SenseBench is the first physics-based benchmark with 10K+ instances and dual protocols to evaluate VLMs on remote sensing low-level perception and diagnostic description, revealing domain bias and specific failure modes.
hub Baseline reference
Ovis: Structural embedding alignment for multimodal large language model
Baseline reference. 88% of citing Pith papers use this work as a benchmark or comparison.
27
Pith papers citing it
Baseline
88% of classified citations
hub tools
citation-role summary
baseline 7
background 1
citation-polarity summary
representative citing papers
MLLMs drop from over 85% accuracy on action presence to under 50% on matched action-denial videos, exposing a causal verification gap that causal graph prompts partially close.
SSMNBench shows that MLLMs suffer distraction degradation on single-view-sufficient tasks and fail to integrate geometric evidence across views, instead relying on semantic averaging and view preference.
Sci-Rho is a dynamic multilingual visually-grounded symbolic benchmark for STEM problems that reveals robustness gaps in current VLMs between average and worst-case performance.
ST-BiBench reveals a coordination paradox in which MLLMs show strong high-level strategic reasoning yet fail at fine-grained 16-dimensional bimanual action synthesis and multi-stream fusion.
CamReasoner uses structured O-T-A reasoning and RL on 56k samples to lift camera movement classification from 73.8% to 78.4% and VQA from 60.9% to 74.5% on Qwen2.5-VL-7B.
OCRBench v2 is a new benchmark with four times more tasks than prior versions that reveals most large multimodal models score below 50 out of 100 on visual text tasks and share five specific weaknesses.
MMGist filters 23,250 items from 18 benchmarks down to 7,262 using three-stage pipeline, preserving model rankings (Spearman ρ=0.98) while cutting items 69% and raising discrimination 78%.
A foveated VLM trained for scene comprehension produces human-like fixations, outperforming models trained for search, classification, or with altered peripheral vision.
DDA-Thinker decouples planning from generation and applies dual-atomic RL with checklist-based rewards to boost reasoning in image editing, yielding competitive results on RISE-Bench and KRIS-Bench.
MAPO improves multimodal chain-of-thought reasoning by requiring explicit textual descriptions of visual tool results and using a novel advantage estimator that combines semantic alignment with task rewards.
AICA-Bench evaluates 23 VLMs on affective image analysis, identifies weak intensity calibration and shallow descriptions as limitations, and proposes training-free Grounded Affective Tree Prompting to improve performance.
Vision-language models consistently lose accuracy when a question’s text is rendered into an image, and the loss grows with perceptual difficulty like small fonts and handwriting.
OmniDrive-R1 boosts VLM reasoning score from 51.77% to 80.35% and answer accuracy from 37.81% to 73.62% on DriveLMM-o1 via reinforcement-driven interleaved multi-modal chain-of-thought with annotation-free grounding.
InternVL3.5 advances open-source multimodal models with Cascade RL for +16% reasoning gains and ViR for 4x inference speedup, with the 241B model reaching SOTA among open-source MLLMs on multimodal, reasoning, and agentic tasks.
LPO optimizes GUI agent positional accuracy by combining information entropy for zone selection with a physical-distance reward inside a Group Relative Preference Optimization framework, claiming SOTA results on benchmarks and online tests.
Circle-RoPE achieves cross-modal positional disentanglement in VLMs by mapping 2D image tokens to a cone-like annulus orthogonal to the text axis, with PTD=0 eliminating RoPE geometric bias while preserving intra-image structure via alternating geometry encoding.
InternVL3-78B sets a new open-source SOTA of 72.2 on MMMU via native joint multimodal pre-training, V2PE, MPO, and test-time scaling while remaining competitive with proprietary models.
InternVL 2.5 is the first open-source MLLM to surpass 70% on the MMMU benchmark via model, data, and test-time scaling, with a 3.7-point gain from chain-of-thought reasoning.
LLaVA-CoT adds autonomous multistage reasoning to vision-language models, delivering 9.4% gains over its base model and outperforming larger models like Gemini-1.5-pro on reasoning benchmarks via a 100k annotated dataset and SWIRES test-time scaling.
Proposes reasoning-prefix masking during VLM distillation to anchor student thinking on visual evidence and improve multimodal reasoning in smaller models.
GETok partitions images with grid tokens and refines locations via offset tokens to enable better native 2D spatial reasoning in MLLMs.
ReVisiT refines LVLM output distributions during decoding by projecting selected vision tokens into text space via context-aware constrained divergence minimization.
VisShield with OPTIC dataset enables VLMs to localize and mask private text in vision data via instruction tuning for privacy preservation.
citing papers explorer
-
SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models
SenseBench is the first physics-based benchmark with 10K+ instances and dual protocols to evaluate VLMs on remote sensing low-level perception and diagnostic description, revealing domain bias and specific failure modes.
-
Learning to Deny: Action Denial in Multimodal Large Language Models
MLLMs drop from over 85% accuracy on action presence to under 50% on matched action-denial videos, exposing a causal verification gap that causal graph prompts partially close.
-
SSMNBench: Diagnosing Image-based Cross-View Human-Object Understanding via Single-View Sufficiency and Multi-View Necessity
SSMNBench shows that MLLMs suffer distraction degradation on single-view-sufficient tasks and fail to integrate geometric evidence across views, instead relying on semantic averaging and view preference.
