DataComp-VLM benchmark shows instruction-heavy data mixing outperforms filtering for VLM training, with DCVLM-Baseline achieving 63.6% on 33 tasks for 8B models (+5.4pp over FineVision).
hub Tool reference
Seed-bench-2-plus: Benchmarking multimodal large language models with text-rich visual comprehension
Tool reference. 86% of classified Pith citations use this work as a method, library, or software dependency, not as a substantive claim.
19
Pith papers citing it
Method reference
86% of classified citations
hub tools
citation-role summary
dataset 6
background 1
citation-polarity summary
representative citing papers
MME-RealWorld is the largest manually annotated high-resolution benchmark for MLLMs, where even the best models achieve less than 60% accuracy on challenging real-world tasks.
CapRL++ applies reinforcement learning with verifiable rewards to dense image and video captioning by scoring captions via the accuracy of a vision-free LLM answering MCQs from the caption alone.
Laser reformulates visual reasoning via Dynamic Windowed Alignment Learning to maintain latent superposition of global features, delivering 5.03% average gains over Monet and over 97% fewer inference tokens on six benchmarks.
FinCriticalED benchmark reveals that OCR and MLLM systems frequently fail to preserve critical financial facts such as numbers and monetary units even when lexical accuracy is high.
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.
StochasT uses stochastic clustering of language tasks into varying turn depths for the same image to improve LVLMs on both single-turn and multi-turn scenarios without discarding data.
FineSightBench reveals VLMs perceive patterns down to 12px but show persistent failures in fine-scale reasoning such as numeracy and sequencing.
A group-revision paradigm for GRPO-based RL fine-tuning of VLMs converts failure responses into improvement signals that refine rewards and advantages, yielding gains on referring segmentation, REC, and counting benchmarks.
Deep Pre-Alignment uses a small VLM perceiver instead of ViT to pre-align visual features with LLM text space, yielding 1.9-3.0 point gains on multimodal benchmarks and 32.9% less language forgetting.
DiM3 is a direction- and magnitude-aware merging method that composes heterogeneous multilingual and multimodal updates in LLM backbones, outperforming baselines on 57-language benchmarks while retaining multimodal performance.
Visual replay module and adaptive depth scaling improve multimodal latent reasoning, reaching SOTA benchmarks with faster inference than explicit chain-of-thought methods.
DeepEyesV2 uses a two-stage cold-start plus reinforcement learning pipeline to produce an agentic multimodal model that adaptively invokes tools and outperforms direct RL on real-world reasoning benchmarks.
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.
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.
An inference-time technique that uses token activation dynamics to adaptively restrict text attention to important visual tokens, improving VLM accuracy on VQA, grounding, counting, OCR, and hallucination benchmarks.
HDPO reframes tool efficiency as a conditional objective within accurate trajectories, enabling Metis to reduce tool invocations by orders of magnitude while raising reasoning accuracy.
citing papers explorer
No citing papers match the current filters.