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
Ovis2.5 Technical Report
Baseline reference. 62% of citing Pith papers use this work as a benchmark or comparison.
25
Pith papers citing it
Baseline
62% of classified citations
abstract
We present Ovis2.5, a successor to Ovis2 designed for native-resolution visual perception and strong multimodal reasoning. Ovis2.5 integrates a native-resolution vision transformer that processes images at their native, variable resolutions, avoiding the degradation from fixed-resolution tiling and preserving both fine detail and global layout -- crucial for visually dense content like complex charts. To strengthen reasoning, we train the model to move beyond linear chain-of-thought and perform reflection -- including self-checking and revision. This advanced capability is exposed as an optional "thinking mode" at inference time, allowing users to trade latency for enhanced accuracy on difficult inputs. The model is trained via a comprehensive five-phase curriculum that progressively builds its skills. The process begins with foundational visual and multimodal pretraining, advances through large-scale instruction tuning, and culminates in alignment and reasoning enhancement using DPO and GRPO. To scale these upgrades efficiently, we employ multimodal data packing and hybrid parallelism, yielding a significant end-to-end speedup. We release two open-source models: Ovis2.5-9B and Ovis2.5-2B. The latter continues the "small model, big performance" philosophy of Ovis2, making it ideal for resource-constrained, on-device scenarios. On the OpenCompass multimodal leaderboard, Ovis2.5-9B averages 78.3, marking a substantial improvement over its predecessor, Ovis2-8B, and achieving state-of-the-art results among open-source MLLMs in the sub-40B parameter range; Ovis2.5-2B scores 73.9, establishing SOTA for its size. Beyond aggregate scores, Ovis2.5 achieves leading results on STEM benchmarks, exhibits strong capabilities on grounding and video tasks, and achieves open-source SOTA at its scale for complex chart analysis.
hub tools
citation-role summary
baseline 8
background 4
other 1
citation-polarity summary
representative citing papers
TABALIGN pairs a diffusion language model planner emitting binary cell masks with a trained attention verifier, raising average accuracy 15.76 points over strong baselines on eight table benchmarks while speeding execution 44.64%.
Evidence utility is defined as information gain on the model's output distribution, with ranking by gain on a latent helpfulness variable shown equivalent to answer-space utility under mild assumptions, enabling a training-free surrogate framework that outperforms baselines.
Chronicles-OCR is the first benchmark with 2,800 images across the complete evolutionary trajectory of Chinese characters, defining four tasks to evaluate VLLMs' cross-temporal visual perception.
EditRefiner uses a perception-reasoning-action-evaluation agent loop and the EditFHF-15K human feedback dataset to refine text-guided image edits more accurately than prior methods.
TopBench is a new benchmark exposing that LLMs default to table lookups instead of intent-aware predictive reasoning on tabular data, with intent disambiguation as a key prerequisite.
FCMBench-Video is a new benchmark with 1,200 videos and 11k QA instances for evaluating Video-MLLMs on document video understanding across 28 document types.
A fixed 1.2B model trained via diversity-aware sampling, cross-model verification, annotation refinement, and progressive stages achieves new state-of-the-art document parsing accuracy of 95.69 on OmniDocBench v1.6.
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.
VISTA-Bench shows vision-language models degrade on visualized text in images compared to equivalent pure text, with larger gaps under increased perceptual difficulty.
VLMs fail to ground numerical values in spatial perception on new bidirectional tasks, relying on shallow cues instead of coordinate-aware representations.
A foveated VLM trained for scene comprehension produces human-like fixations, outperforming models trained for search, classification, or with altered peripheral vision.
SceneGraphVLM generates dynamic scene graphs from video using compact VLMs, TOON serialization, and hallucination-aware RL to improve precision and achieve one-second latency.
ReasonEdit uses a new CoT dataset and reinforcement learning to produce interpretable, human-aligned evaluations of text-guided image edits.
POINTS-Long is a dual-mode multimodal large language model that uses dynamic visual token scaling to retain 97.7-99.7% accuracy on long-form tasks with 1/40 to 1/10th the tokens and supports streaming via detachable KV-cache.
Q-Zoom achieves up to 4.39x inference speedup in high-resolution MLLM scenarios via query-aware gating and region localization, matching or exceeding baseline accuracy on document and high-res benchmarks.
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.
ITIScore evaluates MLLM image captions via image-to-text-to-image reconstruction consistency and aligns with human judgments on a new 40K-caption benchmark.
BrainMem equips LLM-based embodied planners with working, episodic, and semantic memory that evolves interaction histories into retrievable knowledge graphs and guidelines, raising success rates on long-horizon 3D benchmarks.
MapTab is a new multimodal benchmark with 328 images and nearly 200k queries that shows current MLLMs have substantial difficulty with multi-criteria route planning when visual and tabular information must be combined.
Single-agent LLM frameworks outperform naive multi-agent systems in multimodal clinical risk prediction tasks and are better calibrated.