-
Sci-Rho: A Multilingual Visually-Grounded Symbolic Benchmark for STEM Problems
Sci-Rho is a dynamic multilingual visually-grounded symbolic benchmark for STEM problems that reveals robustness gaps in current VLMs between average and worst-case performance.
-
ST-BiBench: Benchmarking Multi-Stream Multimodal Coordination in Bimanual Embodied Tasks for MLLMs
ST-BiBench reveals a coordination paradox in which MLLMs show strong high-level strategic reasoning yet fail at fine-grained 16-dimensional bimanual action synthesis and multi-stream fusion.
-
CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning
CamReasoner uses structured O-T-A reasoning and RL on 56k samples to lift camera movement classification from 73.8% to 78.4% and VQA from 60.9% to 74.5% on Qwen2.5-VL-7B.
-
OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning
OCRBench v2 is a new benchmark with four times more tasks than prior versions that reveals most large multimodal models score below 50 out of 100 on visual text tasks and share five specific weaknesses.
-
MMGist: A Comprehensive Multimodal Benchmark for 2027
MMGist filters 23,250 items from 18 benchmarks down to 7,262 using three-stage pipeline, preserving model rankings (Spearman ρ=0.98) while cutting items 69% and raising discrimination 78%.
-
Why We Look Where We Look: Emergent Human-like Fixations of a Foveated Visual Language Model Maximizing Scene Understanding
A foveated VLM trained for scene comprehension produces human-like fixations, outperforming models trained for search, classification, or with altered peripheral vision.
-
DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing
DDA-Thinker decouples planning from generation and applies dual-atomic RL with checklist-based rewards to boost reasoning in image editing, yielding competitive results on RISE-Bench and KRIS-Bench.
-
Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization
MAPO improves multimodal chain-of-thought reasoning by requiring explicit textual descriptions of visual tool results and using a novel advantage estimator that combines semantic alignment with task rewards.
-
AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysis
AICA-Bench evaluates 23 VLMs on affective image analysis, identifies weak intensity calibration and shallow descriptions as limitations, and proposes training-free Grounded Affective Tree Prompting to improve performance.
-
VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?
Vision-language models consistently lose accuracy when a question’s text is rendered into an image, and the loss grows with perceptual difficulty like small fonts and handwriting.
-
OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving
OmniDrive-R1 boosts VLM reasoning score from 51.77% to 80.35% and answer accuracy from 37.81% to 73.62% on DriveLMM-o1 via reinforcement-driven interleaved multi-modal chain-of-thought with annotation-free grounding.
-
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
InternVL3.5 advances open-source multimodal models with Cascade RL for +16% reasoning gains and ViR for 4x inference speedup, with the 241B model reaching SOTA among open-source MLLMs on multimodal, reasoning, and agentic tasks.
-
LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization
LPO optimizes GUI agent positional accuracy by combining information entropy for zone selection with a physical-distance reward inside a Group Relative Preference Optimization framework, claiming SOTA results on benchmarks and online tests.
-
Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language Models
Circle-RoPE achieves cross-modal positional disentanglement in VLMs by mapping 2D image tokens to a cone-like annulus orthogonal to the text axis, with PTD=0 eliminating RoPE geometric bias while preserving intra-image structure via alternating geometry encoding.
-
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
InternVL3-78B sets a new open-source SOTA of 72.2 on MMMU via native joint multimodal pre-training, V2PE, MPO, and test-time scaling while remaining competitive with proprietary models.
-
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
InternVL 2.5 is the first open-source MLLM to surpass 70% on the MMMU benchmark via model, data, and test-time scaling, with a 3.7-point gain from chain-of-thought reasoning.
-
LLaVA-CoT: Let Vision Language Models Reason Step-by-Step
LLaVA-CoT adds autonomous multistage reasoning to vision-language models, delivering 9.4% gains over its base model and outperforming larger models like Gemini-1.5-pro on reasoning benchmarks via a 100k annotated dataset and SWIRES test-time scaling.
-
Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation
Proposes reasoning-prefix masking during VLM distillation to anchor student thinking on visual evidence and improve multimodal reasoning in smaller models.
-
Grounding Everything in Tokens for Multimodal Large Language Models
GETok partitions images with grid tokens and refines locations via offset tokens to enable better native 2D spatial reasoning in MLLMs.
-
Revisit What You See: Revealing Visual Semantics in Vision Tokens to Guide LVLM Decoding
ReVisiT refines LVLM output distributions during decoding by projecting selected vision tokens into text space via context-aware constrained divergence minimization.
-
Vision Language Model Helps Private Information De-Identification in Vision Data
VisShield with OPTIC dataset enables VLMs to localize and mask private text in vision data via instruction tuning for privacy preservation.
-
VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
VITA-1.5 integrates vision and speech into a single LLM through multi-stage training, delivering competitive benchmark results on image, video, and speech tasks with near real-time response speed.
-
Improving Multimodal Reasoning via Worst Dimension Optimization
Proposes Worst Dimension Optimization to address equal-weighting limitations in Process Reward Models for multimodal reasoning.
-
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
PaddleOCR-VL-1.6 improves on PaddleOCR-VL-1.5 via region-aware data optimization and progressive post-training to reach 96.33% on OmniDocBench v1.6.