title":"Grounding Isn't Knowing: Do VLMs Need Object Localization for Spatial Reasoning?","created":"2026-08-24","cited_by_count":1,"area":"lr"},{"id":"2508.04097","title":"Do Vision-Language Models Leak What They Learn? Adaptive Token-Weighted Model Inversion Attacks","created":"2025-08-06","cited_by_count":0,"area":"mllm"},{"id":"2510.21842","title":"Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2510.27033","title":"A Multi-Modal Neuro-Symbolic Approach for Spatial Reasoning-Based Visual Grounding in Robotics","created":"2025-10-30","cited_by_count":0,"area":"lr"},{"id":"2511.00054","title":"SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation","created":"2025-10-28","cited_by_count":0,"area":"lr"},{"id":"2511.03908","title":"Context informs pragmatic interpretation in vision-language models","created":"2025-11-05","cited_by_count":0,"area":"mllm"},{"id":"2601.12809","title":"Left-Right Symmetry Breaking in CLIP-style Vision-Language Models Trained on Synthetic Spatial-Relation Data","created":"2026-01-19","cited_by_count":0,"area":"mllm"},{"id":"2602.02004","title":"ClueTracer: Question-to-Vision Clue Tracing for Training-Free Hallucination Suppression in Multimodal Reasoning","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2602.04356","title":"Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models","created":"2026-02-04","cited_by_count":0,"area":"mllm"},{"id":"2602.15858","title":"State Design Matters: How Representations Shape Dynamic Reasoning in Large Language Models","created":"2026-01-25","cited_by_count":0,"area":"lr"},{"id":"2602.22227","title":"Dynamic Adversarial Reinforcement Learning for Robust Multimodal Large Language Models","created":"2026-01-24","cited_by_count":0,"area":"mllm"},{"id":"2603.08291","title":"A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoning","created":"2026-03-09","cited_by_count":0,"area":"lr"},{"id":"2604.13321","title":"Why MLLMs Struggle to Determine Object Orientations","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2605.07649","title":"Operating Within the Operational Design Domain: Zero-Shot Perception with Vision-Language Models","created":"2026-05-08","cited_by_count":0,"area":"mllm"},{"id":"2605.15672","title":"VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following","created":"2026-05-15","cited_by_count":0,"area":"mllm"},{"id":"2606.01612","title":"Self-Improving Small Object Grounding in LVLMs","created":"2026-06-01","cited_by_count":0,"area":"mllm"},{"id":"2606.31467","title":"AeroVerse-SatAgent: UAV-Satellite Collaborative Spatial Reasoning Inspired by the Dual Visual Pathway Theory of Cognitive Neuroscience","created":"2026-06-30","cited_by_count":0,"area":"lr"},{"id":"2607.02593","title":"Token-level Response-visual Attention Guidance for Multimodal LLMs Knowledge Distillation","created":"2026-07-01","cited_by_count":0,"area":"mllm"},{"id":"2607.18325","title":"Hazard or Anomaly? Evaluating VLMs for Understanding Dangers and Discrepancies","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2607.21085","title":"Geo3R: Mitigating Spatial Reasoning Hallucination in Multimodal Large Language Models","created":"2026-07-23","cited_by_count":0,"area":"lr"},{"id":"2608.15075","title":"SA-GEM: Scale-Adaptive and Geospatial Evidence-Modulated Token Pruning for Efficient Remote Sensing Large Vision-Language Models","created":"2026-08-15","cited_by_count":0,"area":"mllm"},{"id":"2608.29571","title":"Which one is banana man? Evaluating vision-language models in multi-turn pragmatic interpretation","created":"2026-08-30","cited_by_count":0,"area":"mllm"},{"id":"2609.24813","title":"INTCORT: Training-Free Spatial Reasoning Enhancement for Vision-Language Models via Input Transformations and Confidence Routing","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.32292","title":"Affordance-Conditioned Decision Making: Bridging the Semantic-Spatial Gap in Zero-Shot Cross-Floor Vision-and-Language Navigation","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34408","title":"Distilling Visual Reasoning into Text Space","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.35272","title":"When Words Speak Louder than Images: Towards Understanding Language Bias in Vision-Language Models","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2609.35486","title":"Who Is Left of Whom? Tracing Spatial Evidence and Role Binding in Relative-Position Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.37263","title":"Beyond Attention Imbalance: Mitigating Hallucinations via Spectral Surgery","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2609.38716","title":"SpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision--Language Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.38717","title":"Soft Spatial Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.07646","title":"Matching Object or Relation? Tracing Abstract Reasoning Inside VLMs","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.13527","title":"S-Space: Exploring Spatial Workspace in Multimodal Language Models","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}