An 8B MLLM reaches state-of-the-art efficiency and performance under 30B by combining a unified 3D resampler, joint document-text training, and hybrid RL for reasoning modes.
iDiff is a dual-branch framework with an Answer Model for robust pairwise preference prediction via view decomposition and ensembles, and a Thinking Model for structured rationale generation using templates and answer-aware supervision, winning first place in the NTIRE 2026 RAIM challenge.
OmniFysics is an omni-modal network using a dynamic physical data engine and evolutive tuning to improve performance on multimodal benchmarks and physics-oriented tasks.
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.
-
From Table to Cell: Attention for Better Reasoning with TABALIGN
TABALIGN pairs a diffusion language model planner emitting binary cell masks with a trained attention verifier, raising average accuracy 15.76 points over strong baselines on eight table benchmarks while speeding execution 44.64%.
-
Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation
Evidence utility is defined as information gain on the model's output distribution, with ranking by gain on a latent helpfulness variable shown equivalent to answer-space utility under mild assumptions, enabling a training-free surrogate framework that outperforms baselines.
-
Chronicles-OCR: A Cross-Temporal Perception Benchmark for the Evolutionary Trajectory of Chinese Characters
Chronicles-OCR is the first benchmark with 2,800 images across the complete evolutionary trajectory of Chinese characters, defining four tasks to evaluate VLLMs' cross-temporal visual perception.
-
EditRefiner: A Human-Aligned Agentic Framework for Image Editing Refinement
EditRefiner uses a perception-reasoning-action-evaluation agent loop and the EditFHF-15K human feedback dataset to refine text-guided image edits more accurately than prior methods.
-
TopBench: A Benchmark for Implicit Prediction and Reasoning over Tabular Question Answering
TopBench is a new benchmark exposing that LLMs default to table lookups instead of intent-aware predictive reasoning on tabular data, with intent disambiguation as a key prerequisite.
-
FCMBench-Video: Benchmarking Document Video Intelligence
FCMBench-Video is a new benchmark with 1,200 videos and 11k QA instances for evaluating Video-MLLMs on document video understanding across 28 document types.
-
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
A fixed 1.2B model trained via diversity-aware sampling, cross-model verification, annotation refinement, and progressive stages achieves new state-of-the-art document parsing accuracy of 95.69 on OmniDocBench v1.6.
-
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.
-
VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?
VISTA-Bench shows vision-language models degrade on visualized text in images compared to equivalent pure text, with larger gaps under increased perceptual difficulty.
-
SPACENUM: Revisiting Spatial Numerical Understanding in VLMs
VLMs fail to ground numerical values in spatial perception on new bidirectional tasks, relying on shallow cues instead of coordinate-aware representations.
-
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.
-
SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models
SceneGraphVLM generates dynamic scene graphs from video using compact VLMs, TOON serialization, and hallucination-aware RL to improve precision and achieve one-second latency.
-
ReasonEdit: Towards Interpretable Image Editing Evaluation via Reinforcement Learning
ReasonEdit uses a new CoT dataset and reinforcement learning to produce interpretable, human-aligned evaluations of text-guided image edits.
-
POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs
POINTS-Long is a dual-mode multimodal large language model that uses dynamic visual token scaling to retain 97.7-99.7% accuracy on long-form tasks with 1/40 to 1/10th the tokens and supports streaming via detachable KV-cache.
-
Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models
Q-Zoom achieves up to 4.39x inference speedup in high-resolution MLLM scenarios via query-aware gating and region localization, matching or exceeding baseline accuracy on document and high-res benchmarks.
-
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.
-
ITIScore: An Image-to-Text-to-Image Rating Framework for the Image Captioning Ability of MLLMs
ITIScore evaluates MLLM image captions via image-to-text-to-image reconstruction consistency and aligns with human judgments on a new 40K-caption benchmark.
-
BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planning
BrainMem equips LLM-based embodied planners with working, episodic, and semantic memory that evolves interaction histories into retrievable knowledge graphs and guidelines, raising success rates on long-horizon 3D benchmarks.
-
MapTab: Are MLLMs Ready for Multi-Criteria Route Planning in Heterogeneous Graphs?
MapTab is a new multimodal benchmark with 328 images and nearly 200k queries that shows current MLLMs have substantial difficulty with multi-criteria route planning when visual and tabular information must be combined.
-
AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks
Single-agent LLM frameworks outperform naive multi-agent systems in multimodal clinical risk prediction tasks and are better calibrated.
-
MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
An 8B MLLM reaches state-of-the-art efficiency and performance under 30B by combining a unified 3D resampler, joint document-text training, and hybrid RL for reasoning modes.
-
iDiff: Interpretable Difference-aware Framework for Pairwise Image Quality Assessment
iDiff is a dual-branch framework with an Answer Model for robust pairwise preference prediction via view decomposition and ensembles, and a Thinking Model for structured rationale generation using templates and answer-aware supervision, winning first place in the NTIRE 2026 RAIM challenge.
-
OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization
OmniFysics is an omni-modal network using a dynamic physical data engine and evolutive tuning to improve performance on multimodal benchmarks and physics-oriented tasks.
- EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs